- Local Voice Mcp
Local Voice Mcp
What is Local Voice MCP?
Local Voice MCP is a server application that enables clients to utilize local voice models for text-to-speech (TTS) synthesis, allowing them to convert text into spoken audio using high-quality voice models.
How to use Local Voice MCP?
To use Local Voice MCP, install the package via npm and run it as an MCP server or HTTP server. You can synthesize speech by sending text to the server through its API or command line interface.
Key features of Local Voice MCP?
- Full Model Context Protocol server implementation
- ElevenLabs-compatible REST API for integration
- High-quality voice synthesis using Chatterbox TTS
- Voice cloning capabilities
- Adjustable prosody controls and volume settings
- Automatic cleanup of temporary audio files
- Security features to prevent directory traversal
- Dual mode operation (MCP server or HTTP server)
Use cases of Local Voice MCP?
- Enabling voice interaction in applications for accessibility.
- Creating audio content from text for podcasts or audiobooks.
- Developing interactive voice response systems.
FAQ from Local Voice MCP?
- Can Local Voice MCP support multiple languages?
Yes, it can be configured to support various languages depending on the voice models used.
- Is Local Voice MCP free to use?
Yes, it is open-source and free to use under the MIT license.
- How can I customize the voice output?
You can customize the voice output by adjusting environment variables for voice characteristics and using reference audio for voice cloning.
Server Config
{
"mcpServers": {
"local-voice-mcp": {
"command": "npx",
"args": [
"-y",
"@codecraftersllc/local-voice-mcp"
],
"env": {
"USE_MALE_VOICE": "false",
"CHATTERBOX_EXAGGERATION": "0.5",
"CHATTERBOX_CFG_WEIGHT": "1.2",
"CHATTERBOX_MAX_CHARACTERS": "2000",
"CHATTERBOX_PLAYBACK_VOLUME": "100"
}
}
}
}