Voicemode

dev.voicemodePublished by voicemode.devv9.0.2Updated Oct 30, 2026

Natural voice conversations for AI assistants - STT/TTS via MCP

VerifiedSTDIODesktop onlyCommunication & Collaboration Media & Design

Server details

Identifier: dev.voicemode/voicemode
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to voicemode.dev. It runs from a package rather than a hosted endpoint, so there is no endpoint to match against that domain.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/dev.voicemode%2Fvoicemode.svg)](https://sourceweft.com/mcp/dev.voicemode%2Fvoicemode?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

VoiceMode adds speech-to-text and text-to-speech to MCP-capable agents so you can talk with an assistant and hear its replies.

What you can do: Speak to the assistant and hear spoken replies through a conversation tool, with low-latency turn-taking.
Stop recording automatically when you stop speaking, or disable silence detection for continuous capture.
Manage local voice services (Whisper speech-to-text, Kokoro text-to-speech) so it can run offline or privately.
Switch between local services and OpenAI cloud speech, or skip text-to-speech and show text only for faster responses.
Choose the audio format and Whisper model size through configuration.
When to use it: Useful when your hands or eyes are busy — walking, cooking, or taking a break from the screen — and you want to converse with Claude Code or another MCP agent by voice instead of typing.
Requirements: Runs locally as a Python package (Python 3.10-3.14) via uv or the Claude Code plugin, on Linux, macOS, Windows/WSL or NixOS. Needs a microphone and speakers plus system audio libraries such as ffmpeg and portaudio. An OPENAI_API_KEY is optional for cloud speech; local Whisper and Kokoro services can be installed instead.

Before you install

The optional OPENAI_API_KEY is a secret that, when used, sends your speech audio to OpenAI's cloud service; prefer local services for privacy. Installing local services and system audio packages changes your machine, and the README suggests allowing the converse and service tools without permission prompts, which removes a confirmation step. Debug audio saving can write recordings to disk.

Installation

In SourceWeft

Open Voicemode in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

VoiceMode

Natural voice conversations with Claude Code (and other MCP capable agents)

[PyPI Downloads] [PyPI Downloads] [PyPI Downloads]

VoiceMode enables natural voice conversations with Claude Code. Voice isn't about replacing typing - it's about being available when typing isn't.

Perfect for:

Walking to your next meeting
Cooking while debugging
Giving your eyes a break after hours of screen time
Holding a coffee (or a dog)
Any moment when your hands or eyes are busy

See It In Action

[VoiceMode Demo]

Quick Start

Requirements: Computer with microphone and speakers

Option 1: Claude Code Plugin (Recommended)

The fastest way for Claude Code users to get started:

bash

# Add the VoiceMode marketplaceclaude plugin marketplace add mbailey/voicemode
# Install VoiceMode pluginclaude plugin install voicemode@voicemode
## Install dependencies (CLI, Local Voice Services)
/voicemode:install
# Start talking!/voicemode:converse

# Add the VoiceMode marketplaceclaude plugin marketplace add mbailey/voicemode
# Install VoiceMode pluginclaude plugin install voicemode@voicemode
## Install dependencies (CLI, Local Voice Services)
/voicemode:install
# Start talking!/voicemode:converse

Option 2: Python installer package

Installs dependencies and the VoiceMode Python package.

bash

# Install UV package manager (if needed)curl -LsSf https://astral.sh/uv/install.sh | sh
# Run the installer (sets up dependencies and local voice services)uvx voice-mode-install
# Add to Claude Codeclaude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher
# Optional: Add OpenAI API key as fallback for local servicesexport OPENAI_API_KEY=your-openai-key
# Start a conversationclaude converse

# Install UV package manager (if needed)curl -LsSf https://astral.sh/uv/install.sh | sh
# Run the installer (sets up dependencies and local voice services)uvx voice-mode-install
# Add to Claude Codeclaude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher
# Optional: Add OpenAI API key as fallback for local servicesexport OPENAI_API_KEY=your-openai-key
# Start a conversationclaude converse

For manual setup, see the Getting Started Guide.

