Obsidian Second Brain
Lets Claude Code save, find and update notes in your Obsidian vault across sessions
by Eugeniu Ghelbur
VoiceMode
by Mike BaileyConnectorGet organised
Lets you talk to Claude Code out loud and hear its answers spoken back
About VoiceMode
VoiceMode adds spoken conversation to Claude Code and other AI coding assistants: you talk, it turns your speech into text, the assistant replies and the answer is read aloud. Voice can run offline on your computer.
For Claude Code usersPeople who prefer to talkPeople giving their eyes a rest
Made by Mike Bailey
An open-source project by developer Mike Bailey, published on GitHub.
- Stars
- ★ 1.4k
- License
- MIT
- Cost
- Free
- Level
- Intermediate
- Runs
- Local
Overview
VoiceMode is a connector that adds spoken conversation to Claude Code. You speak, it turns your words into text, Claude works on the request and the reply is read back to you, and it stops recording when you stop talking. It can use speech services that run on your own computer, so voice can stay offline, or a cloud voice service. It suits people who want to keep working with Claude Code while their hands or eyes are busy.
It can run speech-to-text and text-to-speech entirely on your own computer, so you can talk to your agent without sending audio to a cloud service.
Try these first
Start with the first one: it is a small task you can check easily.
- Let's talk. Tell me the name of the folder we are working in.First try · uses microphone
- Read me a short summary of what changed in this project today.
- Start a voice conversation and keep listening until I say we are done.uses microphone
- Check which voice services you are using, local or cloud.
Example prompts written by Agent Flows Hub.
Capabilities
From the creator's documentation.
| Toolset | What your agent can do | Access |
|---|---|---|
| Voice conversation | Listens to you, sends the text to Claude Code and speaks the reply | Microphone |
| Silence detection | Stops recording when you stop speaking | Microphone |
| Local speech services | Optional Whisper speech-to-text and Kokoro text-to-speech on your own computer | Your computer |
| Cloud fallback | Uses OpenAI's voice services when local ones are not available; needs an OpenAI API key | OpenAI API |
Good to know
Talk to Claude Code instead of typing, for example while walking or cooking. VoiceMode records what you say, passes the text to Claude Code and reads the reply back, using local or cloud speech services.
Limits
- Setup installs extra pieces: the VoiceMode command-line tool and, for offline use, local speech-to-text and text-to-speech services. Some systems also need audio packages such as ffmpeg and portaudio.
- Without the local services it falls back to OpenAI's voice services, which needs an OpenAI API key and sends audio to OpenAI.
Notes by Agent Flows Hub (original project name: voicemode), written from the creator's documentation, not from running it ourselves. VoiceMode README and quick start · VoiceMode website
Stuck setting it up?
Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.
More to get organised
Other connectors
- Windows Computer Use for DSH Lets an AI agent see and use Windows apps and web pages: click, type and read the screen
- Windows-MCP Lets your AI agent open apps, click, type and manage files on your Windows PC
- Wix MCP Lets your AI assistant manage your Wix sites, from store products to bookings and blogs
- Xiaohongshu MCP Lets your AI agent search Xiaohongshu and post picture or video notes from your account
- Zapier MCP Lets your AI agent send emails, add rows and post messages in 9,000+ apps
- Zotero MCP Lets your AI assistant search, read, summarise and annotate papers in your Zotero library
See all 52 connectors · An MCP server is missing or disconnected