Skip to content

About

Voice conversation loop for OpenClaw — talk to your AI agent like a phone call

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

8 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OpenClaw Voice Loop 🎙️

Talk to your AI agent like a phone call.

Mic → Whisper → OpenClaw → TTS → Speaker

A continuous voice conversation loop that captures your speech, transcribes it locally with Whisper, sends it to any OpenClaw gateway (any model), and speaks the response back to you.

How It Works

  1. Listen — Records from your mic, detects speech, stops on silence
  2. Transcribe — Local Whisper model converts speech to text
  3. Think — Sends text to your OpenClaw agent via openclaw agent CLI
  4. Speak — Converts the reply to audio via ElevenLabs, OpenAI TTS, Edge TTS, or macOS say (unless the agent already generated audio itself via a tts tool, in which case that's played directly)
  5. Repeat

Works with any OpenClaw gateway and any model configured on that gateway (Claude, GPT, Gemini, local models, etc.).

Requirements

  • Python 3.9+
  • OpenClaw CLI installed and configured
  • ffmpeg and portaudio

macOS

brew install ffmpeg portaudio

Linux

sudo apt install ffmpeg portaudio19-dev

Setup

git clone https://github.com/jdawe/openclaw-voice-loop.git
cd openclaw-voice-loop
pip install -r requirements.txt

Usage

# Basic — uses Edge TTS if installed, else macOS `say`
python voice_loop.py

# With ElevenLabs TTS (highest quality)
export ELEVENLABS_API_KEY=your_key_here
python voice_loop.py

# With OpenAI TTS
export OPENAI_API_KEY=your_key_here
export OPENAI_VOICE=nova  # optional, default: alloy
python voice_loop.py

# With a remote OpenClaw gateway
export OPENCLAW_GATEWAY_URL=wss://your-gateway.example.com
export OPENCLAW_GATEWAY_TOKEN=your_token
python voice_loop.py

Configuration

All configuration is via environment variables:

TTS priority: ElevenLabs → OpenAI → Edge TTS → macOS say (first available option wins; each tier falls through to the next on failure).

Variable Default Description
ELEVENLABS_API_KEY (none) ElevenLabs API key (highest TTS priority). Falls back to ~/.config/elevenlabs/config.json ({"api_key": "..."}) if unset
ELEVENLABS_VOICE_ID 21m00Tcm4TlvDq8ikWAM ElevenLabs voice ID (default: Rachel)
ELEVENLABS_SPEED 1.0 Playback speed multiplier
OPENAI_API_KEY (none) OpenAI API key (second TTS priority)
OPENAI_VOICE alloy OpenAI TTS voice: alloy, echo, fable, onyx, nova, shimmer
EDGE_TTS_VOICE en-US-AriaNeural Edge TTS voice, used if no API key is set and edge-tts is installed
WHISPER_MODEL tiny Whisper model: tiny, base, small, medium, large
OPENCLAW_GATEWAY_URL (none) Remote gateway WebSocket URL
OPENCLAW_GATEWAY_TOKEN (none) Gateway auth token
VOICE_SESSION_ID voice-loop OpenClaw session ID (maintains conversation context)
VOICE_MODEL (gateway default) Model override, e.g. anthropic/claude-sonnet-5. Voice conversations want low latency — the gateway's default model may be larger/slower than that calls for. Must be one of your gateway's configured primary/fallback models
AGENT_TIMEOUT 60 Seconds to wait for agent reply
SAY_RATE 350 macOS say words per minute
MAX_TURNS 50 Max conversation turns before auto-reset
TTS_STRICT (off) If set, a TTS provider failure raises an error instead of silently falling through to the next tier. Use this if hearing the wrong voice would be worse than hearing nothing
TTS_PROVIDER (auto) Pin the provider explicitly: elevenlabs, openai, edge, or macos. Skips auto-pick-by-key-presence — useful if a stale key shouldn't silently decide the voice

Tips

  • First run downloads the Whisper model (~75MB for tiny). Subsequent runs are instant.
  • Use tiny or base Whisper models for fastest transcription. small is a good accuracy/speed tradeoff.
  • The loop auto-calibrates your mic on startup — stay quiet for 1 second.
  • Whisper hallucination filtering is built in (ignores phantom "thank you" / "bye" transcriptions).
  • Sessions persist across turns, so the agent remembers context within a conversation.

License

MIT

About

Voice conversation loop for OpenClaw — talk to your AI agent like a phone call

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages