# mbailey/voicemode

Natural voice conversations with Claude Code

Repository: https://github.com/mbailey/voicemode
Canonical: https://ross.abutalabs.com/products/voicemode
Homepage: https://voicemode.dev
Language: Python
License: MIT
License Family: permissive
Topics: asr, claudecode, kokoro, livekit, mcp, mcp-server, tts, voice, whisper, voicemode, anthropic, claude
Last push: 2026-08-24T13:12:58+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 82, longevity 32
- inputs: {"age_days": 451, "days_push": 9, "days_rel": 43, "gap_med": 0, "n_releases_24m": 158}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1339, forks 186 (observed 2026-08-28T04:04:25.881518+00:00)

## What it is
VoiceMode is a Python-based MCP server and Claude Code plugin that enables natural, hands-free voice conversations with Claude Code and other MCP-capable AI coding agents. It combines speech recognition (Whisper or OpenAI) and text-to-speech (Kokoro or OpenAI) with smart silence detection, and can run entirely locally for privacy.

## Use cases
- talk to Claude Code instead of typing
- hands-free coding assistant conversations while cooking or walking
- run local offline speech-to-text and text-to-speech for AI agents
- add voice interaction to MCP-capable AI assistants
- give my eyes a break and debug by voice
- low-latency voice chat with an AI coding agent
- private voice conversations with AI without cloud services

## When to choose
- you use Claude Code or another MCP-capable agent and want voice interaction
- you need offline/local STT and TTS for privacy
- your hands or eyes are busy and you want to interact with your coding agent
- you want low-latency, natural back-and-forth voice conversations

## When to avoid
- you need voice features in a non-MCP or non-Claude environment without adaptation
- you have no microphone or speakers
- you need a fully managed cloud voice product with no local setup
- you require languages or voices not supported by Whisper/Kokoro/OpenAI

## Facets
- artifact type: cli-tool
- maturity: active
- function: speech-recognition, tts, mcp, chatbot, cli
- domain: speech-processing, developer-tools, artificial-intelligence
- platform: windows, python, cli
- tags: voice-conversation, claude-code, whisper, kokoro, hands-free, mcp-server, livekit, voice-cloning, ai-agents, command-line, linux, macos

## Member repositories
- mbailey/voicemode (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.881518+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:43:55.537828+00:00, confidence not recorded.
  - readme: https://github.com/mbailey/voicemode (fetched 2026-08-28T04:04:25.881518+00:00, sha f8a81cd6f04c)
  - homepage: https://voicemode.dev (fetched 2026-08-29T12:02:54.375239+00:00, sha 60b75d2f6150)
- Data as of 2026-08-30T08:39:29.467469+00:00.