Voice Transcriber MCP Server

MCP server for transcribing Google Chat voice messages using Groq Whisper API

Local serverstdioPython

What is the Voice Transcriber MCP server?

Connect Voice Transcriber to Claude, Cursor or any other MCP client and it stops being a tab you switch to. MCP server for transcribing Google Chat voice messages using Groq Whisper API. The voice transcriber mcp server is what makes that connection.

What the server does

MCP server that automatically transcribes Google Chat voice messages using Groq Whisper API (whisper-large-v3). No local GPU needed.

  • Transcribe Google Chat voice messages by URL (automatic)
  • Transcribe local audio files (mp3, m4a, wav, ogg, flac, webm, aac)
  • Uses Groq Whisper API (free tier, fast, cloud-based)
  • Reuses Google Chat OAuth2 credentials (no separate Google auth needed)

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • transcribe_voice_message — Transcribe a voice message from Google Chat. Called automatically by Claude when it encounters an audio attachment
  • transcribe_audio_file — The transcribe_audio_file tool exposed by this server
  • Linux — The Linux tool exposed by this server
  • macOS — The macOS tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: GROQ_API_KEY, GCHAT_TOKEN_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Where it fits

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Voice Transcriber's toolset — transcribe_voice_message, transcribe_audio_file, Linux and 1 more — is a fair guide to whether it matches your workflow. It is maintained by fgasparetto; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Voice Transcriber's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
transcribe_voice_messageTranscribe a voice message from Google Chat. **Called automatically** by Claude when it encounters an audio attachment.
transcribe_audio_fileThe transcribe_audio_file tool exposed by this server.
LinuxThe Linux tool exposed by this server.
macOSThe macOS tool exposed by this server.

Configuration

VariableDescriptionRequired
GROQ_API_KEYCredential the server authenticates with.Yes
GCHAT_TOKEN_PATHCredential the server authenticates with.Yes

Example prompts to try

  • Use Voice Transcriber to transcribe voice message.
  • Use Voice Transcriber to transcribe audio file.
  • Use Voice Transcriber to Linux.

Frequently asked questions

It connects Voice Transcriber to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (transcribe_voice_message, transcribe_audio_file, Linux, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Voice Transcriber directly.