hume 0.13.3 → 0.13.5

package/.mock/definition/tts/__package__.yml

@@ -1,660 +0,0 @@
-errors:
-  UnprocessableEntityError:
-    status-code: 422
-    type: HTTPValidationError
-    docs: Validation Error
-    examples:
-      - value: {}
-  BadRequestError:
-    status-code: 400
-    type: ErrorResponse
-    docs: Bad Request
-    examples:
-      - value: {}
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    synthesize-json:
-      path: /v0/tts
-      method: POST
-      auth: true
-      docs: >-
-        Synthesizes one or more input texts into speech using the specified
-        voice. If no voice is provided, a novel voice will be generated
-        dynamically. Optionally, additional context can be included to influence
-        the speech's style and prosody.
-
-
-        The response includes the base64-encoded audio and metadata in JSON
-        format.
-      source:
-        openapi: tts-openapi.json
-      display-name: Text-to-speech (Json)
-      request:
-        body:
-          type: PostedTts
-        content-type: application/json
-      response:
-        docs: Successful Response
-        type: ReturnTts
-        status-code: 200
-      errors:
-        - UnprocessableEntityError
-      examples:
-        - request:
-            context:
-              utterances:
-                - text: How can people see beauty so differently?
-                  description: >-
-                    A curious student with a clear and respectful tone, seeking
-                    clarification on Hume's ideas with a straightforward
-                    question.
-            format:
-              type: mp3
-            num_generations: 1
-            utterances:
-              - text: >-
-                  Beauty is no quality in things themselves: It exists merely in
-                  the mind which contemplates them.
-                description: >-
-                  Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm, steady tone with an articulate,
-                  academic quality.
-          response:
-            body:
-              generations:
-                - audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
-                  duration: 7.44225
-                  encoding:
-                    format: mp3
-                    sample_rate: 48000
-                  file_size: 120192
-                  generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
-                  snippets:
-                    - - audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
-                        generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
-                        id: 37b1b1b1-1b1b-1b1b-1b1b-1b1b1b1b1b1b
-                        text: >-
-                          Beauty is no quality in things themselves: It exists
-                          merely in the mind which contemplates them.
-                        utterance_index: 0
-              request_id: 66e01f90-4501-4aa0-bbaf-74f45dc15aa725906
-    synthesize-file:
-      path: /v0/tts/file
-      method: POST
-      auth: true
-      docs: >-
-        Synthesizes one or more input texts into speech using the specified
-        voice. If no voice is provided, a novel voice will be generated
-        dynamically. Optionally, additional context can be included to influence
-        the speech's style and prosody. 
-
-
-        The response contains the generated audio file in the requested format.
-      source:
-        openapi: tts-openapi.json
-      display-name: Text-to-speech (File)
-      request:
-        body:
-          type: PostedTts
-        content-type: application/json
-      response:
-        docs: OK
-        type: file
-        status-code: 200
-      errors:
-        - UnprocessableEntityError
-      examples:
-        - request:
-            context:
-              generation_id: 09ad914d-8e7f-40f8-a279-e34f07f7dab2
-            format:
-              type: mp3
-            num_generations: 1
-            utterances:
-              - text: >-
-                  Beauty is no quality in things themselves: It exists merely in
-                  the mind which contemplates them.
-                description: >-
-                  Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm, steady tone with an articulate,
-                  academic quality.
-    synthesize-json-streaming:
-      path: /v0/tts/stream/json
-      method: POST
-      auth: true
-      docs: >-
-        Streams synthesized speech using the specified voice. If no voice is
-        provided, a novel voice will be generated dynamically. Optionally,
-        additional context can be included to influence the speech's style and
-        prosody. 
-
-
-        The response is a stream of JSON objects including audio encoded in
-        base64.
-      source:
-        openapi: tts-openapi.json
-      display-name: Text-to-speech (Streamed JSON)
-      request:
-        body:
-          type: PostedTts
-        content-type: application/json
-      response-stream:
-        docs: Successful Response
-        type: SnippetAudioChunk
-        format: json
-      errors:
-        - UnprocessableEntityError
-      examples:
-        - request:
-            utterances:
-              - text: >-
-                  Beauty is no quality in things themselves: It exists merely in
-                  the mind which contemplates them.
-                voice:
-                  name: Male English Actor
-                  provider: HUME_AI
-    synthesize-file-streaming:
-      path: /v0/tts/stream/file
-      method: POST
-      auth: true
-      docs: >-
-        Streams synthesized speech using the specified voice. If no voice is
-        provided, a novel voice will be generated dynamically. Optionally,
-        additional context can be included to influence the speech's style and
-        prosody.
