Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
process.env. You'll be asked to provide them before it can run.API_KEYCHATTERBOX_MAX_CHARACTERS— "": "2000",CHATTERBOX_OUTPUT_DIR— Output directory for generated audio files (default: system temp + "local-voice-mcp")CHATTERBOX_PLAYBACK_VOLUME— volume (number, optional): Playback volume as percentage (0-100). If not specified, uses environment variable or default of 50.CHATTERBOX_PYTHON_PATHCHATTERBOX_REFERENCE_AUDIO— Path to reference audio file for voice cloning (can be anywhere on your system, supports .wav, .mp3, .flac, .ogg, .m4a, .aac). If not specified, uses the bundled high-quality female reference voice.KOKORO_LANGUAGE— "": "en-us",KOKORO_MAX_CHARACTERS— Maximum number of characters allowed for text input (integer, default: 5000)KOKORO_MODEL_PATH— Path to kokoro ONNX model file (string, default: "kokoro-v1.0.onnx")KOKORO_OUTPUT_DIR— Output directory for generated audio files (default: system temp + "local-voice-mcp")KOKORO_SPEED— Speech speed (float, 0.5-2.0, default: 1.0)KOKORO_VOICE— "": "af_sarah",KOKORO_VOICES_PATH— Path to voices bin file (string, default: "voices-v1.0.bin")MCP_MODE— http local-voice-mcp-serverPORT— 3000 MCP_MODE=http local-voice-mcp-serverPYTHON_PATH— Path to Python interpreter (default: "python3"). Important: If using Apple Silicon with Python 3.13+, point this to a conda environment with Python 3.11-3.12 where mlx-audio is installed.TTS_ENGINE— To use Kokoro, set the environment variable:USE_MALE_VOICE— "": "false",[](https://m8ven.ai/mcp/codecraftersllc-local-voice-mcp-0h97nj)