🤖
openclaw-voice
Transcribe audio to text and generate spoken AI responses using Whisper and ElevenLabs via CLI with transcript storage and search.
安全通过
技能说明
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.
如何使用「openclaw-voice」？
- 打开小龙虾AI（Web 或 iOS App）
- 点击上方「立即使用」按钮，或在对话框中输入任务描述
- 小龙虾AI 会自动匹配并调用「openclaw-voice」技能完成任务
- 结果即时呈现，支持继续对话优化