assemblyai 4.7.1 → 4.8.0
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 +9 -3
- package/dist/assemblyai.umd.js +1 -1
- package/dist/assemblyai.umd.min.js +1 -1
- package/dist/browser.mjs +1 -1
- package/dist/bun.mjs +1 -1
- package/dist/deno.mjs +1 -1
- package/dist/index.cjs +1 -1
- package/dist/index.mjs +1 -1
- package/dist/node.cjs +1 -1
- package/dist/node.mjs +1 -1
- package/dist/types/openapi.generated.d.ts +187 -30
- package/dist/workerd.mjs +1 -1
- package/package.json +4 -2
- package/src/types/openapi.generated.ts +187 -30
|
@@ -428,6 +428,9 @@ export type ContentSafetyLabelResult = {
|
|
|
428
428
|
* ```
|
|
429
429
|
*/
|
|
430
430
|
export type ContentSafetyLabelsResult = {
|
|
431
|
+
/**
|
|
432
|
+
* An array of results for the Content Moderation model
|
|
433
|
+
*/
|
|
431
434
|
results: ContentSafetyLabelResult[];
|
|
432
435
|
/**
|
|
433
436
|
* A summary of the Content Moderation severity results for the entire audio file
|
|
@@ -556,6 +559,7 @@ export type Error = {
|
|
|
556
559
|
*/
|
|
557
560
|
error: string;
|
|
558
561
|
status?: "error";
|
|
562
|
+
[key: string]: unknown;
|
|
559
563
|
};
|
|
560
564
|
|
|
561
565
|
/**
|
|
@@ -567,7 +571,7 @@ export type Error = {
|
|
|
567
571
|
* ],
|
|
568
572
|
* "context": "This is an interview about wildfires.",
|
|
569
573
|
* "answer_format": "Bullet Points",
|
|
570
|
-
* "final_model": "
|
|
574
|
+
* "final_model": "anthropic/claude-3-5-sonnet",
|
|
571
575
|
* "temperature": 0,
|
|
572
576
|
* "max_output_size": 3000
|
|
573
577
|
* }
|
|
@@ -607,7 +611,7 @@ export type LemurActionItemsResponse = LemurStringResponse;
|
|
|
607
611
|
* "7c3acd18-df4d-4432-88f5-1e89f8827eea"
|
|
608
612
|
* ],
|
|
609
613
|
* "context": "This is an interview about wildfires.",
|
|
610
|
-
* "final_model": "
|
|
614
|
+
* "final_model": "anthropic/claude-3-5-sonnet",
|
|
611
615
|
* "temperature": 0,
|
|
612
616
|
* "max_output_size": 3000
|
|
613
617
|
* }
|
|
@@ -638,12 +642,15 @@ export type LemurBaseParams = {
|
|
|
638
642
|
input_text?: string;
|
|
639
643
|
/**
|
|
640
644
|
* Max output size in tokens, up to 4000
|
|
645
|
+
* @defaultValue 2000
|
|
641
646
|
*/
|
|
642
647
|
max_output_size?: number;
|
|
643
648
|
/**
|
|
644
649
|
* The temperature to use for the model.
|
|
645
650
|
* Higher values result in answers that are more creative, lower values are more conservative.
|
|
646
651
|
* Can be any value between 0.0 and 1.0 inclusive.
|
|
652
|
+
*
|
|
653
|
+
* @defaultValue 0
|
|
647
654
|
*/
|
|
648
655
|
temperature?: number;
|
|
649
656
|
/**
|
|
@@ -773,7 +780,7 @@ export type LemurQuestionAnswer = {
|
|
|
773
780
|
* ]
|
|
774
781
|
* }
|
|
775
782
|
* ],
|
|
776
|
-
* "final_model": "
|
|
783
|
+
* "final_model": "anthropic/claude-3-5-sonnet",
|
|
777
784
|
* "temperature": 0,
|
|
778
785
|
* "max_output_size": 3000
|
|
779
786
|
* }
|
|
@@ -845,7 +852,7 @@ export type LemurStringResponse = {
|
|
|
845
852
|
* "47b95ba5-8889-44d8-bc80-5de38306e582"
|
|
846
853
|
* ],
|
|
847
854
|
* "context": "This is an interview about wildfires.",
|
|
848
|
-
* "final_model": "
|
|
855
|
+
* "final_model": "anthropic/claude-3-5-sonnet",
|
|
849
856
|
* "temperature": 0,
|
|
850
857
|
* "max_output_size": 3000
|
|
851
858
|
* }
|
|
@@ -882,7 +889,7 @@ export type LemurSummaryResponse = LemurStringResponse;
|
|
|
882
889
|
* ],
|
|
883
890
|
* "prompt": "List all the locations affected by wildfires.",
|
|
884
891
|
* "context": "This is an interview about wildfires.",
|
|
885
|
-
* "final_model": "
|
|
892
|
+
* "final_model": "anthropic/claude-3-5-sonnet",
|
|
886
893
|
* "temperature": 0,
|
|
887
894
|
* "max_output_size": 3000
|
|
888
895
|
* }
|
|
@@ -961,6 +968,7 @@ export type ListTranscriptParams = {
|
|
|
961
968
|
status?: TranscriptStatus;
|
|
962
969
|
/**
|
|
963
970
|
* Only get throttled transcripts, overrides the status filter
|
|
971
|
+
* @defaultValue false
|
|
964
972
|
*/
|
|
965
973
|
throttled_only?: boolean;
|
|
966
974
|
};
|
|
@@ -1079,9 +1087,21 @@ export type PageDetails = {
|
|
|
1079
1087
|
* ```
|
|
1080
1088
|
*/
|
|
1081
1089
|
export type ParagraphsResponse = {
|
|
1090
|
+
/**
|
|
1091
|
+
* The duration of the audio file in seconds
|
|
1092
|
+
