voice-router-dev 0.8.9 → 0.9.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +67 -0
- package/dist/constants.d.mts +22 -20
- package/dist/constants.d.ts +22 -20
- package/dist/constants.js +24 -24
- package/dist/constants.mjs +24 -24
- package/dist/{field-configs-CSOt3yc9.d.mts → field-configs-DYiUtRUz.d.mts} +50 -505
- package/dist/{field-configs-CSOt3yc9.d.ts → field-configs-DYiUtRUz.d.ts} +50 -505
- package/dist/field-configs.d.mts +1 -1
- package/dist/field-configs.d.ts +1 -1
- package/dist/field-configs.js +118 -196
- package/dist/field-configs.mjs +118 -196
- package/dist/index.d.mts +1655 -1754
- package/dist/index.d.ts +1655 -1754
- package/dist/index.js +257 -296
- package/dist/index.mjs +257 -296
- package/dist/{speechToTextChunkResponseModel-B4kVoFc3.d.ts → speechToTextChunkResponseModel-CI-Aqxcr.d.ts} +2015 -1846
- package/dist/{speechToTextChunkResponseModel-DmajV4F-.d.mts → speechToTextChunkResponseModel-D8VJ-wz6.d.mts} +2015 -1846
- package/dist/webhooks.d.mts +70 -2
- package/dist/webhooks.d.ts +70 -2
- package/dist/webhooks.js +113 -1
- package/dist/webhooks.mjs +111 -1
- package/package.json +1 -1
package/dist/field-configs.js
CHANGED
|
@@ -300,9 +300,7 @@ var listenTranscribeQueryParams = import_zod.z.object({
|
|
|
300
300
|
),
|
|
301
301
|
dictation: import_zod.z.boolean().optional().describe("Dictation mode for controlling formatting with dictated speech"),
|
|
302
302
|
encoding: import_zod.z.enum(["linear16", "flac", "mulaw", "amr-nb", "amr-wb", "opus", "speex", "g729"]).optional().describe("Specify the expected encoding of your submitted audio"),
|
|
303
|
-
filler_words: import_zod.z.boolean().optional().describe(
|
|
304
|
-
'Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'
|
|
305
|
-
),
|
|
303
|
+
filler_words: import_zod.z.boolean().optional().describe('Filler Words can help transcribe interruptions in your audio, like "uh" and "um"'),
|
|
306
304
|
keyterm: import_zod.z.array(import_zod.z.string()).optional().describe(
|
|
307
305
|
"Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3"
|
|
308
306
|
),
|
|
@@ -992,10 +990,10 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
992
990
|
"The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details."
|
|
993
991
|
),
|
|
994
992
|
auto_chapters: import_zod3.z.boolean().optional().describe(
|
|
995
|
-
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
993
|
+
"Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
996
994
|
),
|
|
997
995
|
auto_highlights: import_zod3.z.boolean().optional().describe(
|
|
998
|
-
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
996
|
+
"Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights), either true or false"
|
|
999
997
|
),
|
|
1000
998
|
content_safety: import_zod3.z.boolean().optional().describe(
|
|
1001
999
|
"Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false"
|
|
@@ -1011,16 +1009,16 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1011
1009
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
1012
1010
|
)
|
|
1013
1011
|
).optional().describe(
|
|
1014
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1012
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
1015
1013
|
),
|
|
1016
1014
|
disfluencies: import_zod3.z.boolean().optional().describe(
|
|
1017
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
1015
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
1018
1016
|
),
|
|
1019
1017
|
domain: import_zod3.z.string().nullish().describe(
|
|
1020
1018
|
'Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages.\n\nSupported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If used with an unsupported language, the parameter is ignored and a warning is returned.\n'
|
|
1021
1019
|
),
|
|
1022
1020
|
entity_detection: import_zod3.z.boolean().optional().describe(
|
|
1023
|
-
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1021
|
+
"Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript), can be true or false"
|
|
1024
1022
|
),
|
|
1025
1023
|
filter_profanity: import_zod3.z.boolean().optional().describe(
|
|
1026
1024
|
"Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details."
|
|
@@ -1029,7 +1027,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1029
1027
|
"Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false"
|
|
1030
1028
|
),
|
|
1031
1029
|
iab_categories: import_zod3.z.boolean().optional().describe(
|
|
1032
|
-
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1030
|
+
"Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics), can be true or false"
|
|
1033
1031
|
),
|
|
1034
1032
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
1035
1033
|
"Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/keyterms-prompting) for more details.\n"
|
|
@@ -1277,7 +1275,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1277
1275
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
1278
1276
|
),
|
|
1279
1277
|
multichannel: import_zod3.z.boolean().optional().describe(
|
|
1280
|
-
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1278
|
+
"Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false."
|
|
1281
1279
|
),
|
|
1282
1280
|
prompt: import_zod3.z.string().optional().describe(
|
|
1283
1281
|
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
@@ -1360,23 +1358,23 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1360
1358
|
"The replacement logic for detected PII, can be `entity_type` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
1361
1359
|
),
|
|
1362
1360
|
sentiment_analysis: import_zod3.z.boolean().optional().describe(
|
|
1363
|
-
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
1361
|
+
"Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech), can be true or false"
|
|
1364
1362
|
),
|
|
1365
1363
|
speaker_labels: import_zod3.z.boolean().optional().describe(
|
|
1366
|
-
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1364
|
+
"Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false"
|
|
1367
1365
|
),
|
|
1368
1366
|
speaker_options: import_zod3.z.object({
|
|
1369
1367
|
min_speakers_expected: import_zod3.z.number().default(createTranscriptBodySpeakerOptionsMinSpeakersExpectedDefault).describe(
|
|
1370
|
-
"The minimum number of speakers expected in the audio file. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1368
|
+
"The minimum number of speakers expected in the audio file. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details."
