@elevenlabs/elevenlabs-js 2.1.0 → 2.3.0

package/.mock/definition/samples.yml

@@ -1,46 +0,0 @@
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    delete:
-      path: /v1/voices/{voice_id}/samples/{sample_id}
-      method: DELETE
-      auth: false
-      docs: Removes a sample by its ID.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. You can use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-        sample_id:
-          type: string
-          docs: >-
-            ID of the sample to be used. You can use the [Get
-            voices](/docs/api-reference/voices/get) endpoint list all the
-            available samples for a voice.
-      display-name: Delete voice sample
-      response:
-        docs: Successful Response
-        type: root.DeleteSampleResponse
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-            sample_id: VW7YKqPnjY4h39yTbx2L
-          response:
-            body:
-              status: ok
-  source:
-    openapi: openapi.json
-  display-name: Samples
-docs: >-
-  Access to your samples. A sample is any audio file you attached to a voice. A
-  voice can have one or more samples.

package/.mock/definition/speechToSpeech.yml

@@ -1,324 +0,0 @@
-types:
-  SpeechToSpeechConvertRequestOutputFormat:
-    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
-  SpeechToSpeechConvertRequestFileFormat:
-    enum:
-      - pcm_s16le_16
-      - other
-    inline: true
-    source:
-      openapi: openapi.json
-  SpeechToSpeechStreamRequestOutputFormat:
-    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
-  SpeechToSpeechStreamRequestFileFormat:
-    enum:
-      - pcm_s16le_16
-      - other
-    inline: true
-    source:
-      openapi: openapi.json
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    convert:
-      path: /v1/speech-to-speech/{voice_id}
-      method: POST
-      auth: false
-      docs: >-
-        Transform audio from one voice to another. Maintain full control over
-        emotion, timing and delivery.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. Use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-      display-name: Voice changer
-      request:
-        name: Body_Speech_to_Speech_v1_speech_to_speech__voice_id__post
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<SpeechToSpeechConvertRequestOutputFormat>
-            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:
-            audio:
-              type: file
-              docs: >-
-                The audio file which holds the content and emotion that will
-                control the generated speech.
-            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 speech
-                to speech, you can check this using the can_do_voice_conversion
-                property.
-              default: eleven_english_sts_v2
-            voice_settings:
-              type: optional<string>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request. Needs to be send as
-                a JSON encoded string.
-            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.
-            remove_background_noise:
-              type: optional<boolean>
-              docs: >-
-                If set, will remove the background noise from your audio input
-                using our audio isolation model. Only applies to Voice Changer.
-              default: false
-            file_format:
-              type: optional<SpeechToSpeechConvertRequestFileFormat>
-              docs: >-
-                The format of input audio. Options are 'pcm_s16le_16' or 'other'
-                For `pcm_s16le_16`, the input audio must be 16-bit PCM at a
-                16kHz sample rate, single channel (mono), and little-endian byte
-                order. Latency will be lower than with passing an encoded
-                waveform.
-        content-type: multipart/form-data
-      response:
-        docs: The generated audio file
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: JBFqnCBsd6RMkjVDRZzb
-          query-parameters:
-            output_format: mp3_44100_128
-          request:
-            model_id: eleven_multilingual_sts_v2
-    stream:
-      path: /v1/speech-to-speech/{voice_id}/stream
-      method: POST
-      auth: false
-      docs: >-
-        Stream audio from one voice to another. Maintain full control over
-        emotion, timing and delivery.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. Use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-      display-name: Voice changer stream
-      request:
-        name: >-
-          Body_Speech_to_Speech_Streaming_v1_speech_to_speech__voice_id__stream_post
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<SpeechToSpeechStreamRequestOutputFormat>
-            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:
-            audio:
-              type: file
-              docs: >-
-                The audio file which holds the content and emotion that will
-                control the generated speech.
-            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 speech
-                to speech, you can check this using the can_do_voice_conversion
-                property.
-              default: eleven_english_sts_v2
-            voice_settings:
-              type: optional<string>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request. Needs to be send as
-                a JSON encoded string.
-            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.
-            remove_background_noise:
-              type: optional<boolean>
-              docs: >-
-                If set, will remove the background noise from your audio input
-                using our audio isolation model. Only applies to Voice Changer.
-              default: false
-            file_format:
-              type: optional<SpeechToSpeechStreamRequestFileFormat>
-              docs: >-
-                The format of input audio. Options are 'pcm_s16le_16' or 'other'
-                For `pcm_s16le_16`, the input audio must be 16-bit PCM at a
-                16kHz sample rate, single channel (mono), and little-endian byte
-                order. Latency will be lower than with passing an encoded
-                waveform.
-        content-type: multipart/form-data
-      response:
-        docs: Streaming audio data
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: JBFqnCBsd6RMkjVDRZzb
-          query-parameters:
-            output_format: mp3_44100_128
-          request:
-            model_id: eleven_multilingual_sts_v2
-  source:
-    openapi: openapi.json

