Google Cloud Text-To-Speech Text:synthesize API

The Text:synthesize API from Google Cloud Text-To-Speech — 1 operation(s) for text:synthesize.

OpenAPI Specification

google-cloud-text-to-speech-text-synthesize-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Google Cloud Text-to-Speech Text:synthesize API
  description: Synthesizes natural-sounding speech from text or SSML input using Google's AI-powered voice synthesis technology.
  version: v1
  contact:
    name: Google Cloud
    url: https://cloud.google.com/text-to-speech
servers:
- url: https://texttospeech.googleapis.com/v1
tags:
- name: Text:synthesize
paths:
  /text:synthesize:
    post:
      operationId: synthesizeSpeech
      summary: Google Cloud Text-To-Speech Synthesize speech
      description: Synthesizes speech from text or SSML input.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SynthesizeSpeechRequest'
      responses:
        '200':
          description: Successful response containing synthesized audio.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SynthesizeSpeechResponse'
      tags:
      - Text:synthesize
components:
  schemas:
    SynthesizeSpeechResponse:
      type: object
      properties:
        audioContent:
          type: string
          description: Base64-encoded audio content.
    SynthesizeSpeechRequest:
      type: object
      required:
      - input
      - voice
      - audioConfig
      properties:
        input:
          type: object
          properties:
            text:
              type: string
            ssml:
              type: string
        voice:
          type: object
          properties:
            languageCode:
              type: string
            name:
              type: string
            ssmlGender:
              type: string
        audioConfig:
          type: object
          properties:
            audioEncoding:
              type: string
              enum:
              - AUDIO_ENCODING_UNSPECIFIED
              - LINEAR16
              - MP3
              - OGG_OPUS
              - MULAW
              - ALAW
            speakingRate:
              type: number
            pitch:
              type: number
            volumeGainDb:
              type: number
            sampleRateHertz:
              type: integer