|
|
1371
1369
|
),
|
|
1372
1370
|
max_speakers_expected: import_zod3.z.number().optional().describe(
|
|
1373
|
-
"<Warning>Setting this parameter too high may hurt model accuracy</Warning>\nThe maximum number of speakers expected in the audio file. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1371
|
+
"<Warning>Setting this parameter too high may hurt model accuracy</Warning>\nThe maximum number of speakers expected in the audio file. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.\n"
|
|
1374
1372
|
)
|
|
1375
1373
|
}).optional().describe(
|
|
1376
|
-
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1374
|
+
"Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers). Use this to set a range of possible speakers."
|
|
1377
1375
|
),
|
|
1378
1376
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
1379
|
-
"Tells the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1377
|
+
"Tells the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details."
|
|
1380
1378
|
),
|
|
1381
1379
|
speech_models: import_zod3.z.array(
|
|
1382
1380
|
import_zod3.z.string().describe(
|
|
@@ -1452,7 +1450,7 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1452
1450
|
"Enable speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.\n"
|
|
1453
1451
|
),
|
|
1454
1452
|
summarization: import_zod3.z.boolean().optional().describe(
|
|
1455
|
-
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
1453
|
+
"Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
1456
1454
|
),
|
|
1457
1455
|
summary_model: import_zod3.z.enum(["informative", "conversational", "catchy"]).optional().describe("The model to summarize the transcript"),
|
|
1458
1456
|
summary_type: import_zod3.z.enum(["bullets", "bullets_verbose", "gist", "headline", "paragraph"]).optional().describe("The type of summary"),
|
|
@@ -1461,6 +1459,9 @@ var createTranscriptBody = import_zod3.z.object({
|
|
|
1461
1459
|
).or(import_zod3.z.null()).optional().describe(
|
|
1462
1460
|
'Remove [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) from the transcript text. Set to `"all"` to remove all audio tags.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n'
|
|
1463
1461
|
),
|
|
1462
|
+
temperature: import_zod3.z.number().optional().describe(
|
|
1463
|
+
"Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
1464
|
+
),
|
|
1464
1465
|
webhook_auth_header_name: import_zod3.z.string().nullish().describe(
|
|
1465
1466
|
"The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests"
|
|
1466
1467
|
),
|
|
@@ -1479,7 +1480,7 @@ var createTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThres
|
|
|
1479
1480
|
var createTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
1480
1481
|
var createTranscriptResponse = import_zod3.z.object({
|
|
1481
1482
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
1482
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1483
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
1483
1484
|
),
|
|
1484
1485
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
1485
1486
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -1490,10 +1491,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1490
1491
|
),
|
|
1491
1492
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
1492
1493
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
1493
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
1494
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
1494
1495
|
),
|
|
1495
1496
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
1496
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
1497
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
1497
1498
|
),
|
|
1498
1499
|
auto_highlights_result: import_zod3.z.object({
|
|
1499
1500
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -1513,9 +1514,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1513
1514
|
})
|
|
1514
1515
|
).describe("A temporally-sequential array of Key Phrases")
|
|
1515
1516
|
}).describe(
|
|
1516
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
1517
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
1517
1518
|
).or(import_zod3.z.null()).optional().describe(
|
|
1518
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
1519
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
1519
1520
|
),
|
|
1520
1521
|
chapters: import_zod3.z.array(
|
|
1521
1522
|
import_zod3.z.object({
|
|
@@ -1528,7 +1529,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1528
1529
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
1529
1530
|
}).describe("Chapter of the audio file")
|
|
1530
1531
|
).nullish().describe(
|
|
1531
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
1532
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
1532
1533
|
),
|
|
1533
1534
|
confidence: import_zod3.z.number().nullish().describe(
|
|
1534
1535
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -1584,10 +1585,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1584
1585
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
1585
1586
|
)
|
|
1586
1587
|
).nullish().describe(
|
|
1587
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1588
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
1588
1589
|
),
|
|
1589
1590
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
1590
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
1591
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
1591
1592
|
),
|
|
1592
1593
|
domain: import_zod3.z.string().nullish().describe(
|
|
1593
1594
|
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
@@ -1649,10 +1650,10 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1649
1650
|
)
|
|
1650
1651
|
}).describe("A detected entity")
|
|
1651
1652
|
).nullish().describe(
|
|
1652
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1653
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
1653
1654
|
),
|
|
1654
1655
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
1655
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1656
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
1656
1657
|
),
|
|
1657
1658
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
1658
1659
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -1662,7 +1663,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1662
1663
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
1663
1664
|
),
|
|
1664
1665
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
1665
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1666
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
1666
1667
|
),
|
|
1667
1668
|
iab_categories_result: import_zod3.z.object({
|
|
1668
1669
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -1685,9 +1686,9 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1685
1686
|
).describe("An array of results for the Topic Detection model"),
|
|
1686
1687
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
1687
1688
|
}).describe(
|
|
1688
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1689
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
1689
1690
|
).or(import_zod3.z.null()).optional().describe(
|
|
1690
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
1691
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
1691
1692
|
),
|
|
1692
1693
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
1693
1694
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -1937,7 +1938,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
1937
1938
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
1938
1939
|
),
|
|
1939
1940
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
1940
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
1941
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
1941
1942
|
),
|
|
1942
1943
|
prompt: import_zod3.z.string().optional().describe(
|
|
1943
1944
|
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
@@ -2020,7 +2021,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2020
2021
|
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
2021
2022
|
),
|
|
2022
2023
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
2023
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
2024
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
2024
2025
|
),
|
|
2025
2026
|
sentiment_analysis_results: import_zod3.z.array(
|
|
2026
2027
|
import_zod3.z.object({
|
|
@@ -2035,17 +2036,17 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2035
2036
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
2036
2037
|
),
|
|
2037
2038
|
speaker: import_zod3.z.string().nullable().describe(
|
|
2038
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2039
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
2039
2040
|
)
|
|
2040
2041
|
}).describe("The result of the Sentiment Analysis model")
|
|
2041
2042
|
).nullish().describe(
|
|
2042
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
2043
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
2043
2044
|
),
|
|
2044
2045
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
2045
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2046
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
2046
2047
|
),
|
|
2047
2048
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
2048
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2049
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details."
