ElevenLabs Text to Speech API — Text to Speech

naftiko: 1.0.0-alpha2
info:
  label: ElevenLabs Text to Speech API — Text to Speech
  description: 'ElevenLabs Text to Speech API — Text to Speech. 4 operations. Lead operation: Create speech. Self-contained
    Naftiko capability covering one Elevenlabs business surface.'
  tags:
  - Elevenlabs
  - Text to Speech
  created: '2026-05-19'
  modified: '2026-05-19'
binds:
- namespace: env
  keys:
    ELEVENLABS_API_KEY: ELEVENLABS_API_KEY
capability:
  consumes:
  - type: http
    namespace: text-to-speech-text-to-speech
    baseUri: https://api.elevenlabs.io
    description: ElevenLabs Text to Speech API — Text to Speech business capability. Self-contained, no shared references.
    resources:
    - name: v1-text-to-speech-voice_id
      path: /v1/text-to-speech/{voice_id}
      operations:
      - name: createspeech
        method: POST
        description: Create speech
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: v1-text-to-speech-voice_id-stream
      path: /v1/text-to-speech/{voice_id}/stream
      operations:
      - name: streamspeech
        method: POST
        description: Stream speech
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: v1-text-to-speech-voice_id-stream-with-timestamps
      path: /v1/text-to-speech/{voice_id}/stream/with-timestamps
      operations:
      - name: streamspeechwithtimestamps
        method: POST
        description: Stream speech with timing
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: v1-text-to-speech-voice_id-with-timestamps
      path: /v1/text-to-speech/{voice_id}/with-timestamps
      operations:
      - name: createspeechwithtimestamps
        method: POST
        description: Create speech with timing
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    authentication:
      type: apikey
      key: xi-api-key
      value: '{{env.ELEVENLABS_API_KEY}}'
      placement: header
  exposes:
  - type: rest
    namespace: text-to-speech-text-to-speech-rest
    port: 8080
    description: REST adapter for ElevenLabs Text to Speech API — Text to Speech. One Spectral-compliant resource per consumed
      operation, prefixed with /v1.
    resources:
    - path: /v1/v1/text-to-speech/{voice-id}
      name: v1-text-to-speech-voice-id
      description: REST surface for v1-text-to-speech-voice_id.
      operations:
      - method: POST
        name: createspeech
        description: Create speech
        call: text-to-speech-text-to-speech.createspeech
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/v1/text-to-speech/{voice-id}/stream
      name: v1-text-to-speech-voice-id-stream
      description: REST surface for v1-text-to-speech-voice_id-stream.
      operations:
      - method: POST
        name: streamspeech
        description: Stream speech
        call: text-to-speech-text-to-speech.streamspeech
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/v1/text-to-speech/{voice-id}/stream/with-timestamps
      name: v1-text-to-speech-voice-id-stream-with-timestamps
      description: REST surface for v1-text-to-speech-voice_id-stream-with-timestamps.
      operations:
      - method: POST
        name: streamspeechwithtimestamps
        description: Stream speech with timing
        call: text-to-speech-text-to-speech.streamspeechwithtimestamps
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/v1/text-to-speech/{voice-id}/with-timestamps
      name: v1-text-to-speech-voice-id-with-timestamps
      description: REST surface for v1-text-to-speech-voice_id-with-timestamps.
      operations:
      - method: POST
        name: createspeechwithtimestamps
        description: Create speech with timing
        call: text-to-speech-text-to-speech.createspeechwithtimestamps
        with:
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: text-to-speech-text-to-speech-mcp
    port: 9090
    transport: http
    description: MCP adapter for ElevenLabs Text to Speech API — Text to Speech. One tool per consumed operation, routed inline
      through this capability's consumes block.
    tools:
    - name: create-speech
      description: Create speech
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: text-to-speech-text-to-speech.createspeech
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: stream-speech
      description: Stream speech
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: text-to-speech-text-to-speech.streamspeech
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: stream-speech-timing
      description: Stream speech with timing
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: text-to-speech-text-to-speech.streamspeechwithtimestamps
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: create-speech-timing
      description: Create speech with timing
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: text-to-speech-text-to-speech.createspeechwithtimestamps
      with:
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.