whisper-stt-mcp

fxckcode/whisper-stt-mcp

★ 0 stars Python AI/LLM Updated today

MCP server for local high-quality audio transcription using faster-whisper (CTranslate2) with NVIDIA GPU acceleration

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "whisper-stt-mcp": {
      "command": "uvx",
      "args": [
        "whisper-stt-mcp"
      ]
    }
  }
}

Or install with pip: pip install whisper-stt-mcp

README Excerpt

MCP server for **local high-quality audio transcription** using faster-whisper (CTranslate2) with NVIDIA GPU acceleration. 🎯 **100% local** — tu audio nunca sale de tu máquina. - **4 MCP tools:** `transcribe`, `list_models`, `download_model`, `transcribe_batch` - **Any Whisper model:** tiny, base, small, medium, large-v3

Tools (11)

beam_sizedirectoryfile_pathlanguagemodelpatterntemperaturetranscribetranscribe_batchvadword_timestamps

Topics

faster-whisperllm-toolsmcpmodel-context-protocolnvidia-gpuspeech-to-texttranscriptionwhisper

whisper-stt-mcp

Quick Install

README Excerpt

Tools (11)

Topics

Related AI/LLM Servers