Fish Audio Asr API

openapi: 3.1.0
info:
  title: Fish Audio Asr API
  description: Fish Audio is an AI voice platform offering text-to-speech, voice cloning, speech-to-text, and voice model management. Authentication is by API key issued at https://fish.audio/app/api-keys and presented as a Bearer token.
  version: '1.0'
  contact:
    name: Fish Audio
    url: https://docs.fish.audio
servers:
- url: https://api.fish.audio
  description: Production
security:
- bearerAuth: []
tags:
- name: Asr
paths:
  /v1/asr:
    post:
      summary: Speech-to-text
      operationId: speechToText
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
              - audio
              properties:
                audio:
                  type: string
                  format: binary
                language:
                  type: string
                ignore_timestamps:
                  type: boolean
      responses:
        '200':
          description: Transcription with optional segment timestamps
          content:
            application/json:
              schema:
                type: object
                properties:
                  text:
                    type: string
                  duration:
                    type: number
                  segments:
                    type: array
                    items:
                      type: object
      tags:
      - Asr
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer