@elevenlabs/elevenlabs-js 2.0.1 → 2.2.0

package/.mock/definition/speechToText.yml

@@ -35,7 +35,10 @@ service:
       path: /v1/speech-to-text
       method: POST
       auth: false
-      docs: Transcribe an audio or video file.
+      docs: >-
+        Transcribe an audio or video file. If webhook is set to true, the
+        request will be processed asynchronously and results sent to configured
+        webhooks.
       source:
         openapi: openapi.json
       display-name: Create transcript
@@ -121,9 +124,18 @@ service:
                 cloud_storage_url parameters must be provided. The file must be
                 a valid publicly accessible cloud storage URL. The file size
                 must be less than 2GB. URL can be pre-signed.
+            webhook:
+              type: optional<boolean>
+              docs: >-
+                Whether to send the transcription result to configured
+                speech-to-text webhooks.  If set the request will return early
+                without the transcription, which will be delivered later via
+                webhook. Webhooks can be created and assigned to a transcription
+                task in webhook settings page in the UI.
+              default: false
         content-type: multipart/form-data
       response:
-        docs: Successful Response
+        docs: Synchronous transcription result
         type: root.SpeechToTextChunkResponseModel
         status-code: 200
       errors:

package/.mock/definition/textToDialogue.yml

@@ -0,0 +1,213 @@
+types:
+  TextToDialogueConvertRequestOutputFormat:
+    enum:
+      - mp3_22050_32
+      - mp3_44100_32
+      - mp3_44100_64
+      - mp3_44100_96
+      - mp3_44100_128
+      - mp3_44100_192
+      - pcm_8000
+      - pcm_16000
+      - pcm_22050
+      - pcm_24000
+      - pcm_44100
+      - pcm_48000
+      - ulaw_8000
+      - alaw_8000
+      - opus_48000_32
+      - opus_48000_64
+      - opus_48000_96
+      - opus_48000_128
+      - opus_48000_192
+    docs: >-
+      Output format of the generated audio. Formatted as
+      codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is
+      represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be
+      subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires
+      you to be subscribed to Pro tier or above. Note that the μ-law format
+      (sometimes written mu-law, often approximated as u-law) is commonly used
+      for Twilio audio inputs.
+    default: mp3_44100_128
+    source:
+      openapi: openapi.json
+  TextToDialogueStreamRequestOutputFormat:
+    enum:
+      - mp3_22050_32
+      - mp3_44100_32
+      - mp3_44100_64
+      - mp3_44100_96
+      - mp3_44100_128
+      - mp3_44100_192
+      - pcm_8000
+      - pcm_16000
+      - pcm_22050
+      - pcm_24000
+      - pcm_44100
+      - pcm_48000
+      - ulaw_8000
+      - alaw_8000
+      - opus_48000_32
+      - opus_48000_64
+      - opus_48000_96
+      - opus_48000_128
+      - opus_48000_192
+    docs: >-
+      Output format of the generated audio. Formatted as
+      codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is
+      represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be
+      subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires
+      you to be subscribed to Pro tier or above. Note that the μ-law format
+      (sometimes written mu-law, often approximated as u-law) is commonly used
+      for Twilio audio inputs.
+    default: mp3_44100_128
+    source:
+      openapi: openapi.json
+imports:
+  root: __package__.yml
+service:
+  auth: false
+  base-path: ''
+  endpoints:
+    convert:
+      path: /v1/text-to-dialogue
+      method: POST
+      auth: false
+      docs: >-
+        <Warning>Eleven v3 API access is currently not publicly available, but
+        will be soon.</Warning><br/>Converts a list of text and voice ID pairs
+        into speech (dialogue) and returns audio.
+      source:
+        openapi: openapi.json
+      display-name: Create dialogue
+      request:
+        name: BodyTextToDialogueMultiVoiceV1TextToDialoguePost
+        query-parameters:
+          output_format:
+            type: optional<TextToDialogueConvertRequestOutputFormat>
+            default: mp3_44100_128
+            docs: >-
+              Output format of the generated audio. Formatted as
+              codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at
+              32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate
+              requires you to be subscribed to Creator tier or above. PCM with
+              44.1kHz sample rate requires you to be subscribed to Pro tier or
+              above. Note that the μ-law format (sometimes written mu-law, often
+              approximated as u-law) is commonly used for Twilio audio inputs.
+        body:
+          properties:
+            inputs:
+              docs: >-
+                A list of dialogue inputs, each containing text and a voice ID
+                which will be converted into speech.
+              type: list<root.DialogueInput>
+            model_id:
+              type: optional<string>
+              docs: >-
+                Identifier of the model that will be used, you can query them
