Claude by Anthropic
A family of foundational AI models
Start new thread

Talk to Claude Code (with your voice) from anywhere

by•

Here's an MCP server that lets you talk to Claude Code from anywhere you can negotiate a WebRTC connection (or make a phone call):

I’ve been talking to all the programs I use on my computer as much as I can, and I have a bunch of different hacked-up ways to do that. This is a pretty clean implementation of an MCP server that any harness (like Claude Code) with MCP support should be able to use. This shows both the strengths and weaknesses of MCP in interesting ways, I think.

What I really want is deep, configurable integration of voice into Claude Code (and other programs that I have long-running “conversations” with, with seamless background process management and network transport). And I think that will actually start to be the norm at some point. Voice such a natural interface for so, so many kinds of interactions.

I was telling a friend the other day that our kids will think about keyboards the way I think about punch cards. “Kind of cool that they used to program computers like that.”

Video here:

791 views

Add a comment

Replies

Best

From tweet thread:

“ I always have multiple Claudes running, and I often want to check in on them when I'm not in front of a computer.”

Super cool! Thanks for sharing here!

Interesting - so you can keep talking into a long running claude task…throughout the day, while on the go?

“Our kids will think about keyboards the way I think about punch cards.”
This line hit me hard.
We’re not just building voice interfaces — we’re retiring the idea that computers need to be “typed at.”

have been thinking about something like this for longer now. it makes so much sense. I'm still not sure if those code diffs are really understandable over voice and I don't think keyboard is gonna disappear soonish but this will accelerate our work in many areas by so much.

Solid example of MCP being useful! Love it!

When you’re tired but reflective, typing might be clearer. When you’re energized and ideating, voice might unlock fluidity. When you’re anxious, typing might provide grounding. When you’re walking, voice is natural.

I see the core value of the MCP in providing multiple client transports to handle audio input, but for casual user it’s too hard to setup such a tool. probably, for voice recognition it’s better to use more ux friendly apps, which there are a lot of on the market
very cool project！
I built a basic voice assistant myself a few months ago and the hardest part was always keeping context alive between sessions. The "check in on a running Claude" use case is genuinely interesting — less about input and more about async monitoring. Gonna look at the pipecat repo.
Hm, looks interesting
yes very interesting!
123
Next
Last