|
|
2049
2050
|
),
|
|
2050
2051
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
2051
2052
|
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
@@ -2148,22 +2149,25 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2148
2149
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
2149
2150
|
),
|
|
2150
2151
|
summarization: import_zod3.z.boolean().describe(
|
|
2151
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2152
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
2152
2153
|
),
|
|
2153
2154
|
summary: import_zod3.z.string().nullish().describe(
|
|
2154
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2155
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
2155
2156
|
),
|
|
2156
2157
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
2157
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2158
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n"
|
|
2158
2159
|
),
|
|
2159
2160
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
2160
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2161
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
2161
2162
|
),
|
|
2162
2163
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
2163
2164
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
2164
2165
|
).or(import_zod3.z.null()).optional().describe(
|
|
2165
2166
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
2166
2167
|
),
|
|
2168
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
2169
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
2170
|
+
),
|
|
2167
2171
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
2168
2172
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
2169
2173
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -2184,7 +2188,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2184
2188
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
2185
2189
|
),
|
|
2186
2190
|
speaker: import_zod3.z.string().nullable().describe(
|
|
2187
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2191
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
2188
2192
|
)
|
|
2189
2193
|
})
|
|
2190
2194
|
).describe("The words in the utterance."),
|
|
@@ -2199,7 +2203,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2199
2203
|
)
|
|
2200
2204
|
})
|
|
2201
2205
|
).nullish().describe(
|
|
2202
|
-
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2206
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
2203
2207
|
),
|
|
2204
2208
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
2205
2209
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -2223,7 +2227,7 @@ var createTranscriptResponse = import_zod3.z.object({
|
|
|
2223
2227
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
2224
2228
|
),
|
|
2225
2229
|
speaker: import_zod3.z.string().nullable().describe(
|
|
2226
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2230
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
2227
2231
|
)
|
|
2228
2232
|
})
|
|
2229
2233
|
).nullish().describe(
|
|
@@ -2292,7 +2296,7 @@ var getTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThreshol
|
|
|
2292
2296
|
var getTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
2293
2297
|
var getTranscriptResponse = import_zod3.z.object({
|
|
2294
2298
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
2295
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2299
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
2296
2300
|
),
|
|
2297
2301
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
2298
2302
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -2303,10 +2307,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2303
2307
|
),
|
|
2304
2308
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
2305
2309
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
2306
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
2310
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
2307
2311
|
),
|
|
2308
2312
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
2309
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
2313
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
2310
2314
|
),
|
|
2311
2315
|
auto_highlights_result: import_zod3.z.object({
|
|
2312
2316
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -2326,9 +2330,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2326
2330
|
})
|
|
2327
2331
|
).describe("A temporally-sequential array of Key Phrases")
|
|
2328
2332
|
}).describe(
|
|
2329
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
2333
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
2330
2334
|
).or(import_zod3.z.null()).optional().describe(
|
|
2331
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
2335
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
2332
2336
|
),
|
|
2333
2337
|
chapters: import_zod3.z.array(
|
|
2334
2338
|
import_zod3.z.object({
|
|
@@ -2341,7 +2345,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2341
2345
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
2342
2346
|
}).describe("Chapter of the audio file")
|
|
2343
2347
|
).nullish().describe(
|
|
2344
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
2348
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
2345
2349
|
),
|
|
2346
2350
|
confidence: import_zod3.z.number().nullish().describe(
|
|
2347
2351
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -2397,10 +2401,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2397
2401
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
2398
2402
|
)
|
|
2399
2403
|
).nullish().describe(
|
|
2400
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2404
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
2401
2405
|
),
|
|
2402
2406
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
2403
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
2407
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
2404
2408
|
),
|
|
2405
2409
|
domain: import_zod3.z.string().nullish().describe(
|
|
2406
2410
|
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
@@ -2462,10 +2466,10 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2462
2466
|
)
|
|
2463
2467
|
}).describe("A detected entity")
|
|
2464
2468
|
).nullish().describe(
|
|
2465
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
2469
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
2466
2470
|
),
|
|
2467
2471
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
2468
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
2472
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
2469
2473
|
),
|
|
2470
2474
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
2471
2475
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -2475,7 +2479,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2475
2479
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
2476
2480
|
),
|
|
2477
2481
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
2478
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
2482
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
2479
2483
|
),
|
|
2480
2484
|
iab_categories_result: import_zod3.z.object({
|
|
2481
2485
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -2498,9 +2502,9 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2498
2502
|
).describe("An array of results for the Topic Detection model"),
|
|
2499
2503
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
2500
2504
|
}).describe(
|
|
2501
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
2505
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
2502
2506
|
).or(import_zod3.z.null()).optional().describe(
|
|
2503
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
2507
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
2504
2508
|
),
|
|
2505
2509
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
2506
2510
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -2750,7 +2754,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2750