*/
|
|
1082
1093
|
audio_duration: number;
|
|
1094
|
+
/**
|
|
1095
|
+
* The confidence score for the transcript
|
|
1096
|
+
*/
|
|
1083
1097
|
confidence: number;
|
|
1098
|
+
/**
|
|
1099
|
+
* The unique identifier of your transcript
|
|
1100
|
+
*/
|
|
1084
1101
|
id: string;
|
|
1102
|
+
/**
|
|
1103
|
+
* An array of paragraphs in the transcript
|
|
1104
|
+
*/
|
|
1085
1105
|
paragraphs: TranscriptParagraph[];
|
|
1086
1106
|
};
|
|
1087
1107
|
|
|
@@ -1183,7 +1203,7 @@ export type RedactedAudioNotification = RedactedAudioResponse;
|
|
|
1183
1203
|
* @example
|
|
1184
1204
|
* ```js
|
|
1185
1205
|
* {
|
|
1186
|
-
* "redacted_audio_url": "https://s3.us-west-2.amazonaws.com/api.assembly.ai.usw2/redacted-audio/785efd9e-0e20-45e1-967b-3db17770ed9f.wav?AWSAccessKeyId=
|
|
1206
|
+
* "redacted_audio_url": "https://s3.us-west-2.amazonaws.com/api.assembly.ai.usw2/redacted-audio/785efd9e-0e20-45e1-967b-3db17770ed9f.wav?AWSAccessKeyId=aws-access-key0id&Signature=signature&x-amz-security-token=security-token&Expires=1698966551",
|
|
1187
1207
|
* "status": "redacted_audio_ready"
|
|
1188
1208
|
* }
|
|
1189
1209
|
* ```
|
|
@@ -1206,7 +1226,6 @@ export type RedactedAudioStatus = "redacted_audio_ready";
|
|
|
1206
1226
|
|
|
1207
1227
|
/**
|
|
1208
1228
|
* Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See {@link https://www.assemblyai.com/docs/models/pii-redaction | PII redaction } for more details.
|
|
1209
|
-
* @defaultValue "mp3"
|
|
1210
1229
|
* @example "mp3"
|
|
1211
1230
|
*/
|
|
1212
1231
|
export type RedactPiiAudioQuality = "mp3" | "wav";
|
|
@@ -1312,9 +1331,21 @@ export type RedactPiiAudioQuality = "mp3" | "wav";
|
|
|
1312
1331
|
* ```
|
|
1313
1332
|
*/
|
|
1314
1333
|
export type SentencesResponse = {
|
|
1334
|
+
/**
|
|
1335
|
+
* The duration of the audio file in seconds
|
|
1336
|
+
*/
|
|
1315
1337
|
audio_duration: number;
|
|
1338
|
+
/**
|
|
1339
|
+
* The confidence score for the transcript
|
|
1340
|
+
*/
|
|
1316
1341
|
confidence: number;
|
|
1342
|
+
/**
|
|
1343
|
+
* The unique identifier for the transcript
|
|
1344
|
+
*/
|
|
1317
1345
|
id: string;
|
|
1346
|
+
/**
|
|
1347
|
+
* An array of sentences in the transcript
|
|
1348
|
+
*/
|
|
1318
1349
|
sentences: TranscriptSentence[];
|
|
1319
1350
|
};
|
|
1320
1351
|
|
|
@@ -1335,6 +1366,10 @@ export type Sentiment = "POSITIVE" | "NEUTRAL" | "NEGATIVE";
|
|
|
1335
1366
|
* ```
|
|
1336
1367
|
*/
|
|
1337
1368
|
export type SentimentAnalysisResult = {
|
|
1369
|
+
/**
|
|
1370
|
+
* The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
|
|
1371
|
+
*/
|
|
1372
|
+
channel?: string | null;
|
|
1338
1373
|
/**
|
|
1339
1374
|
* The confidence score for the detected sentiment of the sentence, from 0 to 1
|
|
1340
1375
|
*/
|
|
@@ -1350,7 +1385,7 @@ export type SentimentAnalysisResult = {
|
|
|
1350
1385
|
/**
|
|
1351
1386
|
* The speaker of the sentence if {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker Diarization } is enabled, else null
|
|
1352
1387
|
*/
|
|
1353
|
-
speaker
|
|
1388
|
+
speaker: string | null;
|
|
1354
1389
|
/**
|
|
1355
1390
|
* The starting time, in milliseconds, of the sentence
|
|
1356
1391
|
*/
|
|
@@ -1394,13 +1429,11 @@ export type SubtitleFormat = "srt" | "vtt";
|
|
|
1394
1429
|
|
|
1395
1430
|
/**
|
|
1396
1431
|
* The model to summarize the transcript
|
|
1397
|
-
* @defaultValue "informative
|
|
1398
1432
|
*/
|
|
1399
1433
|
export type SummaryModel = "informative" | "conversational" | "catchy";
|
|
1400
1434
|
|
|
1401
1435
|
/**
|
|
1402
1436
|
* The type of summary
|
|
1403
|
-
* @defaultValue bullets
|
|
1404
1437
|
*/
|
|
1405
1438
|
export type SummaryType =
|
|
1406
1439
|
| "bullets"
|
|
@@ -1414,7 +1447,7 @@ export type SummaryType =
|
|
|
1414
1447
|
* @example
|
|
1415
1448
|
* ```js
|
|
1416
1449
|
* {
|
|
1417
|
-
* "start": 3978
|
|
1450
|
+
* "start": 3978,
|
|
1418
1451
|
* "end": 5114
|
|
1419
1452
|
* }
|
|
1420
1453
|
* ```
|
|
@@ -1587,6 +1620,9 @@ export type TopicDetectionModelResult = {
|
|
|
1587
1620
|
* ```
|
|
1588
1621
|
*/
|
|
1589
1622
|
export type TopicDetectionResult = {
|
|
1623
|
+
/**
|
|
1624
|
+
* An array of detected topics in the text
|
|
1625
|
+
*/
|
|
1590
1626
|
labels?: {