Features

Natural conversations - speak naturally, hear responses immediately
Works offline - optional local voice services (Whisper STT, Kokoro TTS)
Low latency - fast enough to feel like a real conversation
Smart silence detection - stops recording when you stop speaking
Privacy options - run entirely locally or use cloud services

Compatibility

Platforms: Linux, macOS, Windows (native or WSL), NixOS Python: 3.10-3.14

Configuration

VoiceMode works out of the box. For customization:

bash

# Set OpenAI API key (if using cloud services)export OPENAI_API_KEY="your-key"
# Or configure via filevoicemode config edit

# Set OpenAI API key (if using cloud services)export OPENAI_API_KEY="your-key"
# Or configure via filevoicemode config edit

See the Configuration Guide for all options.

Permissions Setup (Optional)

To use VoiceMode without permission prompts, add to ~/.claude/settings.json:

json

{  "permissions": {    "allow": [      "mcp__voicemode__converse",      "mcp__voicemode__service"    ]  }}

{  "permissions": {    "allow": [      "mcp__voicemode__converse",      "mcp__voicemode__service"    ]  }}

See the Permissions Guide for more options.

Local Voice Services

For privacy or offline use, install local speech services:

Whisper.cpp - Local speech-to-text
Kokoro - Local text-to-speech with multiple voices

These provide the same API as OpenAI, so VoiceMode switches seamlessly between them.

Installation Details

System Dependencies by Platform

Ubuntu/Debian

bash

sudo apt updatesudo apt install -y ffmpeg gcc libasound2-dev libasound2-plugins libportaudio2 portaudio19-dev pulseaudio pulseaudio-utils python3-dev

sudo apt updatesudo apt install -y ffmpeg gcc libasound2-dev libasound2-plugins libportaudio2 portaudio19-dev pulseaudio pulseaudio-utils python3-dev

WSL2 users: The pulseaudio packages above are required for microphone access.

Fedora/RHEL

macOS

NixOS

bash

# Use development shellnix develop github:mbailey/voicemode
# Or install system-widenix profile install github:mbailey/voicemode

# Use development shellnix develop github:mbailey/voicemode
# Or install system-widenix profile install github:mbailey/voicemode

Alternative Installation Methods

From source

NixOS system-wide

nix

# In /etc/nixos/configuration.nixenvironment.systemPackages = [  (builtins.getFlake "github:mbailey/voicemode").packages.${pkgs.system}.default];

# In /etc/nixos/configuration.nixenvironment.systemPackages = [  (builtins.getFlake "github:mbailey/voicemode").packages.${pkgs.system}.default];

Troubleshooting

Problem	Solution
No microphone access	Check terminal/app permissions. WSL2 needs pulseaudio packages.
UV not found	Run `curl -LsSf https://astral.sh/uv/install.sh \| sh`
OpenAI API error	Verify `OPENAI_API_KEY` is set correctly
No audio output	Check system audio settings and available devices

Save Audio for Debugging

Documentation

Getting Started - Full setup guide
Configuration - All environment variables
Whisper Setup - Local speech-to-text
Kokoro Setup - Local text-to-speech
Development Setup - Contributing guide

Full documentation: voicemode.dev

License

MIT - A Failmode Project

mcp-name: dev.voicemode/voicemode

Source: README.md at commit 126d15e

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v9.0.2LatestOct 29, 2026
v9.0.1Oct 25, 2026
v9.0.0Oct 25, 2026
v8.12.0Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

Voicemode

Overview

Installation

In SourceWeft

Other MCP clients

README

VoiceMode

See It In Action

Quick Start

Option 1: Claude Code Plugin (Recommended)

Option 2: Python installer package

Features

Compatibility

Configuration

Permissions Setup (Optional)

Local Voice Services

Installation Details

Ubuntu/Debian

Fedora/RHEL

macOS

NixOS

From source

NixOS system-wide

Troubleshooting

Save Audio for Debugging

Documentation

Links

License

Tools

Version history

Score