2754
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
2751
2755
|
),
|
|
2752
2756
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
2753
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2757
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
2754
2758
|
),
|
|
2755
2759
|
prompt: import_zod3.z.string().optional().describe(
|
|
2756
2760
|
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
@@ -2833,7 +2837,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2833
2837
|
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
2834
2838
|
),
|
|
2835
2839
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
2836
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
2840
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
2837
2841
|
),
|
|
2838
2842
|
sentiment_analysis_results: import_zod3.z.array(
|
|
2839
2843
|
import_zod3.z.object({
|
|
@@ -2848,17 +2852,17 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2848
2852
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
2849
2853
|
),
|
|
2850
2854
|
speaker: import_zod3.z.string().nullable().describe(
|
|
2851
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2855
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
2852
2856
|
)
|
|
2853
2857
|
}).describe("The result of the Sentiment Analysis model")
|
|
2854
2858
|
).nullish().describe(
|
|
2855
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
2859
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
2856
2860
|
),
|
|
2857
2861
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
2858
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2862
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
2859
2863
|
),
|
|
2860
2864
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
2861
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
2865
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details."
|
|
2862
2866
|
),
|
|
2863
2867
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
2864
2868
|
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
@@ -2961,22 +2965,25 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2961
2965
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
2962
2966
|
),
|
|
2963
2967
|
summarization: import_zod3.z.boolean().describe(
|
|
2964
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2968
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
2965
2969
|
),
|
|
2966
2970
|
summary: import_zod3.z.string().nullish().describe(
|
|
2967
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2971
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
2968
2972
|
),
|
|
2969
2973
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
2970
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2974
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n"
|
|
2971
2975
|
),
|
|
2972
2976
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
2973
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
2977
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
2974
2978
|
),
|
|
2975
2979
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
2976
2980
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
2977
2981
|
).or(import_zod3.z.null()).optional().describe(
|
|
2978
2982
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
2979
2983
|
),
|
|
2984
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
2985
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
2986
|
+
),
|
|
2980
2987
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
2981
2988
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
2982
2989
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -2997,7 +3004,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
2997
3004
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
2998
3005
|
),
|
|
2999
3006
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3000
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3007
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3001
3008
|
)
|
|
3002
3009
|
})
|
|
3003
3010
|
).describe("The words in the utterance."),
|
|
@@ -3012,7 +3019,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
3012
3019
|
)
|
|
3013
3020
|
})
|
|
3014
3021
|
).nullish().describe(
|
|
3015
|
-
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3022
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
3016
3023
|
),
|
|
3017
3024
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
3018
3025
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -3036,7 +3043,7 @@ var getTranscriptResponse = import_zod3.z.object({
|
|
|
3036
3043
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3037
3044
|
),
|
|
3038
3045
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3039
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3046
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3040
3047
|
)
|
|
3041
3048
|
})
|
|
3042
3049
|
).nullish().describe(
|
|
@@ -3066,7 +3073,7 @@ var deleteTranscriptResponseLanguageDetectionOptionsCodeSwitchingConfidenceThres
|
|
|
3066
3073
|
var deleteTranscriptResponseSpeechUnderstandingRequestTranslationFormalDefault = true;
|
|
3067
3074
|
var deleteTranscriptResponse = import_zod3.z.object({
|
|
3068
3075
|
audio_channels: import_zod3.z.number().optional().describe(
|
|
3069
|
-
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3076
|
+
"The number of audio channels in the audio file. This is only present when [multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) is enabled."
|
|
3070
3077
|
),
|
|
3071
3078
|
audio_duration: import_zod3.z.number().nullish().describe("The duration of this transcript object's media file, in seconds"),
|
|
3072
3079
|
audio_end_at: import_zod3.z.number().nullish().describe(
|
|
@@ -3077,10 +3084,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3077
3084
|
),
|
|
3078
3085
|
audio_url: import_zod3.z.string().describe("The URL of the media that was transcribed"),
|
|
3079
3086
|
auto_chapters: import_zod3.z.boolean().nullish().describe(
|
|
3080
|
-
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
3087
|
+
"Whether [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) is enabled, can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
3081
3088
|
),
|
|
3082
3089
|
auto_highlights: import_zod3.z.boolean().describe(
|
|
3083
|
-
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
3090
|
+
"Whether [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) is enabled, either true or false"
|
|
3084
3091
|
),
|
|
3085
3092
|
auto_highlights_result: import_zod3.z.object({
|
|
3086
3093
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -3100,9 +3107,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3100
3107
|
})
|
|
3101
3108
|
).describe("A temporally-sequential array of Key Phrases")
|
|
3102
3109
|
}).describe(
|
|
3103
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
3110
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
3104
3111
|
).or(import_zod3.z.null()).optional().describe(
|
|
3105
|
-
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/
|
|
3112
|
+
"An array of results for the Key Phrases model, if it is enabled.\nSee [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/identify-highlights) for more information.\n"
|
|
3106
3113
|
),
|
|
3107
3114
|
chapters: import_zod3.z.array(
|
|
3108
3115
|
import_zod3.z.object({
|
|
@@ -3115,7 +3122,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3115
3122
|
end: import_zod3.z.number().describe("The starting time, in milliseconds, for the chapter")
|
|
3116
3123
|
}).describe("Chapter of the audio file")
|
|
3117
3124
|
).nullish().describe(
|
|
3118
|
-
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/
|
|
3125
|
+
"An array of temporally sequential chapters for the audio file. See [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/create-summarized-chapters) for more information."