package/.mock/definition/speechToText.yml

@@ -1,177 +0,0 @@
-types:
-  SpeechToTextConvertRequestTimestampsGranularity:
-    enum:
-      - none
-      - word
-      - character
-    docs: >-
-      The granularity of the timestamps in the transcription. 'word' provides
-      word-level timestamps and 'character' provides character-level timestamps
-      per word.
-    default: word
-    inline: true
-    source:
-      openapi: openapi.json
-  SpeechToTextConvertRequestFileFormat:
-    enum:
-      - pcm_s16le_16
-      - other
-    docs: >-
-      The format of input audio. Options are 'pcm_s16le_16' or 'other' For
-      `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate,
-      single channel (mono), and little-endian byte order. Latency will be lower
-      than with passing an encoded waveform.
-    default: other
-    inline: true
-    source:
-      openapi: openapi.json
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    convert:
-      path: /v1/speech-to-text
-      method: POST
-      auth: false
-      docs: Transcribe an audio or video file.
-      source:
-        openapi: openapi.json
-      display-name: Create transcript
-      request:
-        name: Body_Speech_to_Text_v1_speech_to_text_post
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-        body:
-          properties:
-            model_id:
-              type: string
-              docs: >-
-                The ID of the model to use for transcription, currently only
-                'scribe_v1' and 'scribe_v1_experimental' are available.
-            file:
-              type: optional<file>
-              docs: >-
-                The file to transcribe. All major audio and video formats are
-                supported. Exactly one of the file or cloud_storage_url
-                parameters must be provided. The file size must be less than
-                1GB.
-            language_code:
-              type: optional<string>
-              docs: >-
-                An ISO-639-1 or ISO-639-3 language_code corresponding to the
-                language of the audio file. Can sometimes improve transcription
-                performance if known beforehand. Defaults to null, in this case
-                the language is predicted automatically.
-            tag_audio_events:
-              type: optional<boolean>
-              docs: >-
-                Whether to tag audio events like (laughter), (footsteps), etc.
-                in the transcription.
-              default: true
-            num_speakers:
-              type: optional<integer>
-              docs: >-
-                The maximum amount of speakers talking in the uploaded file. Can
-                help with predicting who speaks when. The maximum amount of
-                speakers that can be predicted is 32. Defaults to null, in this
-                case the amount of speakers is set to the maximum value the
-                model supports.
-              validation:
-                min: 1
-                max: 32
-            timestamps_granularity:
-              type: optional<SpeechToTextConvertRequestTimestampsGranularity>
-              docs: >-
-                The granularity of the timestamps in the transcription. 'word'
-                provides word-level timestamps and 'character' provides
-                character-level timestamps per word.
-              default: word
-            diarize:
-              type: optional<boolean>
-              docs: >-
-                Whether to annotate which speaker is currently talking in the
-                uploaded file.
-              default: false
-            additional_formats:
-              type: optional<root.AdditionalFormats>
-              docs: A list of additional formats to export the transcript to.
-            file_format:
-              type: optional<SpeechToTextConvertRequestFileFormat>
-              docs: >-
-                The format of input audio. Options are 'pcm_s16le_16' or 'other'
-                For `pcm_s16le_16`, the input audio must be 16-bit PCM at a
-                16kHz sample rate, single channel (mono), and little-endian byte
-                order. Latency will be lower than with passing an encoded
-                waveform.
-              default: other
-            cloud_storage_url:
-              type: optional<string>
-              docs: >-
-                The valid AWS S3, Cloudflare R2 or Google Cloud Storage URL of
-                the file to transcribe. Exactly one of the file or
-                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.
-        content-type: multipart/form-data
-      response:
-        docs: Successful Response
-        type: root.SpeechToTextChunkResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            model_id: model_id
-          response:
-            body:
-              language_code: en
-              language_probability: 0.98
-              text: Hello world!
-              words:
-                - text: Hello
-                  start: 0
-                  end: 0.5
-                  type: word
-                  speaker_id: speaker_1
-                  logprob: 1.1
-                  characters:
-                    - text: text
-                      start: 0
-                      end: 0.1
-                - text: ' '
-                  start: 0.5
-                  end: 0.5
-                  type: spacing
-                  speaker_id: speaker_1
-                  logprob: 1.1
-                  characters:
-                    - text: text
-                      start: 0
-                      end: 0.1
-                - text: world!
-                  start: 0.5
-                  end: 1.2
-                  type: word
-                  speaker_id: speaker_1
-                  logprob: 1.1
-                  characters:
-                    - text: text
-                      start: 0
-                      end: 0.1
-              additional_formats:
-                - requested_format: requested_format
-                  file_extension: file_extension
-                  content_type: content_type
-                  is_base64_encoded: true
-                  content: content
-  source:
-    openapi: openapi.json

