Openclaw Voice

# OpenClaw Voice Skill

## Overview
Voice conversation with AI via Whisper STT + ElevenLabs TTS. Records audio, transcribes, generates spoken responses, stores transcripts. For v1: CLI-based commands only (no real-time conversation mode — that's v1.1). Focus on transcript storage/search + TTS/STT wrappers.

## Tech Stack
- Node.js ESM
- better-sqlite3 (WAL mode always)
- commander for CLI
- uuid for IDs
- @openclaw/interchange (import from ../interchange/src/index.js)
- NO external audio packages — use child_process to call sox/rec and ffplay

## Database
See migrations/001_initial.sql for schema.

## CLI
See src/cli.js for commands.

## Tests
Run with npm test.

# openclaw-voice

[![Tests](https://img.shields.io/badge/tests-10%20passing-brightgreen)]() [![Node](https://img.shields.io/badge/node-%3E%3D18-blue)]() [![License: MIT](https://img.shields.io/badge/license-MIT-yellow)]()

> Voice-first interaction with conversation tracking and ElevenLabs integration.

Manage voice conversations, transcripts, and voice profiles from the command line. Track conversation sessions with full transcript history, search across past interactions, and configure ElevenLabs voice profiles for TTS output. **v1.1 coming soon:** phone calling via Twilio.

## Features

- **Conversation sessions** — start, end, and list voice conversations with summaries
- **Transcript management** — add and review transcript lines with speaker labels and confidence scores
- **Voice profiles** — manage ElevenLabs voice profiles with configurable settings
- **Default profile** — set a preferred voice for quick access
- **Searchable history** — search across all past conversations and transcripts
- **Interchange output** — publish conversation data as `.md` files
- **Backup & restore** — full database backup and recovery
- 🔜 **Phone calling** — Twilio integration for inbound/outbound calls (v1.1)

## Quick Start

```bash
cd skills/voice
npm install

# Start a conversation
node src/cli.js conversation start --summary "Weekly standup"

# Add transcript lines
node src/cli.js transcript add <conv-id> --speaker user --text "What's on the agenda?"
node src/cli.js transcript add <conv-id> --speaker assistant --text "Three items to cover today."

# Review and search
node src/cli.js transcript show <conv-id>
node src/cli.js transcript list --search "standup"

# Set up a voice profile
node src/cli.js profile add nova --voice-id EXAVITQu4vr4xnSDxMaL
node src/cli.js profile default nova
```

## CLI Reference

### Conversations

```bash
voice conversation start [--summary <text>]
voice conversation end <conversation-id> [--summary <text>]
```

### Transcripts

```bash
voice tr...