-      source:
-        openapi: tts-openapi.json
-      display-name: Text-to-speech (Streamed File)
-      request:
-        body:
-          type: PostedTts
-        content-type: application/json
-      response:
-        docs: OK
-        type: file
-        status-code: 200
-      errors:
-        - UnprocessableEntityError
-      examples:
-        - request:
-            utterances:
-              - text: >-
-                  Beauty is no quality in things themselves: It exists merely in
-                  the mind which contemplates them.
-                voice:
-                  name: Male English Actor
-                  provider: HUME_AI
-  source:
-    openapi: tts-openapi.json
-types:
-  PostedContextWithGenerationId:
-    properties:
-      generation_id:
-        type: string
-        docs: >-
-          The ID of a prior TTS generation to use as context for generating
-          consistent speech style and prosody across multiple requests.
-          Including context may increase audio generation times.
-    source:
-      openapi: tts-openapi.json
-  PostedContextWithUtterances:
-    properties:
-      utterances:
-        type: list<PostedUtterance>
-    source:
-      openapi: tts-openapi.json
-  AudioEncoding:
-    docs: >-
-      Encoding information about the generated audio, including the `format` and
-      `sample_rate`.
-    properties:
-      format:
-        type: AudioFormatType
-        docs: Format for the output audio.
-      sample_rate:
-        type: integer
-        docs: >-
-          The sample rate (`Hz`) of the generated audio. The default sample rate
-          is `48000 Hz`.
-    source:
-      openapi: tts-openapi.json
-  AudioFormatType:
-    enum:
-      - mp3
-      - pcm
-      - wav
-    source:
-      openapi: tts-openapi.json
-  ReturnGeneration:
-    properties:
-      generation_id:
-        type: string
-        docs: >-
-          A unique ID associated with this TTS generation that can be used as
-          context for generating consistent speech style and prosody across
-          multiple requests.
-      duration:
-        type: double
-        docs: Duration of the generated audio in seconds.
-      file_size:
-        type: integer
-        docs: Size of the generated audio in bytes.
-      encoding:
-        type: AudioEncoding
-      audio:
-        type: string
-        docs: >-
-          The generated audio output in the requested format, encoded as a
-          base64 string.
-      snippets:
-        docs: >-
-          A list of snippet groups where each group corresponds to an utterance
-          in the request. Each group contains segmented snippets that represent
-          the original utterance divided into more natural-sounding units
-          optimized for speech delivery.
-        type: list<list<Snippet>>
-    source:
-      openapi: tts-openapi.json
-  HTTPValidationError:
-    properties:
-      detail:
-        type: optional<list<ValidationError>>
-    source:
-      openapi: tts-openapi.json
-  FormatMp3:
-    properties: {}
-    source:
-      openapi: tts-openapi.json
-  PostedContext:
-    discriminated: false
-    docs: >-
-      Utterances to use as context for generating consistent speech style and
-      prosody across multiple requests. These will not be converted to speech
-      output.
-    union:
-      - type: PostedContextWithGenerationId
-      - type: PostedContextWithUtterances
-    source:
-      openapi: tts-openapi.json
-    inline: true
-  Format:
-    discriminant: type
-    base-properties: {}
-    docs: Specifies the output audio file format.
-    union:
-      mp3:
-        type: FormatMp3
-      pcm:
-        type: FormatPcm
-      wav:
-        type: FormatWav
-    source:
-      openapi: tts-openapi.json
-  PostedTts:
-    properties:
-      context:
-        type: optional<PostedContext>
-        docs: >-
-          Utterances to use as context for generating consistent speech style
-          and prosody across multiple requests. These will not be converted to
-          speech output.
-      utterances:
-        docs: >-
-          A list of **Utterances** to be converted to speech output.
-
-
-          An **Utterance** is a unit of input for
-          [Octave](/docs/text-to-speech-tts/overview), and includes input
-          `text`, an optional `description` to serve as the prompt for how the
-          speech should be delivered, an optional `voice` specification, and
-          additional controls to guide delivery for `speed` and
-          `trailing_silence`.
-        type: list<PostedUtterance>
-      num_generations:
-        type: optional<integer>
-        docs: Number of generations of the audio to produce.
-        default: 1
-        validation:
-          min: 1
-          max: 5
-      format:
-        type: optional<Format>
-        docs: Specifies the output audio file format.
-      split_utterances:
-        type: optional<boolean>
-        docs: >-
-          Controls how audio output is segmented in the response.
-
-
-          - When **enabled** (`true`), input utterances are automatically split
-          into natural-sounding speech segments.
-
-
-          - When **disabled** (`false`), the response maintains a strict
-          one-to-one mapping between input utterances and output snippets. 
-
-
-          This setting affects how the `snippets` array is structured in the
-          response, which may be important for applications that need to track
-          the relationship between input text and generated audio segments. When
-          setting to `false`, avoid including utterances with long `text`, as
-          this can result in distorted output.
