whisper-telegram-mcp

> Transcribe Telegram voice messages with Whisper -- as an MCP tool for Claude

[](https://github.com/abid-mahdi/whisper-telegram-mcp/actions) [](https://pypi.org/project/whisper-telegram-mcp/) [](LICENSE) [](https://modelcontextprotocol.io)

An MCP server that transcribes audio files and Telegram voice messages using OpenAI's Whisper speech recognition. Works with Claude Desktop, Claude Code, and any MCP-compatible client.

• Transcribe local audio files -- OGG, WAV, MP3, FLAC, and more
• Transcribe Telegram voice messages -- pass a file_id, get text back
• Two backends -- local inference with faster-whisper (free, private) or OpenAI Whisper API (cloud)
• Auto mode -- tries local first, falls back to OpenAI if it fails
• Language detection -- automatic or specify an ISO-639-1 code
• Word-level timestamps -- optional fine-grained timing

uvx whisper-telegram-mcp

No installation needed -- uvx handles everything.

pip install whisper-telegram-mcp
whisper-telegram-mcp

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "whisper-telegram-mcp": {
      "command": "uvx",
      "args": ["whisper-telegram-mcp"],
      "env": {
        "WHISPER_MODEL": "base",
        "WHISPER_BACKEND": "auto"
      }
    }
  }
}

Add to your project's .mcp.json:

{
  "mcpServers": {
    "whisper-telegram-mcp