Local Voice MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port | 59125 |
| MCP_MODE | No | Operation mode - mcp or http | mcp |
| TTS_ENGINE | No | TTS engine to use - chatterbox, kani-mlx, or kokoro | chatterbox |
| PYTHON_PATH | No | Path to Python interpreter | python3 |
| KOKORO_SPEED | No | Speech speed (0.5-2.0) | 1.0 |
| KOKORO_VOICE | No | Voice name | af_sarah |
| USE_MALE_VOICE | No | Use male voice instead of bundled female reference voice (true/false) | false |
| KOKORO_LANGUAGE | No | Language code | en-us |
| KOKORO_MODEL_PATH | No | Path to kokoro ONNX model file | kokoro-v1.0.onnx |
| KOKORO_OUTPUT_DIR | No | Output directory for generated audio files | |
| KOKORO_VOICES_PATH | No | Path to voices bin file | voices-v1.0.bin |
| CHATTERBOX_OUTPUT_DIR | No | Output directory for generated audio files | |
| KOKORO_MAX_CHARACTERS | No | Maximum number of characters allowed for text input | 5000 |
| CHATTERBOX_MAX_CHARACTERS | No | Maximum number of characters allowed for text input | 2000 |
| CHATTERBOX_PLAYBACK_VOLUME | No | Default audio playback volume as percentage (0-100) | 50 |
| CHATTERBOX_REFERENCE_AUDIO | No | Path to reference audio file for voice cloning |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues