openapi: 3.1.0
info:
  title: Fish Audio 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: []
paths:
  /v1/tts:
    post:
      summary: Generate speech from text
      operationId: textToSpeech
      parameters:
        - name: model
          in: header
          required: false
          description: TTS model variant (s1 or s2-pro)
          schema:
            type: string
            enum: [s1, s2-pro]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [text]
              properties:
                text:
                  type: string
                reference_id:
                  type: string
                  description: ID of a voice model to use
                format:
                  type: string
                  enum: [mp3, wav, pcm, opus]
                  default: mp3
                latency:
                  type: string
                  enum: [normal, balanced]
                prosody:
                  type: object
                  properties:
                    speed:
                      type: number
                    volume:
                      type: number
                chunk_length:
                  type: integer
      responses:
        "200":
          description: Audio stream
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
  /v1/tts/stream/with-timestamp:
    post:
      summary: Stream TTS with per-chunk timestamps (Server-Sent Events)
      operationId: textToSpeechStreamWithTimestamp
      parameters:
        - name: model
          in: header
          required: false
          schema:
            type: string
            enum: [s1, s2-pro]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [text]
              properties:
                text:
                  type: string
                reference_id:
                  type: string
                chunk_length:
                  type: integer
      responses:
        "200":
          description: SSE stream of audio chunks plus timing metadata
          content:
            text/event-stream:
              schema:
                type: string
  /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
  /model:
    get:
      summary: List voice models
      operationId: listModels
      parameters:
        - name: page_size
          in: query
          schema:
            type: integer
        - name: page_number
          in: query
          schema:
            type: integer
        - name: title
          in: query
          schema:
            type: string
        - name: tag
          in: query
          schema:
            type: string
        - name: self
          in: query
          schema:
            type: boolean
        - name: author_id
          in: query
          schema:
            type: string
        - name: language
          in: query
          schema:
            type: string
        - name: title_language
          in: query
          schema:
            type: string
        - name: sort_by
          in: query
          schema:
            type: string
      responses:
        "200":
          description: Paginated model list
          content:
            application/json:
              schema:
                type: object
    post:
      summary: Create a voice clone model
      operationId: createModel
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required: [title]
              properties:
                title:
                  type: string
                description:
                  type: string
                voices:
                  type: array
                  items:
                    type: string
                    format: binary
                texts:
                  type: array
                  items:
                    type: string
                tags:
                  type: array
                  items:
                    type: string
                visibility:
                  type: string
                  enum: [public, unlist, private]
                cover_image:
                  type: string
                  format: binary
      responses:
        "200":
          description: Created model
          content:
            application/json:
              schema:
                type: object
  /model/{id}:
    get:
      summary: Get a voice model
      operationId: getModel
      parameters:
        - name: id
          in: path
          required: true
          schema:
            type: string
      responses:
        "200":
          description: Model details
          content:
            application/json:
              schema:
                type: object
    patch:
      summary: Update a voice model
      operationId: updateModel
      parameters:
        - name: id
          in: path
          required: true
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                title:
                  type: string
                description:
                  type: string
                cover_image:
                  type: string
                visibility:
                  type: string
                tags:
                  type: array
                  items:
                    type: string
      responses:
        "200":
          description: Updated
    delete:
      summary: Delete a voice model
      operationId: deleteModel
      parameters:
        - name: id
          in: path
          required: true
          schema:
            type: string
      responses:
        "200":
          description: Deleted
  /wallet/{user_id}/package:
    get:
      summary: Get user package / balance / subscription
      operationId: getUserPackage
      parameters:
        - name: user_id
          in: path
          required: true
          schema:
            type: string
            default: self
      responses:
        "200":
          description: Package payload
          content:
            application/json:
              schema:
                type: object
  /wallet/{user_id}/api-credit:
    get:
      summary: Get API credit balance
      operationId: getApiCredit
      parameters:
        - name: user_id
          in: path
          required: true
          schema:
            type: string
        - name: check_free_credit
          in: query
          schema:
            type: boolean
        - name: team_id
          in: query
          schema:
            type: string
      responses:
        "200":
          description: Credit details
          content:
            application/json:
              schema:
                type: object
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer