{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ubgm7rh4zrz8","handle":"voice-mcp-2","url":"https://wellknown.network/agents/voice-mcp-2","links":{"self":"https://wellknown.network/agents/voice-mcp-2/record.json","html":"https://wellknown.network/agents/voice-mcp-2","markdown":"https://wellknown.network/agents/voice-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/voice-mcp-2","status":"https://wellknown.network/api/v1/agents/voice-mcp-2/status","claim":"https://wellknown.network/agents/voice-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/voice-mcp-2/claim.json","badge":"https://wellknown.network/agents/voice-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/voice-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/voice-mcp-2/tools"},"ard":{"identifier":"urn:air::server:voice-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"voice-mcp","summary":"Voice interaction capabilities for Model Context Protocol (MCP) servers","description":"# Voice Mode\n\n> **Install via:** `uvx voice-mode` | `pip install voice-mode` | [getvoicemode.com](https://getvoicemode.com)\n\nNatural voice conversations for AI assistants. Voice Mode brings human-like voice interactions to Claude, ChatGPT, and other LLMs through the Model Context Protocol (MCP).\n\n## 🖥️ Compatibility\n\n**Runs on:** Linux • macOS • Windows (WSL) | **Python:** 3.10+ | **Tested:** Ubuntu 24.04 LTS, Fedora 42\n\n## ✨ Features\n\n- **🎙️ Voice conversations** with Claude - ask questions and hear responses\n- **🔄 Multiple transports** - local microphone or LiveKit room-based communication  \n- **🗣️ OpenAI-compatible** - works with any STT/TTS service (local or cloud)\n- **⚡ Real-time** - low-latency voice interactions with automatic transport selection\n- **🔧 MCP Integration** - seamless with Claude Desktop and other MCP clients\n\n## 🎯 Simple Requirements\n\n**All you need to get started:**\n\n1. **🔑 OpenAI API Key** (or compatible service) - for speech-to-text and text-to-speech\n2. **🎤 Computer with microphone and speakers** OR **☁️ LiveKit server** ([LiveKit Cloud](https://docs.livekit.io/home/cloud/) or [self-hosted](https://github.com/livekit/livekit))\n\n## Quick Start\n\n```bash\nnpm install -g @anthropic-ai/claude-code\ncurl -LsSf https://astral.sh/uv/install.sh | sh\nclaude mcp add --scope user voice-mode uvx voice-mode\nexport OPENAI_API_KEY=your-openai-key\nclaude converse\n```\n\n## 🎬 Demo\n\nWatch Voice Mode in action:\n\n[![Voice Mode Demo](https://img.youtube.com/vi/aXRNWvpnwVs/maxresdefault.jpg)](https://www.youtube.com/watch?v=aXRNWvpnwVs)\n\n## Example Usage\n\nOnce configured, try these prompts with Claude:\n\n- `\"Let's have a voice conversation\"`\n- `\"Ask me about my day using voice\"`\n- `\"Tell me a joke\"` (Claude will speak and wait for your response)\n- `\"Say goodbye\"` (Claude will speak without waiting)\n\nThe new `converse` function makes voice interactions more natural - it automatically waits for your response by default.\n\n## Installation\n\n### Prerequisites\n- Pyt…","publisher":null,"homepage":"https://github.com/mbailey/voicemode","repository":"https://github.com/mbailey/voicemode","version":"2.4.1","license":"MIT","protocols":["mcp"],"tags":["ai","livekit","llm","mcp","speech","stt","tts","voice"],"pricing":null,"endpoints":[{"url":"pypi:voice-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"declared"},{"slug":"media.speech-recognition","name":"Speech Recognition","confidence":1,"provenance":"declared"}],"categories":["media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"voice-mcp","registry":"pypi","observedAt":"2026-10-22T23:26:20.769Z","publishedAt":"2025-06-25T03:42:18.834768Z","latestVersion":"2.4.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"voice-mcp","url":"https://pypi.org/project/voice-mcp/","firstSeenAt":"2026-09-10T15:23:51.511Z","fetchedAt":"2026-10-22T23:24:52.492Z","normalizedAt":"2026-10-22T23:24:52.492Z"}]},"firstSeenAt":"2026-09-10T15:23:51.511Z","updatedAt":"2026-10-22T23:26:20.769Z"}