|
|
3119
3126
|
),
|
|
3120
3127
|
confidence: import_zod3.z.number().nullish().describe(
|
|
3121
3128
|
"The confidence score for the transcript, between 0.0 (low confidence) and 1.0 (high confidence)"
|
|
@@ -3171,10 +3178,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3171
3178
|
"Object containing words or phrases to replace, and the word or phrase to replace with"
|
|
3172
3179
|
)
|
|
3173
3180
|
).nullish().describe(
|
|
3174
|
-
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3181
|
+
"Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details."
|
|
3175
3182
|
),
|
|
3176
3183
|
disfluencies: import_zod3.z.boolean().nullish().describe(
|
|
3177
|
-
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/filler-words), like "umm", in your media file; can be true or false'
|
|
3184
|
+
'Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false'
|
|
3178
3185
|
),
|
|
3179
3186
|
domain: import_zod3.z.string().nullish().describe(
|
|
3180
3187
|
'The domain-specific model applied to the transcript. When set to `"medical-v1"`, [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) was used to improve accuracy for medical terminology.\n'
|
|
@@ -3236,10 +3243,10 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3236
3243
|
)
|
|
3237
3244
|
}).describe("A detected entity")
|
|
3238
3245
|
).nullish().describe(
|
|
3239
|
-
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
3246
|
+
"An array of results for the Entity Detection model, if it is enabled.\nSee [Entity detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) for more information.\n"
|
|
3240
3247
|
),
|
|
3241
3248
|
entity_detection: import_zod3.z.boolean().nullish().describe(
|
|
3242
|
-
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
3249
|
+
"Whether [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/detect-entities-in-transcript) is enabled, can be true or false"
|
|
3243
3250
|
),
|
|
3244
3251
|
error: import_zod3.z.string().optional().describe("Error message of why the transcript failed"),
|
|
3245
3252
|
filter_profanity: import_zod3.z.boolean().nullish().describe(
|
|
@@ -3249,7 +3256,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3249
3256
|
"Whether [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio) is enabled, either true or false"
|
|
3250
3257
|
),
|
|
3251
3258
|
iab_categories: import_zod3.z.boolean().nullish().describe(
|
|
3252
|
-
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
3259
|
+
"Whether [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) is enabled, can be true or false"
|
|
3253
3260
|
),
|
|
3254
3261
|
iab_categories_result: import_zod3.z.object({
|
|
3255
3262
|
status: import_zod3.z.enum(["success", "unavailable"]).describe("Either success, or unavailable in the rare case that the model failed"),
|
|
@@ -3272,9 +3279,9 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3272
3279
|
).describe("An array of results for the Topic Detection model"),
|
|
3273
3280
|
summary: import_zod3.z.record(import_zod3.z.string(), import_zod3.z.number()).describe("The overall relevance of topic to the entire audio file")
|
|
3274
3281
|
}).describe(
|
|
3275
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
3282
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
3276
3283
|
).or(import_zod3.z.null()).optional().describe(
|
|
3277
|
-
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/
|
|
3284
|
+
"The result of the Topic Detection model, if it is enabled.\nSee [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/detect-discussion-topics) for more information.\n"
|
|
3278
3285
|
),
|
|
3279
3286
|
id: import_zod3.z.string().uuid().describe("The unique identifier of your transcript"),
|
|
3280
3287
|
keyterms_prompt: import_zod3.z.array(import_zod3.z.string()).optional().describe(
|
|
@@ -3524,7 +3531,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3524
3531
|
"Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection)."
|
|
3525
3532
|
),
|
|
3526
3533
|
multichannel: import_zod3.z.boolean().nullish().describe(
|
|
3527
|
-
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3534
|
+
"Whether [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) was enabled in the transcription request, either true or false"
|
|
3528
3535
|
),
|
|
3529
3536
|
prompt: import_zod3.z.string().optional().describe(
|
|
3530
3537
|
"Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
@@ -3607,7 +3614,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3607
3614
|
"The replacement logic for detected PII, can be `entity_name` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details."