|
|
1591
1627
|
/**
|
|
1592
1628
|
* The IAB taxonomical label for the label of the detected topic, where > denotes supertopic/subtopic relationship
|
|
@@ -1614,6 +1650,9 @@ export type TopicDetectionResult = {
|
|
|
1614
1650
|
* "language_model": "assemblyai_default",
|
|
1615
1651
|
* "acoustic_model": "assemblyai_default",
|
|
1616
1652
|
* "language_code": "en_us",
|
|
1653
|
+
* "language_detection": true,
|
|
1654
|
+
* "language_confidence_threshold": 0.7,
|
|
1655
|
+
* "language_confidence": 0.9959,
|
|
1617
1656
|
* "status": "completed",
|
|
1618
1657
|
* "audio_url": "https://assembly.ai/wildfires.mp3",
|
|
1619
1658
|
* "text": "Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines from Maine to Maryland to Minnesota are gray and smoggy. And in some places, the air quality warnings include the warning to stay inside. We wanted to better understand what's happening here and why, so we called Peter de Carlo, an associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University Varsity. Good morning, professor. Good morning. What is it about the conditions right now that have caused this round of wildfires to affect so many people so far away? Well, there's a couple of things. The season has been pretty dry already. And then the fact that we're getting hit in the US. Is because there's a couple of weather systems that are essentially channeling the smoke from those Canadian wildfires through Pennsylvania into the Mid Atlantic and the Northeast and kind of just dropping the smoke there. So what is it in this haze that makes it harmful? And I'm assuming it is harmful. It is. The levels outside right now in Baltimore are considered unhealthy. And most of that is due to what's called particulate matter, which are tiny particles, microscopic smaller than the width of your hair that can get into your lungs and impact your respiratory system, your cardiovascular system, and even your neurological your brain. What makes this particularly harmful? Is it the volume of particulant? Is it something in particular? What is it exactly? Can you just drill down on that a little bit more? Yeah. So the concentration of particulate matter I was looking at some of the monitors that we have was reaching levels of what are, in science, big 150 micrograms per meter cubed, which is more than ten times what the annual average should be and about four times higher than what you're supposed to have on a 24 hours average. And so the concentrations of these particles in the air are just much, much higher than we typically see. And exposure to those high levels can lead to a host of health problems. And who is most vulnerable? I noticed that in New York City, for example, they're canceling outdoor activities. And so here it is in the early days of summer, and they have to keep all the kids inside. So who tends to be vulnerable in a situation like this? It's the youngest. So children, obviously, whose bodies are still developing. The elderly, who are their bodies are more in decline and they're more susceptible to the health impacts of breathing, the poor air quality. And then people who have preexisting health conditions, people with respiratory conditions or heart conditions can be triggered by high levels of air pollution. Could this get worse? That's a good question. In some areas, it's much worse than others. And it just depends on kind of where the smoke is concentrated. I think New York has some of the higher concentrations right now, but that's going to change as that air moves away from the New York area. But over the course of the next few days, we will see different areas being hit at different times with the highest concentrations. I was going to ask you about more fires start burning. I don't expect the concentrations to go up too much higher. I was going to ask you how and you started to answer this, but how much longer could this last? Or forgive me if I'm asking you to speculate, but what do you think? Well, I think the fires are going to burn for a little bit longer, but the key for us in the US. Is the weather system changing. And so right now, it's kind of the weather systems that are pulling that air into our mid Atlantic and Northeast