Hugging Face Audio API

openapi: 3.1.0
info:
  title: Hugging Face Dataset Viewer Audio API
  description: Query and visualize datasets stored on the Hugging Face Hub through a lightweight REST API. Get dataset splits, preview rows, search and filter data, access Parquet files, retrieve size statistics, and obtain Croissant metadata - all without downloading the entire dataset.
  version: 1.0.0
  termsOfService: https://huggingface.co/terms-of-service
  contact:
    name: Hugging Face Support
    url: https://huggingface.co/support
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://datasets-server.huggingface.co
  description: Hugging Face Dataset Viewer production server
security:
- {}
- bearerAuth: []
tags:
- name: Audio
  description: Speech recognition, audio classification, and text-to-speech tasks
paths:
  /models/{model_id}/automatic-speech-recognition:
    post:
      summary: Automatic Speech Recognition Inference
      description: Transcribe audio to text using a speech recognition model.
      operationId: automaticSpeechRecognition
      tags:
      - Audio
      parameters:
      - name: model_id
        in: path
        required: true
        schema:
          type: string
        example: openai/whisper-large-v3
      requestBody:
        required: true
        content:
          audio/flac:
            schema:
              type: string
              format: binary
            examples:
              AutomaticspeechrecognitionRequestExample:
                summary: Default automaticSpeechRecognition request
                x-microcks-default: true
                value: example_value
          audio/wav:
            schema:
              type: string
              format: binary
            examples:
              AutomaticspeechrecognitionRequestExample:
                summary: Default automaticSpeechRecognition request
                x-microcks-default: true
                value: example_value
          audio/mp3:
            schema:
              type: string
              format: binary
            examples:
              AutomaticspeechrecognitionRequestExample:
                summary: Default automaticSpeechRecognition request
                x-microcks-default: true
                value: example_value
      responses:
        '200':
          description: Transcribed text
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SpeechRecognitionResponse'
              examples:
                Automaticspeechrecognition200Example:
                  summary: Default automaticSpeechRecognition 200 response
                  x-microcks-default: true
                  value:
                    text: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /v1/audio/transcriptions:
    post:
      summary: Transcribe Audio
      description: Transcribe audio to text using automatic speech recognition models.
      operationId: createTranscription
      tags:
      - Audio
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - file
              - model
              properties:
                file:
                  type: string
                  format: binary
                  description: Audio file to transcribe
                model:
                  type: string
                  description: Model ID to use for transcription
                  example: openai/whisper-large-v3
                language:
                  type: string
                  description: Language of the audio in ISO 639-1 format
                prompt:
                  type: string
                  description: Optional text to guide transcription
                response_format:
                  type: string
                  enum:
                  - json
                  - text
                  - srt
                  - verbose_json
                  - vtt
                  default: json
                temperature:
                  type: number
                  format: float
            examples:
              CreatetranscriptionRequestExample:
                summary: Default createTranscription request
                x-microcks-default: true
                value:
                  file: example_value
                  model: example_value
                  language: example_value
                  prompt: example_value
                  response_format: json
                  temperature: 42.5
      responses:
        '200':
          description: Transcription result
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                    description: Transcribed text
              examples:
                Createtranscription200Example:
                  summary: Default createTranscription 200 response
                  x-microcks-default: true
                  value:
                    text: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /v1/audio/speech:
    post:
      summary: Generate Speech
      description: Generate audio speech from text input.
      operationId: createSpeech
      tags:
      - Audio
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - model
              - input
              properties:
                model:
                  type: string
                  description: Model ID for speech generation
                input:
                  type: string
                  description: Text to generate audio for
                  maxLength: 4096
                voice:
                  type: string
                  description: Voice to use for generation
                response_format:
                  type: string
                  enum:
                  - mp3
                  - opus
                  - aac
                  - flac
                  - wav
                  default: mp3
                speed:
                  type: number
                  format: float
                  minimum: 0.25
                  maximum: 4.0
                  default: 1.0
            examples:
              CreatespeechRequestExample:
                summary: Default createSpeech request
                x-microcks-default: true
                value:
                  model: example_value
                  input: example_value
                  voice: example_value
                  response_format: mp3
                  speed: 42.5
      responses:
        '200':
          description: Generated audio
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
              examples:
                Createspeech200Example:
                  summary: Default createSpeech 200 response
                  x-microcks-default: true
                  value: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    SpeechRecognitionResponse:
      type: object
      properties:
        text:
          type: string
          description: The transcribed text
          example: example_value
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: HF Token
      description: Optional Hugging Face API token. Required for private and gated datasets.