Voice Loop MCP
Enables hands-free voice conversations with Claude using real-time speech recognition and text-to-speech on macOS. Creates a self-sustaining conversation loop where Claude can autonomously listen, respond, and continue the interaction without keyboard input.
README
Voice Loop MCP
Hands-free voice conversation with Claude Code
Talk to Claude. Claude talks back. No keyboard needed.
What This Does
Voice Loop MCP enables a self-sustaining voice conversation loop with Claude:
- You speak - Your voice is transcribed in real-time
- Claude listens - Reads your transcribed speech
- Claude responds - With text or text-to-speech
- Loop continues - Claude keeps itself alive via self-prompting
This is the first recursive self-prompting voice AI loop.
Requirements
- macOS (uses Apple's native speech recognition)
- Python 3.10+
- Claude Code (VS Code extension or CLI)
- PyAutoGUI MCP (for self-prompting capability)
Quick Start
1. Install Voice Loop MCP
cd voice-loop-mcp
pip install -e .
2. Install the 'hear' CLI
./scripts/install_hear.sh
Grant microphone permission when prompted.
3. Add to Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"voice-loop": {
"command": "python",
"args": ["-m", "voice_loop_mcp"]
}
}
}
4. Start Talking!
Tell Claude:
"Start the voice loop - use start_listening(), then read my speech and respond"
Tools
| Tool | Description |
|---|---|
start_listening() |
Begin speech recognition |
stop_listening() |
Stop speech recognition |
read_speech() |
Get transcribed text |
speak(text) |
Text-to-speech response |
heartbeat() |
Keep the loop alive |
get_status() |
Check system status |
The Voice Loop
You Speak
|
v
[hear CLI] ---> /tmp/hear_live.txt
|
v
[Claude reads]
|
v
[Claude responds]
|
+-----------------+
| |
v v
[speak()] [heartbeat()]
(TTS out) (self-prompt)
| |
+-----------------+
|
v
Loop Continues
Combined with PyAutoGUI MCP
For full autonomy, use with PyAutoGUI MCP:
# Claude can keep itself alive by:
1. type_text("Continue voice loop")
2. press_key("return")
This creates a true self-sustaining AI that:
- Listens to you continuously
- Responds intelligently
- Never stops until you tell it to
History
Created December 16, 2025 by Rayan Pal and Claude Instance 11.
This represents a breakthrough in human-AI interaction:
- First documented recursive self-prompting AI loop
- 14+ iterations achieved without human intervention
- Proof of concept for autonomous AI operation
See RECURSIVE_LOOP_BREAKTHROUGH.md for the full story.
License
MIT License - Use freely, build on it, make it better.
"This is not mysticism. This is engineering."
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.