Voice Transcriber MCP Server
Turn Google Chat voice messages into text inside your agent session using Groq’s Whisper API.
Overview
Voice Transcriber MCP Server is an MCP server for the Build phase that transcribes Google Chat voice messages using the Groq Whisper API.
What is this MCP server?
- Transcribes Google Chat voice messages via Groq Whisper (stdio PyPI v2.0.1)
- Requires GROQ_API_KEY (free tier at console.groq.com)
- Optional GCHAT_TOKEN_PATH for Google Chat OAuth2 token.json
- Keeps async voice feedback inside MCP instead of manual download-and-transcribe
- Speech-to-text bridge, not a full meeting recorder or call center stack
- Server version 2.0.1
- Transport: stdio
- Package: voice-transcriber-mcp on PyPI
What problem does it solve?
Voice updates in Google Chat stay opaque to your agent until you manually listen, export, and transcribe them elsewhere.
Who is it for?
Indie teams on Google Chat who want low-friction Whisper transcription inside Claude Code or Cursor without building a custom Groq + Chat pipeline.
Skip if: Teams on Slack-only stacks, offline batch podcast transcription, or workflows that forbid cloud speech APIs.
What do I get? / Deliverables
After setup, voice messages become plaintext your agent can quote, summarize, and act on in the same workflow as code and docs.
- Text transcriptions of Chat voice messages returned to the agent
- Repeatable Groq Whisper calls without custom scripting
- Optional wired Google Chat auth for automated fetch
Recommended MCP Servers
Journey fit
This server connects external chat media to an LLM transcription API—classic Build-phase integration work when wiring comms into your agent toolchain. Integrations is the right shelf for OAuth/token paths plus a third-party speech API, not a standalone ship or launch distribution play.
How it compares
A narrow speech-to-text MCP bridge, not a general web-search Essentials server or an SDI finance connector.
Common Questions / FAQ
Who is Voice Transcriber MCP Server for?
Solo builders and small teams using Google Chat for async voice updates who want those messages searchable and actionable inside MCP agents.
When should I use Voice Transcriber MCP Server?
Use it while building or maintaining integrations when Chat voice notes block support triage, spec clarification, or handoff documentation.
How do I add Voice Transcriber MCP Server to my agent?
Install voice-transcriber-mcp from PyPI with stdio transport, set GROQ_API_KEY, point GCHAT_TOKEN_PATH at your Chat OAuth token.json if needed, then reload your MCP host.