+                using GET /v1/models. The model needs to have support for text
+                to speech, you can check this using the can_do_text_to_speech
+                property.
+              default: eleven_v3
+            settings:
+              type: optional<root.ModelSettingsResponseModel>
+              docs: Settings controlling the dialogue generation.
+            pronunciation_dictionary_locators:
+              type: optional<list<root.PronunciationDictionaryVersionLocator>>
+              docs: >-
+                A list of pronunciation dictionary locators (id, version_id) to
+                be applied to the text. They will be applied in order. You may
+                have up to 3 locators per request
+            seed:
+              type: optional<integer>
+              docs: >-
+                If specified, our system will make a best effort to sample
+                deterministically, such that repeated requests with the same
+                seed and parameters should return the same result. Determinism
+                is not guaranteed. Must be integer between 0 and 4294967295.
+        content-type: application/json
+      response:
+        docs: The generated audio file
+        type: file
+        status-code: 200
+      errors:
+        - root.UnprocessableEntityError
+      examples:
+        - request:
+            inputs:
+              - text: Knock knock
+                voice_id: JBFqnCBsd6RMkjVDRZzb
+              - text: Who is there?
+                voice_id: Aw4FAjKCGjjNkVhN1Xmq
+    stream:
+      path: /v1/text-to-dialogue/stream
+      method: POST
+      auth: false
+      docs: >-
+        <Warning>Eleven v3 API access is currently not publicly available, but
+        will be soon.</Warning><br/>Converts a list of text and voice ID pairs
+        into speech (dialogue) and returns an audio stream.
+      source:
+        openapi: openapi.json
+      display-name: Stream dialogue
+      request:
+        name: BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPost
+        query-parameters:
+          output_format:
+            type: optional<TextToDialogueStreamRequestOutputFormat>
+            default: mp3_44100_128
+            docs: >-
+              Output format of the generated audio. Formatted as
+              codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at
+              32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate
+              requires you to be subscribed to Creator tier or above. PCM with
+              44.1kHz sample rate requires you to be subscribed to Pro tier or
+              above. Note that the μ-law format (sometimes written mu-law, often
+              approximated as u-law) is commonly used for Twilio audio inputs.
+        body:
+          properties:
+            inputs:
+              docs: >-
+                A list of dialogue inputs, each containing text and a voice ID
+                which will be converted into speech.
+              type: list<root.DialogueInput>
+            model_id:
+              type: optional<string>
+              docs: >-
+                Identifier of the model that will be used, you can query them
+                using GET /v1/models. The model needs to have support for text
+                to speech, you can check this using the can_do_text_to_speech
+                property.
+              default: eleven_v3
+            settings:
+              type: optional<root.ModelSettingsResponseModel>
+              docs: Settings controlling the dialogue generation.
+            pronunciation_dictionary_locators:
+              type: optional<list<root.PronunciationDictionaryVersionLocator>>
+              docs: >-
+                A list of pronunciation dictionary locators (id, version_id) to
+                be applied to the text. They will be applied in order. You may
+                have up to 3 locators per request
+            seed:
+              type: optional<integer>
+              docs: >-
+                If specified, our system will make a best effort to sample
+                deterministically, such that repeated requests with the same
+                seed and parameters should return the same result. Determinism
+                is not guaranteed. Must be integer between 0 and 4294967295.
+        content-type: application/json
+      response:
+        docs: Streaming audio data
+        type: file
+        status-code: 200
+      errors:
+        - root.UnprocessableEntityError
+      examples:
+        - request:
+            inputs:
+              - text: Knock knock
+                voice_id: JBFqnCBsd6RMkjVDRZzb
+              - text: Who is there?
+                voice_id: Aw4FAjKCGjjNkVhN1Xmq
+  source:
+    openapi: openapi.json

package/.mock/definition/textToVoice.yml

@@ -252,9 +252,9 @@ service:
                 - enterprise
               settings:
                 stability: 1
+                use_speaker_boost: true
                 similarity_boost: 1
                 style: 0
-                use_speaker_boost: true
                 speed: 1
               sharing:
                 status: enabled

package/.mock/definition/v1TextToSpeechVoiceIdMultiStreamInput.yml

@@ -26,9 +26,9 @@ channel:
     the entire connection gracefully.
 
