Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
deepgram avatar

Deepclaw Voice

  • 24 installs
  • 79 repo stars
  • Updated February 9, 2026
  • deepgram/deepclaw

Adds real-time voice input/output (Deepgram speech-to-text and text-to-speech) to a Claude/agent workflow so a solo builder can talk to and hear from their coding agent.

About

DeepClaw-voice adds a Deepgram-powered voice layer to a Claude/agent setup, turning speech into text on the way in and text back into speech on the way out. A solo builder reaches for it to interact with a coding agent hands-free or to prototype voice-driven agent experiences without stitching the audio pipeline together from scratch.

  • Voice interface for Claude/agents via Deepgram
  • Real-time speech-to-text and text-to-speech
  • Talk to your coding agent hands-free
  • Built on Deepgram's low-latency voice APIs

Deepclaw Voice by the numbers

  • 24 all-time installs (skills.sh)
  • Ranked #9,876 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/deepgram/deepclaw --skill deepclaw-voice

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs24
repo stars79
Last updatedFebruary 9, 2026
Repositorydeepgram/deepclaw

What it does

Adds real-time voice input/output (Deepgram speech-to-text and text-to-speech) to a Claude/agent workflow so a solo builder can talk to and hear from their coding agent.

Who is it for?

Builders wanting a hands-free or voice-driven agent experience

Skip if: Projects that need no audio/voice interaction

When should I use this skill?

Adding speech input/output to a Claude or agent workflow

What you get

  • a working voice interface for an agent

Related skills

FAQ

What does DeepClaw-voice do?

It adds Deepgram-powered speech-to-text and text-to-speech so you can talk to and hear from a Claude/agent.

What do I need to run it?

A Deepgram API key and an agent runtime to attach the voice layer to.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.