mbailey/voicemode

Natural voice conversations with Claude Code

What it solves

VoiceMode allows users to have natural, hands-free voice conversations with AI agents like Claude Code. It is designed for situations where typing is impractical, such as when the user is walking, cooking, or needs a break from screen time.

How it works

It functions as a plugin or MCP (Model Context Protocol) server that integrates with AI agents. It handles the conversion of spoken language to text (STT) and text back to speech (TTS). The system can use cloud-based services (like OpenAI) or local services for privacy and offline use, specifically utilizing Whisper.cpp for speech-to-text and Kokoro for text-to-speech.

Who it’s for

Developers and users of Claude Code or other MCP-capable agents who want a voice-driven interface for their AI interactions.

Highlights

  • Local-first options: Supports offline operation via Whisper.cpp and Kokoro.
  • Low latency: Optimized for fast, real-time conversational feel.
  • Smart silence detection: Automatically stops recording when the user stops speaking.
  • Cross-platform: Compatible with Linux, macOS, Windows (via native or WSL), and NixOS.

Related

  • Project
    AlexGladkov/claude-in-mobile

    `mcp-devices` (aka `claude‑in‑mobile`) is a modular Node/Rust server that lets Claude‑style AI agents control Android, iOS, web, desktop, Aurora, and HarmonyOS devices. Install the base (`npm i -g mcp-devices`), add platform plugins (e.g., `@mcp-devices/plugin-android`), enable them, and point an MCP‑compatible client at the server. The tool provides actions like screenshots, taps, UI inspection, live debugging, and testing, enabling AI‑driven device automation and embodied‑agent research.

  • Project
    domdomegg/computer-use-mcp

    An MCP server that allows Claude and other AI models to control a local computer via keyboard and mouse automation.

  • Project
    MiniMax-AI/MiniMax-MCP

    An official Model Context Protocol (MCP) server that enables AI clients like Claude and Cursor to generate speech, clone voices, and create images and videos using MiniMax APIs.

  • Project
    resend/resend-mcp

    Resend MCP Server is an open‑source Node.js package that implements the MCP interface, letting AI agents (Claude, Cursor, Copilot, etc.) manage the full Resend email platform—sending messages, handling contacts, templates, broadcasts, domains, webhooks, and more—via either a hosted remote server or a locally run stdio/HTTP server.

  • Project
    AminForou/mcp-gsc

    An MCP server that connects Google Search Console to AI assistants, enabling SEO analysis and site management through natural language conversations.