clvoice-mcp
by tvtdev94
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLVOICE_STT | No | STT engine: groq or gemini. | groq |
| CLVOICE_LANG | No | Spoken language: auto, vi, or en. | auto |
| GROQ_API_KEY | No | Groq API key (required if using groq). | |
| CLVOICE_CLEAN | No | Clean filler words via Groq LLM (set to '0' to disable). | true |
| CLVOICE_HOTKEY | No | Host the push-to-talk watcher in the server (set to '0' to disable). | true |
| GEMINI_API_KEY | No | Gemini API key (required if using gemini). | |
| CLVOICE_AUTO_PASTE | No | Auto-paste into focused window (set to 'false' for clipboard only). | true |
| CLVOICE_GROQ_MODEL | No | Groq Whisper model. | whisper-large-v3-turbo |
| CLVOICE_MIC_DEVICE | No | Exact dshow mic name (default: first input). | |
| CLVOICE_CLEAN_MODEL | No | Groq chat model for cleanup. | llama-3.3-70b-versatile |
| CLVOICE_FFMPEG_PATH | No | Path to the ffmpeg binary. | ffmpeg |
| CLVOICE_MAX_SECONDS | No | Hard cap on record duration. | 60 |
| CLVOICE_GEMINI_MODEL | No | Gemini model. | gemini-2.5-flash |
| CLVOICE_DEFAULT_SECONDS | No | Default record duration for MCP tool. | 15 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tvtdev94/clvoice-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server