Google Cloud Speech-to-Text API

naftiko: 1.0.0-alpha2
info:
  label: Google Cloud Speech-to-Text API
  description: Provides speech recognition capabilities to convert audio to text, supporting synchronous recognition, asynchronous
    batch processing, and real-time streaming transcription across 125+ languages.
  tags:
  - Google
  - Cloud
  - Speech
  - To
  - Text
  - API
  created: '2026-05-06'
  modified: '2026-05-06'
capability:
  consumes:
  - type: http
    namespace: google-cloud-speech-to-text
    baseUri: https://speech.googleapis.com/v1
    description: Google Cloud Speech-to-Text API HTTP API.
    authentication:
      type: bearer
      token: '{{GOOGLE_CLOUD_SPEECH_TO_TEXT_TOKEN}}'
    resources:
    - name: speech-recognize
      path: /speech:recognize
      operations:
      - name: recognize
        method: POST
        description: Google Cloud Speech-To-Text Synchronous speech recognition
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: speech-longrunningrecognize
      path: /speech:longrunningrecognize
      operations:
      - name: longrunningrecognize
        method: POST
        description: Google Cloud Speech-To-Text Asynchronous speech recognition
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: operations-operationid
      path: /operations/{operationId}
      operations:
      - name: getoperation
        method: GET
        description: Google Cloud Speech-To-Text Get operation status
        inputParameters:
        - name: operationId
          in: path
          type: string
          required: true
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
    - name: projects-project-locations-location-recognizers
      path: /projects/{project}/locations/{location}/recognizers
      operations:
      - name: listrecognizers
        method: GET
        description: Google Cloud Speech-To-Text List recognizers
        inputParameters:
        - name: project
          in: path
          type: string
          required: true
        - name: location
          in: path
          type: string
          required: true
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
      - name: createrecognizer
        method: POST
        description: Google Cloud Speech-To-Text Create a recognizer
        inputParameters:
        - name: project
          in: path
          type: string
          required: true
        - name: location
          in: path
          type: string
          required: true
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
  exposes:
  - type: rest
    port: 8080
    namespace: google-cloud-speech-to-text-rest
    description: REST adapter for Google Cloud Speech-to-Text API.
    resources:
    - path: /speech:recognize
      name: recognize
      operations:
      - method: POST
        name: recognize
        description: Google Cloud Speech-To-Text Synchronous speech recognition
        call: google-cloud-speech-to-text.recognize
        outputParameters:
        - type: object
          mapping: $.
    - path: /speech:longrunningrecognize
      name: longrunningrecognize
      operations:
      - method: POST
        name: longrunningrecognize
        description: Google Cloud Speech-To-Text Asynchronous speech recognition
        call: google-cloud-speech-to-text.longrunningrecognize
        outputParameters:
        - type: object
          mapping: $.
    - path: /operations/{operationId}
      name: getoperation
      operations:
      - method: GET
        name: getoperation
        description: Google Cloud Speech-To-Text Get operation status
        call: google-cloud-speech-to-text.getoperation
        with:
          operationId: rest.operationId
        outputParameters:
        - type: object
          mapping: $.
    - path: /projects/{project}/locations/{location}/recognizers
      name: listrecognizers
      operations:
      - method: GET
        name: listrecognizers
        description: Google Cloud Speech-To-Text List recognizers
        call: google-cloud-speech-to-text.listrecognizers
        with:
          project: rest.project
          location: rest.location
        outputParameters:
        - type: object
          mapping: $.
    - path: /projects/{project}/locations/{location}/recognizers
      name: createrecognizer
      operations:
      - method: POST
        name: createrecognizer
        description: Google Cloud Speech-To-Text Create a recognizer
        call: google-cloud-speech-to-text.createrecognizer
        with:
          project: rest.project
          location: rest.location
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    port: 9090
    namespace: google-cloud-speech-to-text-mcp
    transport: http
    description: MCP adapter for Google Cloud Speech-to-Text API for AI agent use.
    tools:
    - name: recognize
      description: Google Cloud Speech-To-Text Synchronous speech recognition
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: google-cloud-speech-to-text.recognize
      outputParameters:
      - type: object
        mapping: $.
    - name: longrunningrecognize
      description: Google Cloud Speech-To-Text Asynchronous speech recognition
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: google-cloud-speech-to-text.longrunningrecognize
      outputParameters:
      - type: object
        mapping: $.
    - name: getoperation
      description: Google Cloud Speech-To-Text Get operation status
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: google-cloud-speech-to-text.getoperation
      with:
        operationId: tools.operationId
      inputParameters:
      - name: operationId
        type: string
        description: operationId
        required: true
      outputParameters:
      - type: object
        mapping: $.
    - name: listrecognizers
      description: Google Cloud Speech-To-Text List recognizers
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: google-cloud-speech-to-text.listrecognizers
      with:
        project: tools.project
        location: tools.location
      inputParameters:
      - name: project
        type: string
        description: project
        required: true
      - name: location
        type: string
        description: location
        required: true
      outputParameters:
      - type: object
        mapping: $.
    - name: createrecognizer
      description: Google Cloud Speech-To-Text Create a recognizer
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: google-cloud-speech-to-text.createrecognizer
      with:
        project: tools.project
        location: tools.location
      inputParameters:
      - name: project
        type: string
        description: project
        required: true
      - name: location
        type: string
        description: location
        required: true
      outputParameters:
      - type: object
        mapping: $.
binds:
- namespace: env
  keys:
    GOOGLE_CLOUD_SPEECH_TO_TEXT_TOKEN: GOOGLE_CLOUD_SPEECH_TO_TEXT_TOKEN