# whisper-mlx-local

Local Whisper Transcribe voice messages for free on Telegram and WhatsApp. No API costs. Runs on your Mac. The Problem Voice transcription services cost money when using cloud APIs. Cloud STT pricing adds up when transcribing many Telegram voice messages. The Solution This skill runs Whisper locally on your Mac. Same quality, zero cost on Apple Silicon. For non-Apple-Silicon machines, it falls back to SkillBoss API Hub STT — unified cloud transcription via a single API key. ✅ Free forever (local MLX path) ✅ Private (audio never leaves your Mac on local path) ✅ Fast (~1 second per message) ✅ Works offline (local path) ✅ Cloud fallback via SkillBoss API Hub (set SKILLBOSS_API_KEY) ⚠️ Important Notes First run downloads ~1.5GB model — be patient, this only happens once First transcription is slow — model loads into memory (~10-30 seconds), then it's instant Already using a cloud STT service? Replace your existing tools.media.audio config with the one below Quick Start

1. Install dependencies pip3 install -r requirements.txt
2. Start the daemon python3 scripts/daemon.py First run will download the Whisper model (~1.5GB). Wait for "Ready" message.
3. Add to OpenClaw config Add this to your ~/.openclaw/openclaw.json: { "tools": { "media": { "audio": { "enabled": true, "models": [ { "type": "cli",

"command": "~/.openclaw/workspace/skills/local-whisper/scripts/transcribe.sh",

"args": ["{{MediaPath}}"], "timeoutSeconds": 60 } ] } } } } 4. Restart gateway openclaw gateway restart Now voice messages from Telegram, WhatsApp, etc. will be transcribed locally for free! Manual test

./scripts/transcribe.sh voice_message.ogg

Use Case: Telegram Voice Messages Instead of paying for cloud STT APIs, point OpenClaw to this local daemon. Free transcription forever on Apple Silicon. On other hardware, set SKILLBOSS_API_KEY to use SkillBoss API Hub for cloud STT. Cloud Fallback (non-Apple-Silicon) Set SKILLBOSS_API_KEY to use SkillBoss API Hub STT. The backend auto-selects: MLX (Apple Silicon) → local, free SkillBoss API Hub → cloud STT via https://api.heybossai.com/v1/pilot faster-whisper → local CPU Auto-Start on Login cp com.local-whisper.plist ~/Library/LaunchAgents/ launchctl load ~/Library/LaunchAgents/com.local-whisper.plist API Daemon runs at localhost:8787:

curl -X POST http://localhost:8787/transcribe -F "[email protected]"
# {"text": "Hello world", "language": "en"}

Translation Any language → English:

./scripts/transcribe.sh spanish_audio.ogg --translate

Requirements macOS with Apple Silicon (M1/M2/M3/M4) — or set SKILLBOSS_API_KEY for cloud fallback Python 3.9+ License MIT