Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TTS_VOICE | No | Voice selection for text-to-speech | |
| LIVEKIT_URL | No | LiveKit server URL for room-based communication | |
| STT_BASE_URL | No | Custom speech-to-text service URL (OpenAI-compatible) | |
| TTS_BASE_URL | No | Custom text-to-speech service URL (OpenAI-compatible) | |
| OPENAI_API_KEY | Yes | Your OpenAI API key for speech-to-text and text-to-speech | |
| LIVEKIT_API_KEY | No | LiveKit API key | |
| OPENAI_BASE_URL | No | Custom OpenAI API base URL | |
| VOICE_MCP_DEBUG | No | Enable detailed logging | |
| LIVEKIT_API_SECRET | No | LiveKit API secret | |
| VOICE_MCP_SAVE_AUDIO | No | Save all audio files (both TTS output and STT input) |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |