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."
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。