Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VOICE_MODEL | No | The specific model name to use. | |
| VOICE_DEVICE | No | The device to use for Automatic Speech Recognition (ASR): 'cuda' (GPU) or 'cpu'. | cuda |
| VOICE_API_KEY | No | API key for the LLM provider. | |
| VOICE_API_URL | No | OpenAI-compatible API URL for the LLM backend. | http://localhost:1234/v1 |
| OPENAI_API_KEY | No | API key required when using OpenAI as the provider. | |
| VOICE_PROVIDER | No | Force a specific provider: lm_studio, openrouter, or openai. | |
| VOICE_TTS_VOICE | No | Default Text-to-Speech voice. | alba |
| OPENROUTER_API_KEY | No | API key required when using OpenRouter as the provider. | |
| VOICE_SMART_TURN_THRESHOLD | No | The threshold for smart turn completion detection (0.0-1.0). | 0.5 |
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 | |