-        default: true
-      strip_headers:
-        type: optional<boolean>
-        docs: >-
-          If enabled, the audio for all the chunks of a generation, once
-          concatenated together, will constitute a single audio file. Otherwise,
-          if disabled, each chunk's audio will be its own audio file, each with
-          its own headers (if applicable).
-        default: false
-      instant_mode:
-        type: optional<boolean>
-        docs: >-
-          Enables ultra-low latency streaming, significantly reducing the time
-          until the first audio chunk is received. Recommended for real-time
-          applications requiring immediate audio playback. For further details,
-          see our documentation on [instant
-          mode](/docs/text-to-speech-tts/overview#ultra-low-latency-streaming-instant-mode). 
-
-          - A
-          [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice)
-          must be specified when instant mode is enabled. Dynamic voice
-          generation is not supported with this mode.
-
-          - Instant mode is only supported for streaming endpoints (e.g.,
-          [/v0/tts/stream/json](/reference/text-to-speech-tts/synthesize-json-streaming),
-          [/v0/tts/stream/file](/reference/text-to-speech-tts/synthesize-file-streaming)).
-
-          - Ensure only a single generation is requested
-          ([num_generations](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.num_generations)
-          must be `1` or omitted).
-        default: true
-    source:
-      openapi: tts-openapi.json
-  ReturnTts:
-    properties:
-      request_id:
-        type: optional<string>
-        docs: >-
-          A unique ID associated with this request for tracking and
-          troubleshooting. Use this ID when contacting [support](/support) for
-          troubleshooting assistance.
-      generations:
-        type: list<ReturnGeneration>
-    source:
-      openapi: tts-openapi.json
-  ReturnVoice:
-    docs: An Octave voice available for text-to-speech
-    properties:
-      id:
-        type: optional<string>
-        docs: ID of the voice in the `Voice Library`.
-      name:
-        type: optional<string>
-        docs: Name of the voice in the `Voice Library`.
-      provider:
-        type: optional<VoiceProvider>
-        docs: >-
-          The provider associated with the created voice.
-
-
-          Voices created through this endpoint will always have the provider set
-          to `CUSTOM_VOICE`, indicating a custom voice stored in your account.
-    source:
-      openapi: tts-openapi.json
-  FormatPcm:
-    properties: {}
-    source:
-      openapi: tts-openapi.json
-  Snippet:
-    properties:
-      id:
-        type: string
-        docs: A unique ID associated with this **Snippet**.
-      text:
-        type: string
-        docs: The text for this **Snippet**.
-      generation_id:
-        type: string
-        docs: The generation ID this snippet corresponds to.
-      utterance_index:
-        type: optional<integer>
-        docs: The index of the utterance in the request this snippet corresponds to.
-      transcribed_text:
-        type: optional<string>
-        docs: >-
-          The transcribed text of the generated audio. It is only present if
-          `instant_mode` is set to `false`.
-      audio:
-        type: string
-        docs: >-
-          The segmented audio output in the requested format, encoded as a
-          base64 string.
-    source:
-      openapi: tts-openapi.json
-  SnippetAudioChunk:
-    properties:
-      generation_id:
-        type: string
-        docs: >-
-          The generation ID of the parent snippet that this chunk corresponds
-          to.
-      snippet_id:
-        type: string
-        docs: The ID of the parent snippet that this chunk corresponds to.
-      text:
-        type: string
-        docs: The text of the parent snippet that this chunk corresponds to.
-      transcribed_text:
-        type: optional<string>
-        docs: >-
-          The transcribed text of the generated audio of the parent snippet that
-          this chunk corresponds to. It is only present if `instant_mode` is set
-          to `false`.
-      chunk_index:
-        type: integer
-        docs: The index of the audio chunk in the snippet.
-      audio:
-        type: string
-        docs: The generated audio output chunk in the requested format.
-      audio_format:
-        type: AudioFormatType
-        docs: The generated audio output format.
-      is_last_chunk:
-        type: boolean
-        docs: >-
-          Whether or not this is the last chunk streamed back from the decoder
-          for one input snippet.
-      utterance_index:
-        type: optional<integer>
-        docs: >-
-          The index of the utterance in the request that the parent snippet of
-          this chunk corresponds to.
-      snippet:
-        type: Snippet
-    source:
-      openapi: tts-openapi.json
-  PostedUtterance:
-    properties:
-      text:
-        type: string
-        docs: The input text to be synthesized into speech.
-        validation:
-          maxLength: 5000
-      description:
-        type: optional<string>
-        docs: >-
-          Natural language instructions describing how the synthesized speech
-          should sound, including but not limited to tone, intonation, pacing,
-          and accent.
