Voice MCP

by mbailey · File Systems · mcp-server, pypi

Enables two-way voice conversations through multiple transport methods including local microphone recording and LiveKit room-based communication, with configurable STT/TTS services and automatic transport fallback for creating voice-enabled applications.

This MCP server provides voice interaction capabilities through multiple transport methods, enabling AI assistants to conduct two-way voice conversations using either local microphone recording or LiveKit room-based communication. Built by mbailey using Python with FastMCP, sounddevice, and OpenAI-compatible APIs, it features automatic transport selection that tries LiveKit first then falls back to local audio, configurable STT/TTS services with support for self-hosted alternatives, debug mode with audio file saving, and privacy-conscious design with clear user consent requirements. The implementation includes tools for asking voice questions with automatic response recording, standalone text-to-speech and speech-to-text functions, audio device detection, and LiveKit room status monitoring, making it valuable for creating voice-enabled AI assistants, accessibility applications requiring audio interaction, and development workflows that need flexible voice processing with both cloud and local deployment options.

Source: https://github.com/mbailey/voicemode

Install

uvx voice-mcp

Tags: mcp-server, pypi

⭐ 912 GitHub stars · Source: pulsemcp

About File Systems MCP servers and Claude skills

File Systems MCP servers extend what AI agents can do inside Claude Code, Cursor, Copilot, Codex, and Windsurf. The Skiln directory indexes 16,000+ such integrations across 22 categories.

Voice MCP is one of hundreds of File Systems entries indexed on Skiln. Browse the full File Systems category or the complete directory of Claude skills, MCP servers, agents, commands, and hooks.

Related File Systems MCPs and skills

  • LLM Code Context by cyberchitta

    Streamlines code context sharing with LLMs by implementing smart file selection, code outlining, and multi-language support for efficient code reviews and documentation generation.

  • Everything Search by mamertofabian

    Integrates with the Everything SDK to enable rapid file searches and metadata retrieval on Windows.

  • NixOS by utensils

    Provides a server for accessing NixOS packages, system options, Home Manager, and nix-darwin configurations with multi-level caching and advanced search capabilities

  • File Format Converter (Pandoc) by vivekvells

    Document format conversion using Pandoc, enabling transformation of content between PDF, HTML, Markdown, .docx, .rst, .epuc, .latex, and more.

  • FreeCAD by neka-nat

    Enables AI-driven CAD modeling by providing a remote procedure call (RPC) server that allows programmatic control of FreeCAD, supporting operations like creating documents, inserting parts, editing objects, and executing Python code for generative design workflows.

  • LLMS.txt Documentation by langchain-ai

    Provides AI systems with access to documentation from llms.txt files by fetching and parsing content from specified URLs, enabling seamless documentation lookup during coding sessions.

  • ElevenLabs by elevenlabs

    Integrates with ElevenLabs to provide high-quality text-to-speech, voice cloning, and conversational capabilities with customizable voice profiles and audio processing features.

  • MiniMax by minimax-ai

    Enables high-quality text-to-speech, voice cloning, and video generation capabilities through MiniMax's API with robust error handling and file management features.

Frequently asked questions

How do I install Voice MCP?

Add the install command above to your Claude Code, Cursor, or Windsurf MCP configuration. Most servers register via npx, a local command, or a Docker image. Refer to the source repository for environment variables and credential requirements.

Which clients support Voice MCP?

Any MCP-compatible client works: Claude Desktop, Claude Code CLI, Cursor, Windsurf, Zed, and VS Code with the official MCP extension. OpenAI Codex and GitHub Copilot increasingly support MCP via adapter bridges.

Is Voice MCP free?

The server itself is typically open source. Any upstream service (API keys, paid tiers, hosted infrastructure) may have its own pricing. Check the source repository for details.