package/.mock/definition/studio/projects/chapters/snapshots.yml

@@ -1,141 +0,0 @@
-imports:
-  root: ../../../__package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    list:
-      path: /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots
-      method: GET
-      auth: false
-      docs: >-
-        Gets information about all the snapshots of a chapter. Each snapshot can
-        be downloaded as audio. Whenever a chapter is converted a snapshot will
-        automatically be created.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        project_id:
-          type: string
-          docs: >-
-            The ID of the project to be used. You can use the [List
-            projects](/docs/api-reference/studio/get-projects) endpoint to list
-            all the available projects.
-        chapter_id:
-          type: string
-          docs: >-
-            The ID of the chapter to be used. You can use the [List project
-            chapters](/docs/api-reference/studio/get-chapters) endpoint to list
-            all the available chapters.
-      display-name: List Chapter Snapshots
-      response:
-        docs: Successful Response
-        type: root.ChapterSnapshotsResponse
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            project_id: 21m00Tcm4TlvDq8ikWAM
-            chapter_id: 21m00Tcm4TlvDq8ikWAM
-          response:
-            body:
-              snapshots:
-                - chapter_snapshot_id: aw1NgEzBg83R7vgmiJt1
-                  project_id: aw1NgEzBg83R7vgmiJt2
-                  chapter_id: aw1NgEzBg83R7vgmiJt3
-                  created_at_unix: 1714204800
-                  name: My Chapter Snapshot
-    get:
-      path: >-
-        /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots/{chapter_snapshot_id}
-      method: GET
-      auth: false
-      docs: Returns the chapter snapshot.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        project_id:
-          type: string
-          docs: The ID of the Studio project.
-        chapter_id:
-          type: string
-          docs: The ID of the chapter.
-        chapter_snapshot_id:
-          type: string
-          docs: The ID of the chapter snapshot.
-      display-name: Get Chapter Snapshot
-      response:
-        docs: Successful Response
-        type: root.ChapterSnapshotExtendedResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            project_id: 21m00Tcm4TlvDq8ikWAM
-            chapter_id: 21m00Tcm4TlvDq8ikWAM
-            chapter_snapshot_id: 21m00Tcm4TlvDq8ikWAM
-          response:
-            body:
-              chapter_snapshot_id: aw1NgEzBg83R7vgmiJt1
-              project_id: aw1NgEzBg83R7vgmiJt2
-              chapter_id: aw1NgEzBg83R7vgmiJt3
-              created_at_unix: 1714204800
-              name: My Chapter Snapshot
-              character_alignments:
-                - characters:
-                    - characters
-                  character_start_times_seconds:
-                    - 1.1
-                  character_end_times_seconds:
-                    - 1.1
-    stream:
-      path: >-
-        /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots/{chapter_snapshot_id}/stream
-      method: POST
-      auth: false
-      docs: >-
-        Stream the audio from a chapter snapshot. Use `GET
-        /v1/studio/projects/{project_id}/chapters/{chapter_id}/snapshots` to
-        return the snapshots of a chapter.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        project_id:
-          type: string
-          docs: >-
-            The ID of the project to be used. You can use the [List
-            projects](/docs/api-reference/studio/get-projects) endpoint to list
-            all the available projects.
-        chapter_id:
-          type: string
-          docs: >-
-            The ID of the chapter to be used. You can use the [List project
-            chapters](/docs/api-reference/studio/get-chapters) endpoint to list
-            all the available chapters.
-        chapter_snapshot_id:
-          type: string
-          docs: >-
-            The ID of the chapter snapshot to be used. You can use the [List
-            project chapter snapshots](/docs/api-reference/studio/get-snapshots)
-            endpoint to list all the available snapshots.
-      display-name: Stream Chapter Audio
-      request:
-        name: >-
-          BodyStreamChapterAudioV1StudioProjectsProjectIdChaptersChapterIdSnapshotsChapterSnapshotIdStreamPost
-        body:
-          properties:
-            convert_to_mpeg:
-              type: optional<boolean>
-              docs: Whether to convert the audio to mpeg format.
-              default: false
-        content-type: application/json
-      response:
-        docs: Streaming audio data
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-  source:
-    openapi: openapi.json