region. As those weather systems change and shift, we'll see that smoke going elsewhere and not impact us in this region as much. And so I think that's going to be the defining factor. And I think the next couple of days we're going to see a shift in that weather pattern and start to push the smoke away from where we are. And finally, with the impacts of climate change, we are seeing more wildfires. Will we be seeing more of these kinds of wide ranging air quality consequences or circumstances? I mean, that is one of the predictions for climate change. Looking into the future, the fire season is starting earlier and lasting longer, and we're seeing more frequent fires. So, yeah, this is probably something that we'll be seeing more frequently. This tends to be much more of an issue in the Western US. So the eastern US. Getting hit right now is a little bit new. But yeah, I think with climate change moving forward, this is something that is going to happen more frequently. That's Peter De Carlo, associate professor in the Department of Environmental Health and Engineering at Johns Hopkins University. Sergeant Carlo, thanks so much for joining us and sharing this expertise with us. Thank you for having me.",
|
|
@@ -1844,6 +1883,7 @@ export type TopicDetectionResult = {
|
|
|
1844
1883
|
* "audio_duration": 281,
|
|
1845
1884
|
* "punctuate": true,
|
|
1846
1885
|
* "format_text": true,
|
|
1886
|
+
* "multichannel": false,
|
|
1847
1887
|
* "dual_channel": false,
|
|
1848
1888
|
* "webhook_url": "https://your-webhook-url.tld/path",
|
|
1849
1889
|
* "webhook_status_code": 200,
|
|
@@ -2185,7 +2225,6 @@ export type TopicDetectionResult = {
|
|
|
2185
2225
|
* "MedicalHealth>DiseasesAndConditions>Injuries>FirstAid": 0.0004885646631009877
|
|
2186
2226
|
* }
|
|
2187
2227
|
* },
|
|
2188
|
-
* "language_detection": false,
|
|
2189
2228
|
* "custom_spelling": null,
|
|
2190
2229
|
* "throttled": null,
|
|
2191
2230
|
* "auto_chapters": true,
|
|
@@ -2300,6 +2339,10 @@ export type Transcript = {
|
|
|
2300
2339
|
* The acoustic model that was used for the transcript
|
|
2301
2340
|
*/
|
|
2302
2341
|
acoustic_model: string;
|
|
2342
|
+
/**
|
|
2343
|
+
* The number of audio channels in the audio file. This is only present when multichannel is enabled.
|
|
2344
|
+
*/
|
|
2345
|
+
audio_channels?: number;
|
|
2303
2346
|
/**
|
|
2304
2347
|
* The duration of this transcript object's media file, in seconds
|
|
2305
2348
|
*/
|
|
@@ -2363,6 +2406,7 @@ export type Transcript = {
|
|
|
2363
2406
|
*/
|
|
2364
2407
|
disfluencies?: boolean | null;
|
|
2365
2408
|
/**
|
|
2409
|
+
* @deprecated
|
|
2366
2410
|
* Whether {@link https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription | Dual channel transcription } was enabled in the transcription request, either true or false
|
|
2367
2411
|
*/
|
|
2368
2412
|
dual_channel?: boolean | null;
|
|
@@ -2412,8 +2456,7 @@ export type Transcript = {
|
|
|
2412
2456
|
language_confidence: number | null;
|
|
2413
2457
|
/**
|
|
2414
2458
|
* The confidence threshold for the automatically detected language.
|
|
2415
|
-
* An error will be returned if the
|
|
2416
|
-
* Defaults to 0.
|
|
2459
|
+
* An error will be returned if the language confidence is below this threshold.
|
|
2417
2460
|
*/
|
|
2418
2461
|
language_confidence_threshold: number | null;
|
|
2419
2462
|
/**
|
|
@@ -2425,6 +2468,10 @@ export type Transcript = {
|
|
|
2425
2468
|
* The language model that was used for the transcript
|
|
2426
2469
|
*/
|
|
2427
2470
|
language_model: string;
|
|
2471
|
+
/**
|
|
2472
|
+
* Whether {@link https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription | Multichannel transcription } was enabled in the transcription request, either true or false
|
|
2473
|
+
*/
|
|
2474
|
+
multichannel?: boolean | null;
|
|
2428
2475
|
/**
|
|
2429
2476
|
* Whether Automatic Punctuation is enabled, either true or false
|
|
2430
2477
|
*/
|
|
@@ -2583,7 +2630,6 @@ export type TranscriptCustomSpelling = {
|
|
|
2583
2630
|
* The language of your audio file. Possible values are found in {@link https://www.assemblyai.com/docs/concepts/supported-languages | Supported Languages }.
|
|
2584
2631
|
* The default value is 'en_us'.