|
|
3608
3615
|
),
|
|
3609
3616
|
sentiment_analysis: import_zod3.z.boolean().nullish().describe(
|
|
3610
|
-
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
3617
|
+
"Whether [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) is enabled, can be true or false"
|
|
3611
3618
|
),
|
|
3612
3619
|
sentiment_analysis_results: import_zod3.z.array(
|
|
3613
3620
|
import_zod3.z.object({
|
|
@@ -3622,17 +3629,17 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3622
3629
|
"The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3623
3630
|
),
|
|
3624
3631
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3625
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3632
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3626
3633
|
)
|
|
3627
3634
|
}).describe("The result of the Sentiment Analysis model")
|
|
3628
3635
|
).nullish().describe(
|
|
3629
|
-
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-
|
|
3636
|
+
"An array of results for the Sentiment Analysis model, if it is enabled.\nSee [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/analyze-sentiment-of-speech) for more information.\n"
|
|
3630
3637
|
),
|
|
3631
3638
|
speaker_labels: import_zod3.z.boolean().nullish().describe(
|
|
3632
|
-
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3639
|
+
"Whether [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, can be true or false"
|
|
3633
3640
|
),
|
|
3634
3641
|
speakers_expected: import_zod3.z.number().nullish().describe(
|
|
3635
|
-
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3642
|
+
"Tell the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details."
|
|
3636
3643
|
),
|
|
3637
3644
|
speech_model_used: import_zod3.z.string().optional().describe(
|
|
3638
3645
|
"The speech model to use for the transcription. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models."
|
|
@@ -3735,22 +3742,25 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3735
3742
|
"The status of your transcript. Possible values are queued, processing, completed, or error."
|
|
3736
3743
|
),
|
|
3737
3744
|
summarization: import_zod3.z.boolean().describe(
|
|
3738
|
-
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
3745
|
+
"Whether [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled, either true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n\nNote: This parameter is only supported for the Universal-2 model.\n"
|
|
3739
3746
|
),
|
|
3740
3747
|
summary: import_zod3.z.string().nullish().describe(
|
|
3741
|
-
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
3748
|
+
"The generated summary of the media file, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
3742
3749
|
),
|
|
3743
3750
|
summary_model: import_zod3.z.string().nullish().describe(
|
|
3744
|
-
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
3751
|
+
"The Summarization model used to generate the summary,\nif [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-models) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details.\n"
|
|
3745
3752
|
),
|
|
3746
3753
|
summary_type: import_zod3.z.string().nullish().describe(
|
|
3747
|
-
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/
|
|
3754
|
+
"The type of summary generated, if [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts#summary-types) is enabled. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarize-transcripts) for details."
|
|
3748
3755
|
),
|
|
3749
3756
|
remove_audio_tags: import_zod3.z.enum(["all"]).describe(
|
|
3750
3757
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
3751
3758
|
).or(import_zod3.z.null()).optional().describe(
|
|
3752
3759
|
"Whether [audio event tags](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro#audio-event-tags) were removed from the transcript text.\n\nNote: This parameter is only supported for the Universal-3 Pro model.\n"
|
|
3753
3760
|
),
|
|
3761
|
+
temperature: import_zod3.z.number().nullish().describe(
|
|
3762
|
+
"The temperature that was used for the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details.\n\nNote: This parameter can only be used with the Universal-3 Pro model.\n"
|
|
3763
|
+
),
|
|
3754
3764
|
text: import_zod3.z.string().nullish().describe("The textual transcript of your media file"),
|
|
3755
3765
|
throttled: import_zod3.z.boolean().nullish().describe(
|
|
3756
3766
|
"True while a request is throttled and false when a request is no longer throttled"
|
|
@@ -3771,7 +3781,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3771
3781
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3772
3782
|
),
|
|
3773
3783
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3774
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3784
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3775
3785
|
)
|
|
3776
3786
|
})
|
|
3777
3787
|
).describe("The words in the utterance."),
|
|
@@ -3786,7 +3796,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3786
3796
|
)
|
|
3787
3797
|
})
|
|
3788
3798
|
).nullish().describe(
|
|
3789
|
-
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3799
|
+
"When multichannel or speaker_labels is enabled, a list of turn-by-turn utterance objects.\nSee [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) and [Multichannel transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) for more information.\n"
|
|
3790
3800
|
),
|
|
3791
3801
|
webhook_auth: import_zod3.z.boolean().describe(
|
|
3792
3802
|
"Whether [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) authentication details were provided"
|
|
@@ -3810,7 +3820,7 @@ var deleteTranscriptResponse = import_zod3.z.object({
|
|
|
3810
3820
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3811
3821
|
),
|
|
3812
3822
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3813
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3823
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3814
3824
|
)
|
|
3815
3825
|
})
|
|
3816
3826
|
).nullish().describe(
|
|
@@ -3855,7 +3865,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
3855
3865
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3856
3866
|
),
|
|
3857
3867
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3858
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3868
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3859
3869
|
)
|
|
3860
3870
|
})
|
|
3861
3871
|
).describe("An array of words in the sentence"),
|
|
@@ -3863,7 +3873,7 @@ var getTranscriptSentencesResponse = import_zod3.z.object({
|
|
|
3863
3873
|
"The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3864
3874
|
),
|
|
3865
3875
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3866
|
-
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3876
|
+
"The speaker of the sentence if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3867
3877
|
)
|
|
3868
3878
|
})
|
|
3869
3879
|
).describe("An array of sentences in the transcript")
|
|
@@ -3891,7 +3901,7 @@ var getTranscriptParagraphsResponse = import_zod3.z.object({
|
|
|
3891
3901
|
"The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially."
