#240240th of 389 in Skills, plugins and promptsFor voice, speech and music

voicemode

Voice conversations with Claude Code and other MCP agents

Stars
1.5k
License
MIT
Last commit
Nov 2026
Last release
Oct 2026
Language
Python
Stars, last 29 weeks+371
21 Apr 2026: 1,079 stars28 Apr 2026: 1,111 stars5 May 2026: 1,130 stars12 May 2026: 1,149 stars19 May 2026: 1,167 stars26 May 2026: 1,176 stars2 Jun 2026: 1,185 stars9 Jun 2026: 1,201 stars16 Jun 2026: 1,211 stars23 Jun 2026: 1,221 stars30 Jun 2026: 1,235 stars7 Jul 2026: 1,250 stars14 Jul 2026: 1,262 stars21 Jul 2026: 1,272 stars28 Jul 2026: 1,288 stars4 Aug 2026: 1,298 stars11 Aug 2026: 1,309 stars18 Aug 2026: 1,322 stars25 Aug 2026: 1,329 stars1 Sept 2026: 1,339 stars8 Sept 2026: 1,346 stars15 Sept 2026: 1,358 stars22 Sept 2026: 1,366 stars29 Sept 2026: 1,377 stars6 Oct 2026: 1,384 stars13 Oct 2026: 1,396 stars20 Oct 2026: 1,408 stars27 Oct 2026: 1,421 stars3 Nov 2026: 1,436 stars10 Nov 2026: 1,450 stars

1,079 on 21 Apr 20261,450 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

VoiceMode is an MCP server and Claude Code plugin that adds spoken input and output to coding agent sessions. It records from the microphone with silence detection, then transcribes and speaks replies through local Whisper.cpp and Kokoro or through OpenAI as a fallback. Install via the Claude Code plugin marketplace or the uvx installer.

Who it is for: Claude Code users who want hands-free voice conversations with their agent

Strengths

  • Local Whisper.cpp STT and Kokoro TTS expose OpenAI-style APIs, so it can run fully offline
  • Installs as a Claude Code plugin or via uvx, with MCP launcher for other agents
  • Runs on Linux, macOS, Windows (native or WSL) and NixOS, Python 3.10-3.14
  • Silence detection ends recording automatically when you stop speaking

Weaknesses

  • Needs a microphone and speakers; WSL2 requires pulseaudio packages for mic access
  • Native dependencies (ffmpeg, portaudio, compiler toolchain) must be installed per platform
  • Documentation is centered on Claude Code; setup for other MCP agents is not detailed
  • Cloud fallback depends on an OpenAI API key

What it needs

  • Needs uv, ffmpeg, portaudio, Whisper.cpp, Kokoro, OpenAI API (optional fallback)
  • Models: Whisper.cpp, Kokoro, OpenAI STT/TTS

Quick answers

Is voicemode open source?

Yes. Its code is on GitHub under the MIT license.

Also in Skills, plugins and prompts

See all 389
Also in Skills, plugins and prompts
RankProjectScore
1claude-memPersistent cross-session memory plugin for Claude Code and other coding agents116.1k stars+16,557 (+17%) in 30 daysApache-2.097 out of 100
2impeccableDesign skill with 24 slash commands for AI coding agents' frontend output Live demo ↗ (opens in a new tab)108k stars+28,186 (+35%) in 30 daysApache-2.097 out of 100
3gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles141.2k stars+5,515 (+4.1%) in 30 daysMIT96 out of 100
#4rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex Live demo ↗ (opens in a new tab)81.5k stars+7,413 (+10%) in 30 daysMIT96 out of 100
#5cavemanShortens coding-agent replies and compresses tool output before the model reads it Live demo ↗ (opens in a new tab)119k stars+8,390 (+7.6%) in 30 daysApache-2.095 out of 100