CHeema-Text-to-Voice-MCP-Server
JSON →AI-powered text-to-speech MCP server with instant voice cloning. Generate speech from Claude Desktop, Claude Code, or n8n using 5 built-in voices (English, German, French, Spanish) or clone any voice from a short audio sample. Runs fully local, no API keys, no cloud. Supports stdio, SSE, and HTTP transports.
Install
pip install -e Tools · 5
- tts_help Shows a complete usage guide with examples — start here
- tts_synthesize Converts text to speech, saves a WAV file
- tts_list_speakers Lists all available voices
- tts_list_models Shows the active model and alternatives
- tts_add_speaker Clones a new voice from an audio sample
Environment variables
NEUTTS_HOSTNEUTTS_PORT
★ 1 GitHub stars