Natural voice conversations for AI assistants - STT/TTS via MCP
Connect Runs on your machine
claude mcp add voicemode -e OPENAI_API_KEY=<OPENAI_API_KEY> -e VOICEMODE_DEBUG=<VOICEMODE_DEBUG> -e VOICEMODE_SKIP_TTS=<VOICEMODE_SKIP_TTS> -e VOICEMODE_PREFER_LOCAL=<VOICEMODE_PREFER_LOCAL> -e VOICEMODE_AUDIO_FORMAT=<VOICEMODE_AUDIO_FORMAT> -e VOICEMODE_WHISPER_MODEL=<VOICEMODE_WHISPER_MODEL> -e VOICEMODE_DISABLE_SILENCE_DETECTION=<VOICEMODE_DISABLE_SILENCE_DETECTION> -- uvx voice-mode==9.0.2
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode==9.0.2"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"VOICEMODE_DEBUG": "<VOICEMODE_DEBUG>",
"VOICEMODE_SKIP_TTS": "<VOICEMODE_SKIP_TTS>",
"VOICEMODE_PREFER_LOCAL": "<VOICEMODE_PREFER_LOCAL>",
"VOICEMODE_AUDIO_FORMAT": "<VOICEMODE_AUDIO_FORMAT>",
"VOICEMODE_WHISPER_MODEL": "<VOICEMODE_WHISPER_MODEL>",
"VOICEMODE_DISABLE_SILENCE_DETECTION": "<VOICEMODE_DISABLE_SILENCE_DETECTION>"
}
}
}
}
{
"mcpServers": {
"voicemode": {
"command": "uvx",
"args": [
"voice-mode==9.0.2"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"VOICEMODE_DEBUG": "<VOICEMODE_DEBUG>",
"VOICEMODE_SKIP_TTS": "<VOICEMODE_SKIP_TTS>",
"VOICEMODE_PREFER_LOCAL": "<VOICEMODE_PREFER_LOCAL>",
"VOICEMODE_AUDIO_FORMAT": "<VOICEMODE_AUDIO_FORMAT>",
"VOICEMODE_WHISPER_MODEL": "<VOICEMODE_WHISPER_MODEL>",
"VOICEMODE_DISABLE_SILENCE_DETECTION": "<VOICEMODE_DISABLE_SILENCE_DETECTION>"
}
}
}
}
{
"servers": {
"voicemode": {
"type": "stdio",
"command": "uvx",
"args": [
"voice-mode==9.0.2"
],
"env": {
"OPENAI_API_KEY": "<OPENAI_API_KEY>",
"VOICEMODE_DEBUG": "<VOICEMODE_DEBUG>",
"VOICEMODE_SKIP_TTS": "<VOICEMODE_SKIP_TTS>",
"VOICEMODE_PREFER_LOCAL": "<VOICEMODE_PREFER_LOCAL>",
"VOICEMODE_AUDIO_FORMAT": "<VOICEMODE_AUDIO_FORMAT>",
"VOICEMODE_WHISPER_MODEL": "<VOICEMODE_WHISPER_MODEL>",
"VOICEMODE_DISABLE_SILENCE_DETECTION": "<VOICEMODE_DISABLE_SILENCE_DETECTION>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
OPENAI_API_KEYOptional, secret | OpenAI API key for cloud-based STT/TTS (optional - local services can be installed) |
VOICEMODE_DEBUGOptional | Enable debug mode with detailed logging (true/false) |
VOICEMODE_SKIP_TTSOptional | Skip TTS and show text only for faster response (true/false) |
VOICEMODE_PREFER_LOCALOptional | Prefer local services over cloud when available (true/false, default: true) |
VOICEMODE_AUDIO_FORMATOptional | Audio format: pcm, mp3, wav, flac, aac, opus (default: pcm) |
VOICEMODE_WHISPER_MODELOptional | Whisper model: tiny, base, small, medium, large (default: base) |
VOICEMODE_DISABLE_SILENCE_DETECTIONOptional | Disable silence detection for continuous recording (true/false) |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 29 Oct 2026 |
| Last updated | 29 Oct 2026 |
| Registry name | dev.voicemode/voicemode |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
