OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Voice Agents

Voicemode

Voicemode is a Python MCP server that adds voice conversations to Claude Code and other MCP-capable agents, connecting speech recognition and text-to-speech services to an agent interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Voicemode — OpenViST project profile in Voice Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Voicemode when spoken interaction is more practical than typing, such as while cooking, walking, or taking a break from the screen.

Who it is for

  • Claude Code users who want to speak to an agent and hear replies.
  • Users of other MCP-capable agents seeking a voice interface.
  • People who want to interact with an agent while their hands or eyes are occupied.

Documented uses

  • Speak naturally to Claude Code instead of entering every interaction by typing.
  • Use a voice interface with an MCP-capable agent.
  • Choose local Whisper.cpp speech recognition and Kokoro speech output for offline use, or configure cloud voice services.
Before you choose

Requirements & limits

The documented interfaces are a Claude Code plugin and a Python installer/MCP server. The project lists Linux, macOS, Windows including WSL, and NixOS, with Python 3.10–3.14. A microphone and speakers are required. The repository specifies an MIT license.

  • The primary documented setup targets Claude Code; support is also described for other MCP-capable agents.
  • Local Whisper.cpp and Kokoro services are the stated route for offline use; cloud services are also configurable.
  • The Python installer route sets up dependencies and local voice services, while the plugin route is described as the fastest start for Claude Code users.
  • System dependencies differ by platform, with PulseAudio packages specifically noted for microphone access under WSL2.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Voicemode as a Claude Code plugin

Add the Voicemode plugin, install its dependencies and local voice services, then begin a conversation.

Before you start

  • Claude Code
  • A computer with a microphone and speakers

Steps

  1. Add the Voicemode marketplace with claude plugin marketplace add mbailey/voicemode.

  2. Install the plugin with claude plugin install voicemode@voicemode.

  3. In Claude Code, run /voicemode:install to install dependencies and local voice services.

  4. Start a conversation with /voicemode:converse.

Expected outcome

The plugin is installed in Claude Code and ready for voice conversations.

Guide limitations

  • The instructions require microphone and speaker hardware.
  • The README lists platform-specific system dependencies; WSL2 requires PulseAudio packages for microphone access.
Documentation 1 ↗
Source-based practical guide

Set up Voicemode through its Python installer

Install Voicemode and its local voice services, register it with Claude Code, and start a conversation.

Before you start

  • Claude Code
  • A computer with a microphone and speakers
  • The uv package manager; install it first if needed

Steps

  1. Run the documented uv installer if the package manager is not already installed.

  2. Run uvx voice-mode-install to set up dependencies and local voice services.

  3. Register the server in Claude Code with claude mcp add --scope user voicemode -- uvx --refresh --from voice-mode voicemode-mcp-launcher.

  4. If using OpenAI services as a fallback, set OPENAI_API_KEY; then start a conversation with claude converse.

Expected outcome

Voicemode is registered with Claude Code for voice conversations, with local services installed and an optional OpenAI fallback configured.

Guide limitations

  • The OpenAI API key applies to cloud-service use; it is not required for the documented local-service option.
  • System dependencies vary by operating system, and WSL2 requires PulseAudio packages for microphone access.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
mbailey/voicemode · Official homepage title · retained in its source language
How we review sourcesSuggest a correction