Google Cloud Speech and Text-to-Speech
Official Google Cloud REST operations for Speech-to-Text and Text-to-Speech.
Connect this API to an AI agent Browse all specs
What you can do with Google Cloud Speech and Text-to-Speech via MCP
Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.
| Method | Path | Operation | Description |
|---|---|---|---|
| POST | /v1/speech:recognize |
recognizeSpeech | Recognize speech Method: POST Path: /v1/speech:recognize IMPORTANT: This function has 2 REQUIRED parameter(s) and 0 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Request Body: REQUIRED: - config: config parameter from application/json - audio: audio parameter from application/json |
| POST | /v1/text:synthesize |
synthesizeSpeech | Synthesize speech Method: POST Path: /v1/text:synthesize IMPORTANT: This function has 3 REQUIRED parameter(s) and 0 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Request Body: REQUIRED: - input: input parameter from application/json - voice: voice parameter from application/json - audioConfig: audioConfig parameter from application/json |
Usage guide
## Authentication Enable the APIs in a Google Cloud project and obtain an OAuth 2.0 access token from a service account or workload identity. Send `Authorization: Bearer $GOOGLE_ACCESS_TOKEN`. ## Speech to text Call `POST https://speech.googleapis.com/v1/speech:recognize` with `config` and inline or Cloud Storage `audio`. ## Text to speech Call `POST https://texttospeech.googleapis.com/v1/text:synthesize` with `input`, `voice`, and `audioConfig`; the response contains base64 audio. Official docs: https://docs.cloud.google.com/speech-to-text/docs/reference/rest and https://docs.cloud.google.com/text-to-speech/docs/reference/rest
How to use this spec
- Create a free VX Agents account (sandbox tools included).
- Open the marketplace and connect “Google Cloud Speech and Text-to-Speech” to an agent.
- Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.