-
-
-          **This field behaves differently depending on whether a voice is
-          specified**:
-
-          - **Voice specified**: the description will serve as acting directions
-          for delivery. Keep directions concise—100 characters or fewer—for best
-          results. See our guide on [acting
-          instructions](/docs/text-to-speech-tts/acting-instructions).
-
-          - **Voice not specified**: the description will serve as a voice
-          prompt for generating a voice. See our [prompting
-          guide](/docs/text-to-speech-tts/prompting) for design tips.
-        validation:
-          maxLength: 1000
-      voice:
-        type: optional<PostedUtteranceVoice>
-        docs: >-
-          The `name` or `id` associated with a **Voice** from the **Voice
-          Library** to be used as the speaker for this and all subsequent
-          `utterances`, until the `voice` field is updated again.
-
-           See our [voices guide](/docs/text-to-speech-tts/voices) for more details on generating and specifying **Voices**.
-      speed:
-        type: optional<double>
-        docs: >-
-          Speed multiplier for the synthesized speech. Extreme values below 0.75
-          and above 1.5 may sometimes cause instability to the generated output.
-        default: 1
-        validation:
-          min: 0.5
-          max: 2
-      trailing_silence:
-        type: optional<double>
-        docs: Duration of trailing silence (in seconds) to add to this utterance
-        default: 0
-        validation:
-          min: 0
-          max: 5
-    source:
-      openapi: tts-openapi.json
-  ValidationErrorLocItem:
-    discriminated: false
-    union:
-      - string
-      - integer
-    source:
-      openapi: tts-openapi.json
-    inline: true
-  ValidationError:
-    properties:
-      loc:
-        type: list<ValidationErrorLocItem>
-      msg: string
-      type: string
-    source:
-      openapi: tts-openapi.json
-  PostedUtteranceVoiceWithId:
-    properties:
-      id:
-        type: string
-        docs: The unique ID associated with the **Voice**.
-      provider:
-        type: optional<VoiceProvider>
-        docs: >-
-          Specifies the source provider associated with the chosen voice.
-
-
-          - **`HUME_AI`**: Select voices from Hume's [Voice
-          Library](https://platform.hume.ai/tts/voice-library), containing a
-          variety of preset, shared voices.
-
-          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
-          and saved in your account. 
-
-
-          If no provider is explicitly set, the default provider is
-          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
-          must explicitly set the provider to `HUME_AI`.
-
-
-          Preset voices from Hume's **Voice Library** are accessible by all
-          users. In contrast, your custom voices are private and accessible only
-          via requests authenticated with your API key.
-    source:
-      openapi: tts-openapi.json
-  PostedUtteranceVoiceWithName:
-    properties:
-      name:
-        type: string
-        docs: The name of a **Voice**.
-      provider:
-        type: optional<VoiceProvider>
-        docs: >-
-          Specifies the source provider associated with the chosen voice.
-
-
-          - **`HUME_AI`**: Select voices from Hume's [Voice
-          Library](https://platform.hume.ai/tts/voice-library), containing a
-          variety of preset, shared voices.
-
-          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
-          and saved in your account. 
-
-
-          If no provider is explicitly set, the default provider is
-          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
-          must explicitly set the provider to `HUME_AI`.
-
-
-          Preset voices from Hume's **Voice Library** are accessible by all
-          users. In contrast, your custom voices are private and accessible only
-          via requests authenticated with your API key.
-    source:
-      openapi: tts-openapi.json
-  VoiceProvider:
-    enum:
-      - HUME_AI
-      - CUSTOM_VOICE
-    source:
-      openapi: tts-openapi.json
-  PostedUtteranceVoice:
-    discriminated: false
-    union:
-      - type: PostedUtteranceVoiceWithId
-      - type: PostedUtteranceVoiceWithName
-    source:
-      openapi: tts-openapi.json
-  FormatWav:
-    properties: {}
-    source:
-      openapi: tts-openapi.json
-  ErrorResponse:
-    properties:
-      error: optional<string>
-      message: optional<string>
-      code: optional<string>
-    source:
-      openapi: tts-openapi.json
-  ReturnPagedVoices:
-    docs: A paginated list Octave voices available for text-to-speech
-    properties:
-      page_number:
-        type: optional<integer>
-        docs: >-
-          The page number of the returned list.
-
-
-          This value corresponds to the `page_number` parameter specified in the
-          request. Pagination uses zero-based indexing.
-      page_size:
-        type: optional<integer>
-        docs: >-
-          The maximum number of items returned per page.
-
-
-          This value corresponds to the `page_size` parameter specified in the
-          request.
-      total_pages:
-        type: optional<integer>
-        docs: The total number of pages in the collection.
-      voices_page:
-        type: optional<list<ReturnVoice>>
-        docs: >-
-          List of voices returned for the specified `page_number` and
-          `page_size`.
-    source:
-      openapi: tts-openapi.json