@elevenlabs/elevenlabs-js 2.2.0 → 2.3.0

package/.mock/definition/v1TextToSpeechVoiceIdMultiStreamInput.yml

@@ -1,252 +0,0 @@
-imports:
-  root: __package__.yml
-channel:
-  path: /v1/text-to-speech/{voice_id}/multi-stream-input
-  url: WSS
-  auth: false
-  docs: >
-    The Multi-Context Text-to-Speech WebSockets API allows for generating audio
-    from text input
-
-    while managing multiple independent audio generation streams (contexts) over
-    a single WebSocket connection.
-
-    This is useful for scenarios requiring concurrent or interleaved audio
-    generations, such as dynamic
-
-    conversational AI applications.
-
-
-    Each context, identified by a context id, maintains its own state. You can
-    send text to specific
-
-    contexts, flush them, or close them independently. A `close_socket` message
-    can be used to terminate
-
-    the entire connection gracefully.
-
-
-    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
-      docs: The unique identifier for the voice to use in the TTS process.
-  query-parameters:
-    authorization:
-      type: optional<string>
-      docs: Your authorization bearer token.
-    model_id:
-      type: optional<string>
-      docs: The model ID to use.
-    language_code:
-      type: optional<string>
-      docs: The ISO 639-1 language code (for specific models).
-    enable_logging:
-      type: optional<boolean>
-      default: true
-      docs: Whether to enable logging of the request.
-    enable_ssml_parsing:
-      type: optional<boolean>
-      default: false
-      docs: Whether to enable SSML parsing.
-    output_format:
-      type: root.TextToSpeechOutputFormatEnum
-      docs: The output audio format
-    inactivity_timeout:
-      type: optional<integer>
-      default: 20
-      docs: >-
-        Timeout for inactivity before a context is closed (seconds), can be up
-        to 180 seconds.
-    sync_alignment:
-      type: optional<boolean>
-      default: false
-      docs: Whether to include timing data with every audio chunk.
-    auto_mode:
-      type: optional<boolean>
-      default: false
-      docs: >-
-        Reduces latency by disabling chunk schedule and buffers. Recommended for
-        full sentences/phrases.
-    apply_text_normalization:
-      type: root.TextToSpeechApplyTextNormalizationEnum
-      docs: >-
-        This parameter controls text normalization with three modes - 'auto',
-        'on', and 'off'. When set to 'auto', the system will automatically
-        decide whether to apply text normalization (e.g., spelling out numbers).
-        With 'on', text normalization will always be applied, while with 'off',
-        it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-        'eleven_flash_v2_5' models. Defaults to 'auto'.
-    seed:
-      type: optional<integer>
-      docs: >-
-        If specified, system will best-effort sample deterministically. Integer
-        between 0 and 4294967295.
-      validation:
-        min: 0
-  messages:
-    publish:
-      origin: client
-      body:
-        type: sendMessageMulti
-        docs: Send messages to the multi-context WebSocket.
-    subscribe:
-      origin: server
-      body:
-        type: receiveMessageMulti
-        docs: Receive messages from the multi-context WebSocket.
-  examples:
-    - messages:
-        - type: publish
-          body:
-            text: ' '
-            voice_settings:
-              stability: 0.5
-              similarity_boost: 0.8
-            context_id: conv_1
-        - type: publish
-          body:
-            text: 'Hello from conversation one. '
-            context_id: conv_1
-        - type: publish
-          body:
-            context_id: conv_1
-            text: 'This is added to the buffer of text to flush. '
-            flush: true
-        - type: subscribe
-          body:
-            audio: Y3VyaW91cyBtaW5kcyB0aGluayBhbGlrZSA6KQ==
-            normalizedAlignment:
-              charStartTimesMs:
-                - 0
-                - 3
-                - 7
-                - 9
-                - 11
-                - 12
-                - 13
-                - 15
-                - 17
-                - 19
-                - 21
-              charsDurationsMs:
-                - 3
-                - 4
-                - 2
-                - 2
-                - 1
-                - 1
-                - 2
-                - 2
-                - 2
-                - 2
-                - 3
-              chars:
-                - H
-                - e
-                - l
-                - l
-                - o
-                - ' '
-                - w
-                - o
-                - r
-                - l
-                - d
-            alignment:
-              charStartTimesMs:
-                - 0
-                - 3
-                - 7
-                - 9
-                - 11
-                - 12
-                - 13
-                - 15
-                - 17
-                - 19
-                - 21
-              charsDurationsMs:
-                - 3
-                - 4
-                - 2
-                - 2
-                - 1
-                - 1
-                - 2
-                - 2
-                - 2
-                - 2
-                - 3
-              chars:
-                - H
-                - e
-                - l
-                - l
-                - o
-                - ' '
-                - w
-                - o
-                - r
-                - l
-                - d
-            contextId: conv_1
-        - type: publish
-          body:
-            text: 'Hi this is a new context with different settings! '
-            voice_settings:
-              stability: 0.2
-              similarity_boost: 0.9
-            context_id: interruption_context
-        - type: publish
-          body:
-            context_id: conv_1
-            close_context: true
-        - type: publish
-          body:
-            context_id: interruption_context
-            flush: true
-        - type: subscribe
-          body:
-            audio: Y3VyaW91cyBtaW5kcyB0aGluayBhbGlrZSA6KQ==
-            contextId: interruption_context
-        - type: subscribe
-          body:
-            isFinal: true
-            contextId: interruption_context
-        - type: publish
-          body:
-            text: ''
-            context_id: interruption_context
-        - type: publish
-          body:
-            close_socket: true
-      docs: Demonstrates initializing two contexts, sending text, and managing them.
-      query-parameters:
-        output_format: mp3_22050_32
-        apply_text_normalization: auto
-        seed: 12345
-types:
-  sendMessageMulti:
-    discriminated: false
-    docs: Send messages to the multi-context WebSocket.
-    union:
-      - root.InitializeConnectionMulti
-      - root.InitialiseContext
-      - root.SendTextMulti
-      - root.FlushContext
-      - root.CloseContext
-      - root.CloseSocket
-      - root.KeepContextAlive
-    source:
-      openapi: asyncapi.yml
-  receiveMessageMulti:
-    discriminated: false
-    docs: Receive messages from the multi-context WebSocket.
-    union:
-      - root.AudioOutputMulti
-      - root.FinalOutputMulti
-    source:
-      openapi: asyncapi.yml

