Google Cloud Speech-To-Text Speech API

openapi: 3.1.0
info:
  title: Google Cloud -to-Text Operations Speech 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.
  version: v1
  contact:
    name: Google Cloud
    url: https://cloud.google.com/speech-to-text/docs
servers:
- url: https://speech.googleapis.com/v1
  description: Google Cloud Speech-to-Text production endpoint
security:
- oauth2:
  - https://www.googleapis.com/auth/cloud-platform
tags:
- name: Speech
  description: Perform speech recognition on audio
paths:
  /speech:recognize:
    post:
      operationId: recognize
      summary: Google Cloud Speech-To-Text Synchronous speech recognition
      description: Performs synchronous speech recognition on audio data, returning transcription results for short audio (up to 1 minute).
      tags:
      - Speech
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RecognizeRequest'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RecognizeResponse'
  /speech:longrunningrecognize:
    post:
      operationId: longRunningRecognize
      summary: Google Cloud Speech-To-Text Asynchronous speech recognition
      description: Performs asynchronous speech recognition on audio data. Results are available via the returned long-running operation. Supports audio up to 480 minutes.
      tags:
      - Speech
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LongRunningRecognizeRequest'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Operation'
  /projects/{project}/locations/{location}/recognizers:
    get:
      operationId: listRecognizers
      summary: Google Cloud Speech-To-Text List recognizers
      description: Lists recognizers in the specified project and location.
      tags:
      - Speech
      parameters:
      - name: project
        in: path
        required: true
        schema:
          type: string
      - name: location
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RecognizerList'
    post:
      operationId: createRecognizer
      summary: Google Cloud Speech-To-Text Create a recognizer
      description: Creates a custom recognizer for speech recognition.
      tags:
      - Speech
      parameters:
      - name: project
        in: path
        required: true
        schema:
          type: string
      - name: location
        in: path
        required: true
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Recognizer'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Operation'
components:
  schemas:
    RecognitionAudio:
      type: object
      properties:
        content:
          type: string
          format: byte
          description: Base64-encoded audio data
        uri:
          type: string
          description: URI pointing to the audio file (GCS URI)
    RecognizeRequest:
      type: object
      properties:
        config:
          $ref: '#/components/schemas/RecognitionConfig'
        audio:
          $ref: '#/components/schemas/RecognitionAudio'
      required:
      - config
      - audio
    RecognizerList:
      type: object
      properties:
        recognizers:
          type: array
          items:
            $ref: '#/components/schemas/Recognizer'
        nextPageToken:
          type: string
    Operation:
      type: object
      properties:
        name:
          type: string
        done:
          type: boolean
        response:
          type: object
        metadata:
          type: object
    SpeechRecognitionResult:
      type: object
      properties:
        alternatives:
          type: array
          items:
            type: object
            properties:
              transcript:
                type: string
                description: Transcription text
              confidence:
                type: number
                description: Confidence score (0.0 to 1.0)
              words:
                type: array
                items:
                  type: object
                  properties:
                    word:
                      type: string
                    startTime:
                      type: string
                    endTime:
                      type: string
        channelTag:
          type: integer
    RecognitionConfig:
      type: object
      properties:
        encoding:
          type: string
          enum:
          - LINEAR16
          - FLAC
          - MULAW
          - AMR
          - AMR_WB
          - OGG_OPUS
          - SPEEX_WITH_HEADER_BYTE
          - WEBM_OPUS
          - MP3
          description: Encoding of the audio data
        sampleRateHertz:
          type: integer
          description: Sample rate in Hertz of the audio data
        languageCode:
          type: string
          description: Language of the audio (BCP-47 format)
        maxAlternatives:
          type: integer
          description: Maximum number of recognition hypotheses
        enableWordTimeOffsets:
          type: boolean
          description: If true, include time offset for each word
        enableAutomaticPunctuation:
          type: boolean
          description: If true, add punctuation to recognition result
        model:
          type: string
          description: Speech recognition model to use
      required:
      - languageCode
    RecognizeResponse:
      type: object
      properties:
        results:
          type: array
          items:
            $ref: '#/components/schemas/SpeechRecognitionResult'
        totalBilledTime:
          type: string
          description: Total billed time for the request
    LongRunningRecognizeRequest:
      type: object
      properties:
        config:
          $ref: '#/components/schemas/RecognitionConfig'
        audio:
          $ref: '#/components/schemas/RecognitionAudio'
        outputConfig:
          type: object
          properties:
            gcsUri:
              type: string
              description: GCS URI for output results
      required:
      - config
      - audio
    Recognizer:
      type: object
      properties:
        name:
          type: string
        displayName:
          type: string
        model:
          type: string
        languageCodes:
          type: array
          items:
            type: string
  securitySchemes:
    oauth2:
      type: oauth2
      flows:
        authorizationCode:
          authorizationUrl: https://accounts.google.com/o/oauth2/auth
          tokenUrl: https://oauth2.googleapis.com/token
          scopes:
            https://www.googleapis.com/auth/cloud-platform: Full access to Google Cloud Platform resources