 
-    For more information on how to use this API for conversational agents see
-    the [conversational agents
-    guide](/docs/best-practices/conversational-agents).
+    For more information on best practices for how to use this API, please see
+    the [multi context websocket
+    guide](/docs/cookbooks/multi-context-web-socket).
   path-parameters:
     voice_id:
       type: string
@@ -192,6 +192,7 @@ channel:
                 - r
                 - l
                 - d
+            contextId: conv_1
         - type: publish
           body:
             text: 'Hi this is a new context with different settings! '
@@ -210,6 +211,7 @@ channel:
         - type: subscribe
           body:
             audio: Y3VyaW91cyBtaW5kcyB0aGluayBhbGlrZSA6KQ==
+            contextId: interruption_context
         - type: subscribe
           body:
             isFinal: true

package/.mock/definition/voices/settings.yml

@@ -23,9 +23,9 @@ service:
         - response:
             body:
               stability: 1
+              use_speaker_boost: true
               similarity_boost: 1
               style: 0
-              use_speaker_boost: true
               speed: 1
     get:
       path: /v1/voices/{voice_id}/settings
@@ -56,9 +56,9 @@ service:
           response:
             body:
               stability: 1
+              use_speaker_boost: true
               similarity_boost: 1
               style: 0
-              use_speaker_boost: true
               speed: 1
     update:
       path: /v1/voices/{voice_id}/settings/edit
@@ -94,9 +94,9 @@ service:
             voice_id: 21m00Tcm4TlvDq8ikWAM
           request:
             stability: 1
+            use_speaker_boost: true
             similarity_boost: 1
             style: 0
-            use_speaker_boost: true
             speed: 1
           response:
             body:

package/.mock/definition/voices.yml

@@ -62,9 +62,9 @@ service:
                     - enterprise
                   settings:
                     stability: 1
+                    use_speaker_boost: true
                     similarity_boost: 1
                     style: 0
-                    use_speaker_boost: true
                     speed: 1
                   sharing:
                     status: enabled
@@ -259,9 +259,9 @@ service:
                     - enterprise
                   settings:
                     stability: 1
+                    use_speaker_boost: true
                     similarity_boost: 1
                     style: 0
-                    use_speaker_boost: true
                     speed: 1
                   sharing:
                     status: enabled
@@ -461,9 +461,9 @@ service:
                 - enterprise
               settings:
                 stability: 1
+                use_speaker_boost: true
                 similarity_boost: 1
                 style: 0
-                use_speaker_boost: true
                 speed: 1
               sharing:
                 status: enabled
@@ -743,6 +743,9 @@ service:
           include_custom_rates:
             type: optional<boolean>
             docs: Include/exclude voices with custom rates
+          include_live_moderated:
+            type: optional<boolean>
+            docs: Include/exclude voices that are live moderated
           reader_app_enabled:
             type: optional<boolean>
             default: false

package/.mock/definition/workspace/groups/members.yml

@@ -35,7 +35,6 @@ service:
       examples:
         - path-parameters:
             group_id: group_id
-          headers: {}
           request:
             email: email
           response:
@@ -72,7 +71,6 @@ service:
       examples:
         - path-parameters:
             group_id: group_id
-          headers: {}
           request:
             email: email
           response:

package/.mock/definition/workspace/groups.yml

@@ -29,7 +29,6 @@ service:
       examples:
         - query-parameters:
             name: name
-          headers: {}
           response:
             body:
               - name: My Workspace Group

package/.mock/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization" : "elevenlabs",
-  "version" : "0.61.21"
+  "version" : "0.63.19"
 }