|
|
2585
2632
|
*
|
|
2586
|
-
* @defaultValue "en_us
|
|
2587
2633
|
*/
|
|
2588
2634
|
export type TranscriptLanguageCode =
|
|
2589
2635
|
| "en"
|
|
@@ -2695,7 +2741,7 @@ export type TranscriptLanguageCode =
|
|
|
2695
2741
|
* ```js
|
|
2696
2742
|
* {
|
|
2697
2743
|
* "page_details": {
|
|
2698
|
-
* "limit": 3
|
|
2744
|
+
* "limit": 3,
|
|
2699
2745
|
* "result_count": 3,
|
|
2700
2746
|
* "current_url": "https://api.assemblyai.com/v2/transcript?limit=3",
|
|
2701
2747
|
* "prev_url": "https://api.assemblyai.com/v2/transcript?limit=3&before_id=28a73d01-98db-41dd-9e98-2533ba0af117",
|
|
@@ -2734,7 +2780,13 @@ export type TranscriptLanguageCode =
|
|
|
2734
2780
|
* ```
|
|
2735
2781
|
*/
|
|
2736
2782
|
export type TranscriptList = {
|
|
2783
|
+
/**
|
|
2784
|
+
* Details of the transcript page
|
|
2785
|
+
*/
|
|
2737
2786
|
page_details: PageDetails;
|
|
2787
|
+
/**
|
|
2788
|
+
* An array of transcripts
|
|
2789
|
+
*/
|
|
2738
2790
|
transcripts: TranscriptListItem[];
|
|
2739
2791
|
};
|
|
2740
2792
|
|
|
@@ -2753,15 +2805,33 @@ export type TranscriptList = {
|
|
|
2753
2805
|
* ```
|
|
2754
2806
|
*/
|
|
2755
2807
|
export type TranscriptListItem = {
|
|
2808
|
+
/**
|
|
2809
|
+
* The URL to the audio file
|
|
2810
|
+
*/
|
|
2756
2811
|
audio_url: string;
|
|
2812
|
+
/**
|
|
2813
|
+
* The date and time the transcript was completed
|
|
2814
|
+
*/
|
|
2757
2815
|
completed: Date | null;
|
|
2816
|
+
/**
|
|
2817
|
+
* The date and time the transcript was created
|
|
2818
|
+
*/
|
|
2758
2819
|
created: Date;
|
|
2759
2820
|
/**
|
|
2760
2821
|
* Error message of why the transcript failed
|
|
2761
2822
|
*/
|
|
2762
2823
|
error: string | null;
|
|
2824
|
+
/**
|
|
2825
|
+
* The unique identifier for the transcript
|
|
2826
|
+
*/
|
|
2763
2827
|
id: string;
|
|
2828
|
+
/**
|
|
2829
|
+
* The URL to retrieve the transcript
|
|
2830
|
+
*/
|
|
2764
2831
|
resource_url: string;
|
|
2832
|
+
/**
|
|
2833
|
+
* The status of the transcript
|
|
2834
|
+
*/
|
|
2765
2835
|
status: TranscriptStatus;
|
|
2766
2836
|
};
|
|
2767
2837
|
|
|
@@ -2772,9 +2842,12 @@ export type TranscriptListItem = {
|
|
|
2772
2842
|
* {
|
|
2773
2843
|
* "speech_model": null,
|
|
2774
2844
|
* "language_code": "en_us",
|
|
2845
|
+
* "language_detection": true,
|
|
2846
|
+
* "language_confidence_threshold": 0.7,
|
|
2775
2847
|
* "punctuate": true,
|
|
2776
2848
|
* "format_text": true,
|
|
2777
|
-
* "
|
|
2849
|
+
* "multichannel": true,
|
|
2850
|
+
* "dual_channel": false,
|
|
2778
2851
|
* "webhook_url": "https://your-webhook-url.tld/path",
|
|
2779
2852
|
* "webhook_auth_header_name": "webhook-secret",
|
|
2780
2853
|
* "webhook_auth_header_value": "webhook-secret-value",
|
|
@@ -2800,7 +2873,6 @@ export type TranscriptListItem = {
|
|
|
2800
2873
|
* "speakers_expected": 2,
|
|
2801
2874
|
* "content_safety": true,
|
|
2802
2875
|
* "iab_categories": true,
|
|
2803
|
-
* "language_detection": false,
|
|
2804
2876
|
* "custom_spelling": [],
|
|
2805
2877
|
* "disfluencies": false,
|
|
2806
2878
|
* "sentiment_analysis": true,
|
|
@@ -2826,22 +2898,27 @@ export type TranscriptOptionalParams = {
|
|
|
2826
2898
|
audio_start_from?: number;
|
|
2827
2899
|
/**
|
|
2828
2900
|
* Enable {@link https://www.assemblyai.com/docs/models/auto-chapters | Auto Chapters }, can be true or false
|
|
2901
|
+
* @defaultValue false
|
|
2829
2902
|
*/
|
|
2830
2903
|
auto_chapters?: boolean;
|
|
2831
2904
|
/**
|
|
2832
2905
|
* Enable Key Phrases, either true or false
|
|
2906
|
+
* @defaultValue false
|
|
2833
2907
|
*/
|
|
2834
2908
|
auto_highlights?: boolean;
|
|
2835
2909
|
/**
|
|
2836
2910
|
* How much to boost specified words
|
|
2911
|
+
* @defaultValue default
|
|
2837
2912
|
*/
|
|
2838
2913
|
boost_param?: TranscriptBoostParam;
|
|
2839
2914
|
/**
|
|
2840
2915
|
* Enable {@link https://www.assemblyai.com/docs/models/content-moderation | Content Moderation }, can be true or false
|
|
2916
|
+
* @defaultValue false
|
|
2841
2917
|
*/
|
|
2842
2918
|
content_safety?: boolean;
|
|
2843
2919
|
/**
|
|
2844
2920
|
* The confidence threshold for the Content Moderation model. Values must be between 25 and 100.