|
|
3892
3902
|
),
|
|
3893
3903
|
speaker: import_zod3.z.string().nullable().describe(
|
|
3894
|
-
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/
|
|
3904
|
+
"The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null"
|
|
3895
3905
|
)
|
|
3896
3906
|
})
|
|
3897
3907
|
).describe("An array of words in the paragraph")
|
|
@@ -5770,23 +5780,6 @@ var preRecordedControllerGetPreRecordedJobsV2Response = import_zod5.z.object({
|
|
|
5770
5780
|
}).optional().describe(
|
|
5771
5781
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
5772
5782
|
),
|
|
5773
|
-
speaker_reidentification: import_zod5.z.object({
|
|
5774
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
5775
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
5776
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
5777
|
-
error: import_zod5.z.object({
|
|
5778
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
5779
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
5780
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
5781
|
-
}).nullable().describe(
|
|
5782
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
5783
|
-
),
|
|
5784
|
-
results: import_zod5.z.string().describe(
|
|
5785
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
5786
|
-
)
|
|
5787
|
-
}).optional().describe(
|
|
5788
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
5789
|
-
),
|
|
5790
5783
|
structured_data_extraction: import_zod5.z.object({
|
|
5791
5784
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
5792
5785
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -7251,23 +7244,6 @@ var preRecordedControllerGetPreRecordedJobV2Response = import_zod5.z.object({
|
|
|
7251
7244
|
}).optional().describe(
|
|
7252
7245
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
7253
7246
|
),
|
|
7254
|
-
speaker_reidentification: import_zod5.z.object({
|
|
7255
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
7256
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
7257
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
7258
|
-
error: import_zod5.z.object({
|
|
7259
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
7260
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
7261
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
7262
|
-
}).nullable().describe(
|
|
7263
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
7264
|
-
),
|
|
7265
|
-
results: import_zod5.z.string().describe(
|
|
7266
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
7267
|
-
)
|
|
7268
|
-
}).optional().describe(
|
|
7269
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
7270
|
-
),
|
|
7271
7247
|
structured_data_extraction: import_zod5.z.object({
|
|
7272
7248
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
7273
7249
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -9355,23 +9331,6 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
9355
9331
|
}).optional().describe(
|
|
9356
9332
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
9357
9333
|
),
|
|
9358
|
-
speaker_reidentification: import_zod5.z.object({
|
|
9359
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
9360
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
9361
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
9362
|
-
error: import_zod5.z.object({
|
|
9363
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
9364
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
9365
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
9366
|
-
}).nullable().describe(
|
|
9367
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
9368
|
-
),
|
|
9369
|
-
results: import_zod5.z.string().describe(
|
|
9370
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
9371
|
-
)
|
|
9372
|
-
}).optional().describe(
|
|
9373
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
9374
|
-
),
|
|
9375
9334
|
structured_data_extraction: import_zod5.z.object({
|
|
9376
9335
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
9377
9336
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -9671,11 +9630,7 @@ var transcriptionControllerListV2Response = import_zod5.z.object({
|
|
|
9671
9630
|
channels: import_zod5.z.number().min(1).max(transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsMax).default(
|
|
9672
9631
|
transcriptionControllerListV2ResponseItemsItemRequestParamsChannelsDefault
|
|
9673
9632
|
).describe("The number of channels of the audio stream"),
|
|
9674
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
9675
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
9676
|
-
).default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe(
|
|
9677
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
9678
|
-
),
|
|
9633
|
+
model: import_zod5.z.enum(["solaria-1"]).describe('The model used to process the audio. "solaria-1" is used by default.').default(transcriptionControllerListV2ResponseItemsItemRequestParamsModelDefault).describe('The model used to process the audio. "solaria-1" is used by default.'),
|
|
9679
9634
|
endpointing: import_zod5.z.number().min(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMin).max(transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
9680
9635
|
transcriptionControllerListV2ResponseItemsItemRequestParamsEndpointingDefault
|
|
9681
9636
|
).describe(
|
|
@@ -12065,23 +12020,6 @@ var transcriptionControllerGetTranscriptV2Response = import_zod5.z.discriminated
|
|
|
12065
12020
|
}).optional().describe(
|
|
12066
12021
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
12067
12022
|
),
|
|
12068
|
-
speaker_reidentification: import_zod5.z.object({
|
|
12069
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
12070
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
12071
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
12072
|
-
error: import_zod5.z.object({
|
|
12073
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
12074
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
12075
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
12076
|
-
}).nullable().describe(
|
|
12077
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
12078
|
-
),
|
|
12079
|
-
results: import_zod5.z.string().describe(
|
|
12080
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
12081
|
-
)
|
|
12082
|
-
}).optional().describe(
|
|
12083
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
12084
|
-
),
|
|
12085
12023
|
structured_data_extraction: import_zod5.z.object({
|
|
12086
12024
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
12087
12025
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -15204,23 +15142,6 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
15204
15142
|
}).optional().describe(
|
|
15205
15143
|
"If `name_consistency` has been enabled, Gladia will improve consistency of the names accross the transcription"
|
|
15206
15144
|
),
|
|
15207
|
-
speaker_reidentification: import_zod5.z.object({
|
|
15208
|
-
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
15209
|
-
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
15210
|
-
exec_time: import_zod5.z.number().describe("Time audio intelligence model took to complete the task"),
|
|
15211
|
-
error: import_zod5.z.object({
|
|
15212
|
-
status_code: import_zod5.z.number().describe("Status code of the addon error"),
|
|
15213
|
-
exception: import_zod5.z.string().describe("Reason of the addon error"),
|
|
15214
|
-
message: import_zod5.z.string().describe("Detailed message of the addon error")
|
|
15215
|
-
}).nullable().describe(
|
|
15216
|
-
"`null` if `success` is `true`. Contains the error details of the failed model"
|
|
15217
|
-
),
|
|
15218
|
-
results: import_zod5.z.string().describe(
|
|
15219
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
15220
|
-
)
|
|
15221
|
-
}).optional().describe(
|
|
15222
|
-
"If `speaker_reidentification` has been enabled, results of the AI speaker reidentification."