package/.mock/definition/v1TextToSpeechVoiceIdStreamInput.yml

@@ -1,207 +0,0 @@
-imports:
-  root: __package__.yml
-channel:
-  path: /v1/text-to-speech/{voice_id}/stream-input
-  url: WSS
-  auth: false
-  docs: >
-    The Text-to-Speech WebSockets API is designed to generate audio from partial
-    text input
-
-    while ensuring consistency throughout the generated audio. Although highly
-    flexible,
-
-    the WebSockets API isn't a one-size-fits-all solution. It's well-suited for
-    scenarios where:
-      * The input text is being streamed or generated in chunks.
-      * Word-to-audio alignment information is required.
-
-    However, it may not be the best choice when:
-      * The entire input text is available upfront. Given that the generations are partial,
-        some buffering is involved, which could potentially result in slightly higher latency compared
-        to a standard HTTP request.
-      * You want to quickly experiment or prototype. Working with WebSockets can be harder and more
-        complex than using a standard HTTP API, which might slow down rapid development and testing.
-  path-parameters:
-    voice_id:
-      type: string
-      docs: The unique identifier for the voice to use in the TTS process.
-  query-parameters:
-    authorization:
-      type: optional<string>
-      docs: Your authorization bearer token.
-    model_id:
-      type: optional<string>
-      docs: The model ID to use.
-    language_code:
-      type: optional<string>
-      docs: The ISO 639-1 language code (for specific models).
-    enable_logging:
-      type: optional<boolean>
-      default: true
-      docs: Whether to enable logging of the request.
-    enable_ssml_parsing:
-      type: optional<boolean>
-      default: false
-      docs: Whether to enable SSML parsing.
-    output_format:
-      type: root.TextToSpeechOutputFormatEnum
-      docs: The output audio format
-    inactivity_timeout:
-      type: optional<integer>
-      default: 20
-      docs: >-
-        Timeout for inactivity before a context is closed (seconds), can be up
-        to 180 seconds.
-    sync_alignment:
-      type: optional<boolean>
-      default: false
-      docs: Whether to include timing data with every audio chunk.
-    auto_mode:
-      type: optional<boolean>
-      default: false
-      docs: >-
-        Reduces latency by disabling chunk schedule and buffers. Recommended for
-        full sentences/phrases.
-    apply_text_normalization:
-      type: root.TextToSpeechApplyTextNormalizationEnum
-      docs: >-
-        This parameter controls text normalization with three modes - 'auto',
-        'on', and 'off'. When set to 'auto', the system will automatically
-        decide whether to apply text normalization (e.g., spelling out numbers).
-        With 'on', text normalization will always be applied, while with 'off',
-        it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-        'eleven_flash_v2_5' models. Defaults to 'auto'.
-    seed:
-      type: optional<integer>
-      docs: >-
-        If specified, system will best-effort sample deterministically. Integer
-        between 0 and 4294967295.
-      validation:
-        min: 0
-  messages:
-    publish:
-      origin: client
-      body:
-        type: sendMessage
-        docs: Send messages to the WebSocket
-    subscribe:
-      origin: server
-      body:
-        type: receiveMessage
-        docs: Receive messages from the WebSocket
-  examples:
-    - messages:
-        - type: publish
-          body:
-            text: ' '
-            voice_settings:
-              stability: 0.5
-              similarity_boost: 0.8
-              speed: 1
-        - type: publish
-          body:
-            text: Hello World
-            try_trigger_generation: true
-        - type: publish
-          body:
-            text: ''
-        - type: subscribe
-          body:
-            audio: Y3VyaW91cyBtaW5kcyB0aGluayBhbGlrZSA6KQ==
-            normalizedAlignment:
-              charStartTimesMs:
-                - 0
-                - 3
-                - 7
-                - 9
-                - 11
-                - 12
-                - 13
-                - 15
-                - 17
-                - 19
-                - 21
-              charsDurationsMs:
-                - 3
-                - 4
-                - 2
-                - 2
-                - 1
-                - 1
-                - 2
-                - 2
-                - 2
-                - 2
-                - 3
-              chars:
-                - H
-                - e
-                - l
-                - l
-                - o
-                - ' '
-                - w
-                - o
-                - r
-                - l
-                - d
-            alignment:
-              charStartTimesMs:
-                - 0
-                - 3
-                - 7
-                - 9
-                - 11
-                - 12
-                - 13
-                - 15
-                - 17
-                - 19
-                - 21
-              charsDurationsMs:
-                - 3
-                - 4
-                - 2
-                - 2
-                - 1
-                - 1
-                - 2
-                - 2
-                - 2
-                - 2
-                - 3
-              chars:
-                - H
-                - e
-                - l
-                - l
-                - o
-                - ' '
-                - w
-                - o
-                - r
-                - l
-                - d
-      query-parameters:
-        output_format: mp3_22050_32
-        apply_text_normalization: auto
-        seed: 12345
-types:
-  sendMessage:
-    discriminated: false
-    docs: Send messages to the WebSocket
-    union:
-      - root.InitializeConnection
-      - root.SendText
-      - root.CloseConnection
-    source:
-      openapi: asyncapi.yml
-  receiveMessage:
-    discriminated: false
-    docs: Receive messages from the WebSocket
-    union:
-      - root.AudioOutput
-      - root.FinalOutput
-    source:
-      openapi: asyncapi.yml

package/.mock/definition/voices/ivc.yml

@@ -1,57 +0,0 @@
-imports:
-  root: ../__package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    create:
-      path: /v1/voices/add
-      method: POST
-      auth: false
-      docs: Create a voice clone and add it to your Voices
-      source:
-        openapi: openapi.json
-      display-name: Create voice clone
-      request:
-        name: Body_Add_voice_v1_voices_add_post
-        body:
-          properties:
-            name:
-              type: string
-              docs: >-
-                The name that identifies this voice. This will be displayed in
-                the dropdown of the website.
-            files:
-              type: list<file>
-              docs: >-
-                A list of file paths to audio recordings intended for voice
-                cloning.
-            remove_background_noise:
-              type: optional<boolean>
-              docs: >-
-                If set will remove background noise for voice samples using our
-                audio isolation model. If the samples do not include background
-                noise, it can make the quality worse.
-              default: false
-            description:
-              type: optional<string>
-              docs: A description of the voice.
-            labels:
-              type: optional<string>
-              docs: Serialized labels dictionary for the voice.
-        content-type: multipart/form-data
-      response:
-        docs: Successful Response
-        type: root.AddVoiceIvcResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            name: name
-          response:
-            body:
-              voice_id: c38kUX8pkfYO2kHyqfFy
-              requires_verification: false
-  source:
-    openapi: openapi.json