|
|
2921
|
+
* @defaultValue 50
|
|
2845
2922
|
*/
|
|
2846
2923
|
content_safety_confidence?: number;
|
|
2847
2924
|
/**
|
|
@@ -2850,57 +2927,78 @@ export type TranscriptOptionalParams = {
|
|
|
2850
2927
|
custom_spelling?: TranscriptCustomSpelling[];
|
|
2851
2928
|
/**
|
|
2852
2929
|
* Enable custom topics, either true or false
|
|
2930
|
+
* @defaultValue false
|
|
2853
2931
|
*/
|
|
2854
2932
|
custom_topics?: boolean;
|
|
2855
2933
|
/**
|
|
2856
2934
|
* Transcribe Filler Words, like "umm", in your media file; can be true or false
|
|
2935
|
+
* @defaultValue false
|
|
2857
2936
|
*/
|
|
2858
2937
|
disfluencies?: boolean;
|
|
2859
2938
|
/**
|
|
2939
|
+
* @deprecated
|
|
2860
2940
|
* Enable {@link https://www.assemblyai.com/docs/models/speech-recognition#dual-channel-transcription | Dual Channel } transcription, can be true or false.
|
|
2941
|
+
* @defaultValue false
|
|
2861
2942
|
*/
|
|
2862
2943
|
dual_channel?: boolean;
|
|
2863
2944
|
/**
|
|
2864
2945
|
* Enable {@link https://www.assemblyai.com/docs/models/entity-detection | Entity Detection }, can be true or false
|
|
2946
|
+
* @defaultValue false
|
|
2865
2947
|
*/
|
|
2866
2948
|
entity_detection?: boolean;
|
|
2867
2949
|
/**
|
|
2868
2950
|
* Filter profanity from the transcribed text, can be true or false
|
|
2951
|
+
* @defaultValue false
|
|
2869
2952
|
*/
|
|
2870
2953
|
filter_profanity?: boolean;
|
|
2871
2954
|
/**
|
|
2872
2955
|
* Enable Text Formatting, can be true or false
|
|
2956
|
+
* @defaultValue true
|
|
2873
2957
|
*/
|
|
2874
2958
|
format_text?: boolean;
|
|
2875
2959
|
/**
|
|
2876
2960
|
* Enable {@link https://www.assemblyai.com/docs/models/topic-detection | Topic Detection }, can be true or false
|
|
2961
|
+
* @defaultValue false
|
|
2877
2962
|
*/
|
|
2878
2963
|
iab_categories?: boolean;
|
|
2879
2964
|
/**
|
|
2880
2965
|
* The language of your audio file. Possible values are found in {@link https://www.assemblyai.com/docs/concepts/supported-languages | Supported Languages }.
|
|
2881
2966
|
* The default value is 'en_us'.
|
|
2967
|
+
*
|
|
2968
|
+
* @defaultValue en_us
|
|
2882
2969
|
*/
|
|
2883
2970
|
language_code?: LiteralUnion<TranscriptLanguageCode, string> | null;
|
|
2884
2971
|
/**
|
|
2885
2972
|
* The confidence threshold for the automatically detected language.
|
|
2886
|
-
* An error will be returned if the
|
|
2973
|
+
* An error will be returned if the language confidence is below this threshold.
|
|
2887
2974
|
* Defaults to 0.
|
|
2975
|
+
*
|
|
2976
|
+
* @defaultValue 0
|
|
2888
2977
|
*/
|
|
2889
2978
|
language_confidence_threshold?: number;
|
|
2890
2979
|
/**
|
|
2891
2980
|
* Enable {@link https://www.assemblyai.com/docs/models/speech-recognition#automatic-language-detection | Automatic language detection }, either true or false.
|
|
2981
|
+
* @defaultValue false
|
|
2892
2982
|
*/
|
|
2893
2983
|
language_detection?: boolean;
|
|
2984
|
+
/**
|
|
2985
|
+
* Enable {@link https://www.assemblyai.com/docs/models/speech-recognition#multichannel-transcription | Multichannel } transcription, can be true or false.
|
|
2986
|
+
* @defaultValue false
|
|
2987
|
+
*/
|
|
2988
|
+
multichannel?: boolean;
|
|
2894
2989
|
/**
|
|
2895
2990
|
* Enable Automatic Punctuation, can be true or false
|
|
2991
|
+
* @defaultValue true
|
|
2896
2992
|
*/
|
|
2897
2993
|
punctuate?: boolean;
|
|
2898
2994
|
/**
|
|
2899
2995
|
* Redact PII from the transcribed text using the Redact PII model, can be true or false
|
|
2996
|
+
* @defaultValue false
|
|
2900
2997
|
*/
|
|
2901
2998
|
redact_pii?: boolean;
|
|
2902
2999
|
/**
|
|
2903
3000
|
* Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See {@link https://www.assemblyai.com/docs/models/pii-redaction | PII redaction } for more details.
