DeepL Voice API

openapi: 3.1.0
info:
  title: DeepL Voice API
  description: >-
    REST surface of the DeepL Voice API used to request and reconnect a
    real-time voice transcription / translation session. The session metadata
    returned by these endpoints (streaming_url + token) is then used to
    establish a WebSocket connection described by the companion AsyncAPI
    specification.
  version: "3"
  contact:
    name: DeepL Developers
    url: https://developers.deepl.com/
servers:
  - url: https://api.deepl.com/v3
    description: DeepL Pro
tags:
  - name: Voice
paths:
  /voice/realtime:
    post:
      summary: Request a real-time voice session
      operationId: requestVoiceSession
      tags: [Voice]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                source_media_content_type:
                  type: string
                  description: Audio format for the source media (e.g., "audio/ogg; codecs=opus").
                message_format:
                  type: string
                  enum: [json, msgpack]
                  default: json
                source_language:
                  type: string
                source_language_mode:
                  type: string
                  enum: [auto, fixed]
                  default: auto
                target_languages:
                  type: array
                  maxItems: 5
                  items:
                    type: string
                target_media_languages:
                  type: array
                  maxItems: 1
                  items:
                    type: string
                target_media_content_type:
                  type: string
                target_media_voice:
                  type: string
                  enum: [male, female]
                spoken_terms_id:
                  type: string
                  format: uuid
                glossary_id:
                  type: string
                formality:
                  type: string
                  enum: [default, formal, more, informal, less]
              required:
                - source_media_content_type
      responses:
        "200":
          description: Session created. Returns the WebSocket streaming URL and an ephemeral token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoiceSession'
    get:
      summary: Reconnect to an existing real-time voice session
      operationId: reconnectVoiceSession
      tags: [Voice]
      parameters:
        - in: query
          name: token
          required: true
          schema:
            type: string
          description: The latest ephemeral token obtained for the stream.
      responses:
        "200":
          description: Reconnect details. Returns a fresh streaming URL and token.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoiceSession'
components:
  securitySchemes:
    authKey:
      type: apiKey
      in: header
      name: Authorization
      description: "DeepL-Auth-Key <key>"
  schemas:
    VoiceSession:
      type: object
      properties:
        streaming_url:
          type: string
          format: uri
          description: WebSocket URL for the real-time voice channel.
        token:
          type: string
          description: Ephemeral, single-use authentication token for the WebSocket connection.
        session_id:
          type: string
          format: uuid
security:
  - authKey: []