package/.mock/definition/voices/pvc/samples/audio.yml

@@ -1,44 +0,0 @@
-imports:
-  root: ../../../__package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    get:
-      path: /v1/voices/pvc/{voice_id}/samples/{sample_id}/audio
-      method: GET
-      auth: false
-      docs: >-
-        Retrieve the first 30 seconds of voice sample audio with or without
-        noise removal.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices
-            to list all the available voices.
-        sample_id:
-          type: string
-          docs: Sample ID to be used
-      display-name: Retrieve Voice Sample Audio
-      response:
-        docs: Successful Response
-        type: root.VoiceSamplePreviewResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-            sample_id: VW7YKqPnjY4h39yTbx2L
-          response:
-            body:
-              audio_base_64: audio_base_64
-              voice_id: DCwhRBWXzGAHq8TQ4Fs18
-              sample_id: DCwhRBWXzGAHq8TQ4Fs18
-              media_type: audio/mpeg
-              duration_secs: 5
-  source:
-    openapi: openapi.json

package/.mock/definition/voices/pvc/samples/speakers/audio.yml

@@ -1,48 +0,0 @@
-imports:
-  root: ../../../../__package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    get:
-      path: >-
-        /v1/voices/pvc/{voice_id}/samples/{sample_id}/speakers/{speaker_id}/audio
-      method: GET
-      auth: false
-      docs: Retrieve the separated audio for a specific speaker.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices
-            to list all the available voices.
-        sample_id:
-          type: string
-          docs: Sample ID to be used
-        speaker_id:
-          type: string
-          docs: >-
-            Speaker ID to be used, you can use GET
-            https://api.elevenlabs.io/v1/voices/{voice_id}/samples/{sample_id}/speakers
-            to list all the available speakers for a sample.
-      display-name: Retrieve Separated Speaker Audio
-      response:
-        docs: Successful Response
-        type: root.SpeakerAudioResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-            sample_id: VW7YKqPnjY4h39yTbx2L
-            speaker_id: VW7YKqPnjY4h39yTbx2L
-          response:
-            body:
-              audio_base_64: audio_base_64
-              media_type: audio/mpeg
-              duration_secs: 5
-  source:
-    openapi: openapi.json

package/.mock/definition/voices/pvc/samples/speakers.yml

@@ -1,81 +0,0 @@
-imports:
-  root: ../../../__package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    get:
-      path: /v1/voices/pvc/{voice_id}/samples/{sample_id}/speakers
-      method: GET
-      auth: false
-      docs: >-
-        Retrieve the status of the speaker separation process and the list of
-        detected speakers if complete.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices
-            to list all the available voices.
-        sample_id:
-          type: string
-          docs: Sample ID to be used
-      display-name: Retrieve Speaker Separation Status
-      response:
-        docs: Successful Response
-        type: root.SpeakerSeparationResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-            sample_id: VW7YKqPnjY4h39yTbx2L
-          response:
-            body:
-              voice_id: DCwhRBWXzGAHq8TQ4Fs18
-              sample_id: DCwhRBWXzGAHq8TQ4Fs18
-              status: not_started
-              speakers:
-                key:
-                  speaker_id: DCwhRBWXzGAHq8TQ4Fs18
-                  duration_secs: 5
-                  utterances:
-                    - start: 0
-                      end: 1
-              selected_speaker_ids:
-                - selected_speaker_ids
-    separate:
-      path: /v1/voices/pvc/{voice_id}/samples/{sample_id}/separate-speakers
-      method: POST
-      auth: false
-      docs: Start speaker separation process for a sample
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices
-            to list all the available voices.
-        sample_id:
-          type: string
-          docs: Sample ID to be used
-      display-name: Start Speaker Separation
-      response:
-        docs: Successful Response
-        type: root.StartSpeakerSeparationResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-            sample_id: VW7YKqPnjY4h39yTbx2L
-          response:
-            body:
-              status: ok
-  source:
-    openapi: openapi.json