|
|
3001
|
+
* @defaultValue false
|
|
2904
3002
|
*/
|
|
2905
3003
|
redact_pii_audio?: boolean;
|
|
2906
3004
|
/**
|
|
@@ -2914,35 +3012,39 @@ export type TranscriptOptionalParams = {
|
|
|
2914
3012
|
redact_pii_policies?: PiiPolicy[];
|
|
2915
3013
|
/**
|
|
2916
3014
|
* The replacement logic for detected PII, can be "entity_type" or "hash". See {@link https://www.assemblyai.com/docs/models/pii-redaction | PII redaction } for more details.
|
|
3015
|
+
* @defaultValue "hash"
|
|
2917
3016
|
*/
|
|
2918
3017
|
redact_pii_sub?: SubstitutionPolicy | null;
|
|
2919
3018
|
/**
|
|
2920
3019
|
* Enable {@link https://www.assemblyai.com/docs/models/sentiment-analysis | Sentiment Analysis }, can be true or false
|
|
3020
|
+
* @defaultValue false
|
|
2921
3021
|
*/
|
|
2922
3022
|
sentiment_analysis?: boolean;
|
|
2923
3023
|
/**
|
|
2924
3024
|
* Enable {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker diarization }, can be true or false
|
|
3025
|
+
* @defaultValue false
|
|
2925
3026
|
*/
|
|
2926
3027
|
speaker_labels?: boolean;
|
|
2927
3028
|
/**
|
|
2928
|
-
* Tells the speaker label model how many speakers it should attempt to identify, up to 10. See {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker diarization } for more details.
|
|
3029
|
+
* Tells the speaker label model how many speakers it should attempt to identify, up to 10". See {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker diarization } for more details.
|
|
2929
3030
|
* @defaultValue "null
|
|
2930
3031
|
*/
|
|
2931
3032
|
speakers_expected?: number | null;
|
|
2932
3033
|
/**
|
|
2933
3034
|
* The speech model to use for the transcription. When `null`, the "best" model is used.
|
|
2934
|
-
* @defaultValue
|
|
3035
|
+
* @defaultValue best
|
|
2935
3036
|
*/
|
|
2936
3037
|
speech_model?: SpeechModel | null;
|
|
2937
3038
|
/**
|
|
2938
3039
|
* Reject audio files that contain less than this fraction of speech.
|
|
2939
3040
|
* Valid values are in the range [0", 1] inclusive.
|
|
2940
3041
|
*
|
|
2941
|
-
* @defaultValue
|
|
3042
|
+
* @defaultValue 0
|
|
2942
3043
|
*/
|
|
2943
3044
|
speech_threshold?: number | null;
|
|
2944
3045
|
/**
|
|
2945
3046
|
* Enable {@link https://www.assemblyai.com/docs/models/summarization | Summarization }, can be true or false
|
|
3047
|
+
* @defaultValue false
|
|
2946
3048
|
*/
|
|
2947
3049
|
summarization?: boolean;
|
|
2948
3050
|
/**
|
|
@@ -2970,7 +3072,9 @@ export type TranscriptOptionalParams = {
|
|
|
2970
3072
|
*/
|
|
2971
3073
|
webhook_auth_header_value?: string | null;
|
|
2972
3074
|
/**
|
|
2973
|
-
* The URL to which we send webhook requests.
|
|
3075
|
+
* The URL to which we send webhook requests.
|
|
3076
|
+
* We sends two different types of webhook requests.
|
|
3077
|
+
* One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.
|
|
2974
3078
|
*/
|
|
2975
3079
|
webhook_url?: string;
|
|
2976
3080
|
/**
|
|
@@ -3021,14 +3125,25 @@ export type TranscriptOptionalParams = {
|
|
|
3021
3125
|
* ```
|
|
3022
3126
|
*/
|
|
3023
3127
|
export type TranscriptParagraph = {
|
|
3128
|
+
/**
|
|
3129
|
+
* The confidence score for the transcript of this paragraph
|
|
3130
|
+
*/
|
|
3024
3131
|
confidence: number;
|
|
3132
|
+
/**
|
|
3133
|
+
* The ending time, in milliseconds, of the paragraph
|
|
3134
|
+
*/
|
|
3025
3135
|
end: number;
|
|
3026
3136
|
/**
|
|
3027
|
-
* The
|
|
3137
|
+
* The starting time, in milliseconds, of the paragraph
|
|
3028
3138
|
*/
|
|
3029
|
-
speaker?: string | null;
|
|
3030
3139
|
start: number;
|
|
3140
|
+
/**
|
|
3141
|
+
* The transcript of the paragraph
|
|
3142
|
+
*/
|
|
3031
3143
|
text: string;
|
|
3144
|
+
/**
|
|
3145
|
+
* An array of words in the paragraph
|
|
3146
|
+
*/
|
|
3032
3147
|
words: TranscriptWord[];
|
|
3033
3148
|
};
|
|
3034
3149
|
|
|
@@ -3039,10 +3154,13 @@ export type TranscriptParagraph = {
|
|
|
3039
3154
|
* {
|
|
3040
3155
|
* "speech_model": null,
|
|
3041
3156
|
* "language_code": "en_us",
|
|
3157
|
+
* "language_detection": true,
|
|
3158
|
+
* "language_confidence_threshold": 0.7,
|
|
3042
3159
|
* "audio_url": "https://assembly.ai/wildfires.mp3",
|
|
3043
3160
|
* "punctuate": true,
|
|
3044
3161
|
* "format_text": true,
|
|
3045
|
-
* "
|
|
3162
|
+
* "multichannel": true,
|
|
3163
|
+
* "dual_channel": false,
|
|
3046
3164
|
* "webhook_url": "https://your-webhook-url/path",
|
|
3047
3165
|
* "webhook_auth_header_name": "webhook-secret",
|
|
3048
3166
|
* "webhook_auth_header_value": "webhook-secret-value",
|
|
@@ -3068,7 +3186,6 @@ export type TranscriptParagraph = {
|
|
|
3068
3186
|
* "speakers_expected": 2,
|
|
3069
3187
|
* "content_safety": true,
|
|
3070
3188
|
* "iab_categories": true,
|
|
3071
|
-
* "language_detection": false,
|
|
3072
3189
|
* "custom_spelling": [],
|
|
3073
3190
|
* "disfluencies": false,
|
|
3074
3191
|
* "sentiment_analysis": true,
|
|
@@ -3159,14 +3276,33 @@ export type TranscriptReadyStatus = "completed" | "error";
|
|
|
3159
3276
|
* ```
|
|
3160
3277
|
*/
|
|
3161
3278
|
export type TranscriptSentence = {
|
|
3279
|
+
/**
|
|
3280
|
+
* The channel of the sentence. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
|
|
3281
|
+
*/
|
|
3282
|
+
channel?: string | null;
|
|
3283
|
+
/**
|
|
3284
|
+
* The confidence score for the transcript of this sentence
|
|
3285
|
+
*/
|
|
3162
3286
|
confidence: number;
|
|
3287
|
+
/**
|
|
3288
|
+
* The ending time, in milliseconds, for the sentence
|
|
3289
|
+
*/
|
|
3163
3290
|
end: number;
|
|
3164
3291
|
/**
|
|
3165
3292
|
* The speaker of the sentence if {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker Diarization } is enabled, else null
|
|
3166
3293
|
*/
|
|
3167
|
-
speaker
|
|
3294
|
+
speaker: string | null;
|
|
3295
|
+
/**
|
|
3296
|
+
* The starting time, in milliseconds, for the sentence
|
|
3297
|
+
*/
|
|
3168
3298
|
start: number;
|
|
3299
|
+
/**
|
|
3300
|
+
* The transcript of the sentence
|
|
3301
|
+
*/
|
|
3169
3302
|
text: string;
|
|
3303
|
+
/**
|
|
3304
|
+
* An array of words in the sentence
|
|
3305
|
+
*/
|
|
3170
3306
|
words: TranscriptWord[];
|
|
3171
3307
|
};
|
|
3172
3308
|
|
|
@@ -3295,6 +3431,10 @@ export type TranscriptStatus = "queued" | "processing" | "completed" | "error";
|
|
|
3295
3431
|
* ```
|
|
3296
3432
|
*/
|
|
3297
3433
|
export type TranscriptUtterance = {
|
|
3434
|
+
/**
|
|
3435
|
+
* The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
|
|
3436
|
+
*/
|
|
3437
|
+
channel?: string | null;
|
|
3298
3438
|
/**
|
|
3299
3439
|
* The confidence score for the transcript of this utterance
|
|
3300
3440
|
*/
|
|
@@ -3336,18 +3476,35 @@ export type TranscriptWebhookNotification =
|
|
|
3336
3476
|
* "start": 250,
|
|
3337
3477
|
* "end": 650,
|
|
3338
3478
|
* "confidence": 0.97465,
|
|
3479
|
+
* "channel": null,
|
|
3339
3480
|
* "speaker": null
|
|
3340
3481
|
* }
|
|
3341
3482
|
* ```
|
|
3342
3483
|
*/
|
|
3343
3484
|
export type TranscriptWord = {
|
|
3485
|
+
/**
|
|
3486
|
+
* The channel of the word. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
|
|
3487
|
+
*/
|
|
3488
|
+
channel?: string | null;
|
|
3489
|
+
/**
|
|
3490
|
+
* The confidence score for the transcript of this word
|
|
3491
|
+
*/
|
|
3344
3492
|
confidence: number;
|
|
3493
|
+
/**
|
|
3494
|
+
* The ending time, in milliseconds, for the word
|
|
3495
|
+
*/
|
|
3345
3496
|
end: number;
|
|
3346
3497
|
/**
|
|
3347
|
-
* The speaker of the
|
|
3498
|
+
* The speaker of the word if {@link https://www.assemblyai.com/docs/models/speaker-diarization | Speaker Diarization } is enabled, else null
|
|
3499
|
+
*/
|
|
3500
|
+
speaker: string | null;
|
|
3501
|
+
/**
|
|
3502
|
+
* The starting time, in milliseconds, for the word
|
|
3348
3503
|
*/
|
|
3349
|
-
speaker?: string | null;
|
|
3350
3504
|
start: number;
|
|
3505
|
+
/**
|
|
3506
|
+
* The text of the word
|
|
3507
|
+
*/
|
|
3351
3508
|
text: string;
|
|
3352
3509
|
};
|
|
3353
3510
|
|