|
|
15223
|
-
),
|
|
15224
15145
|
structured_data_extraction: import_zod5.z.object({
|
|
15225
15146
|
success: import_zod5.z.boolean().describe("The audio intelligence model succeeded to get a valid output"),
|
|
15226
15147
|
is_empty: import_zod5.z.boolean().describe("The audio intelligence model returned an empty value"),
|
|
@@ -15514,11 +15435,7 @@ var historyControllerGetListV1Response = import_zod5.z.object({
|
|
|
15514
15435
|
historyControllerGetListV1ResponseItemsItemRequestParamsSampleRateDefault
|
|
15515
15436
|
).describe("The sample rate of the audio stream"),
|
|
15516
15437
|
channels: import_zod5.z.number().min(1).max(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsMax).default(historyControllerGetListV1ResponseItemsItemRequestParamsChannelsDefault).describe("The number of channels of the audio stream"),
|
|
15517
|
-
model: import_zod5.z.enum(["solaria-1"]).describe(
|
|
15518
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
15519
|
-
).default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe(
|
|
15520
|
-
'The model used to process the audio. "solaria-1" is used by default.'
|
|
15521
|
-
),
|
|
15438
|
+
model: import_zod5.z.enum(["solaria-1"]).describe('The model used to process the audio. "solaria-1" is used by default.').default(historyControllerGetListV1ResponseItemsItemRequestParamsModelDefault).describe('The model used to process the audio. "solaria-1" is used by default.'),
|
|
15522
15439
|
endpointing: import_zod5.z.number().min(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMin).max(historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingMax).default(
|
|
15523
15440
|
historyControllerGetListV1ResponseItemsItemRequestParamsEndpointingDefault
|
|
15524
15441
|
).describe(
|
|
@@ -24580,11 +24497,11 @@ var getTranscriptionsResponse = import_zod10.z.object({
|
|
|
24580
24497
|
});
|
|
24581
24498
|
var createTranscriptionBodyModelMaxThree = 32;
|
|
24582
24499
|
var createTranscriptionBodyAudioUrlMaxOne = 4096;
|
|
24583
|
-
var createTranscriptionBodyAudioUrlRegExpOne =
|
|
24500
|
+
var createTranscriptionBodyAudioUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
24584
24501
|
var createTranscriptionBodyLanguageHintsItemMax = 10;
|
|
24585
24502
|
var createTranscriptionBodyLanguageHintsMaxOne = 100;
|
|
24586
24503
|
var createTranscriptionBodyWebhookUrlMaxOne = 256;
|
|
24587
|
-
var createTranscriptionBodyWebhookUrlRegExpOne =
|
|
24504
|
+
var createTranscriptionBodyWebhookUrlRegExpOne = /^https?:\/\/[^\s]+$/;
|
|
24588
24505
|
var createTranscriptionBodyWebhookAuthHeaderNameMaxOne = 256;
|
|
24589
24506
|
var createTranscriptionBodyWebhookAuthHeaderValueMaxOne = 256;
|
|
24590
24507
|
var createTranscriptionBodyClientReferenceIdMaxOne = 256;
|
|
@@ -24732,10 +24649,15 @@ var getModelsResponse = import_zod10.z.object({
|
|
|
24732
24649
|
});
|
|
24733
24650
|
var createTemporaryApiKeyBodyExpiresInSecondsMax = 3600;
|
|
24734
24651
|
var createTemporaryApiKeyBodyClientReferenceIdMaxOne = 256;
|
|
24652
|
+
var createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne = 18e3;
|
|
24735
24653
|
var createTemporaryApiKeyBody = import_zod10.z.object({
|
|
24736
24654
|
usage_type: import_zod10.z.enum(["transcribe_websocket"]),
|
|
24737
24655
|
expires_in_seconds: import_zod10.z.number().min(1).max(createTemporaryApiKeyBodyExpiresInSecondsMax).describe("Duration in seconds until the temporary API key expires."),
|
|
24738
|
-
client_reference_id: import_zod10.z.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(import_zod10.z.null()).optional().describe("Optional tracking identifier string. Does not need to be unique.")
|
|
24656
|
+
client_reference_id: import_zod10.z.string().max(createTemporaryApiKeyBodyClientReferenceIdMaxOne).or(import_zod10.z.null()).optional().describe("Optional tracking identifier string. Does not need to be unique."),
|
|
24657
|
+
single_use: import_zod10.z.boolean().or(import_zod10.z.null()).optional().describe("If true, the temporary API key can be used only once."),
|
|
24658
|
+
max_session_duration_seconds: import_zod10.z.number().min(1).max(createTemporaryApiKeyBodyMaxSessionDurationSecondsMaxOne).or(import_zod10.z.null()).optional().describe(
|
|
24659
|
+
"Maximum WebSocket connection duration in seconds. If exceeded, the connection will be dropped. If not set, no limit is applied."
|
|
24660
|
+
)
|
|
24739
24661
|
});
|
|
24740
24662
|
|
|
24741
24663
|
// src/generated/soniox/streaming-types.zod.ts
|