Skip to content
TakoAPI
Back to skills

voice-assistant

by charantejmandali18

Coding Agents & IDEs
1.4kDownloads reported by clawskills.sh
4Stars
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Real-time voice assistant for OpenClaw.

Description

What This Skill Does

Adds a voice interface to any OpenClaw agent. Browser mic audio streams through a configurable STT provider to your OpenClaw gateway, and the response comes back as spoken audio through a configurable TTS provider. Targets sub-2 second time-to-first-audio with full streaming at every stage.

Full end-to-end streaming across audio capture, STT, LLM, and TTS keeps total latency under 2.5 seconds, which browser-based voice tools typically don't achieve.

When to Use It

  • Dictating tasks to your agent hands-free while cooking or commuting
  • Running voice Q&A with a document-aware agent
  • Talking through code problems out loud and hearing solutions back
  • Getting spoken summaries of long reports without reading
  • Using multilingual voice input via ElevenLabs STT

Example Workflow

INPUT

User asks: "Set up voice chat with Deepgram STT and ElevenLabs TTS"

AGENT
  1. 1

    Copies .env.example to .env in the skill directory

  2. 2

    Sets VOICE_STT_PROVIDER=deepgram and VOICE_TTS_PROVIDER=elevenlabs in .env

  3. 3

    Prompts user to add DEEPGRAM_API_KEY and ELEVENLABS_API_KEY

  4. 4

    Runs uv run scripts/server.py to start the voice server

  5. 5

    Opens http://localhost:7860 in the browser

OUTPUT

Voice server running on port 7860. Click the mic to start talking to your agent.

Requirements

  • Deepgram API key (required if using Deepgram for STT or TTS)
  • ElevenLabs API key (required if using ElevenLabs for STT or TTS)

Installation

clawhub install charantejmandali18/voice-assistant

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links