🎙️ Video Whisper

Local video/audio transcription on Apple Silicon using MLX Whisper.

No API keys. No cloud. No cost. Runs entirely on your Mac.

Supports YouTube, Bilibili (B站), Xiaohongshu (小红书), Douyin (抖音), podcasts, and local files.

Quick Start

# Install dependencies
brew install yt-dlp ffmpeg
python3 -m venv ~/.openclaw/venvs/whisper
~/.openclaw/venvs/whisper/bin/pip install mlx-whisper

# Transcribe
bash scripts/transcribe.sh "https://www.youtube.com/watch?v=..."

Output: /tmp/whisper_output.txt (text) + /tmp/whisper_output.json (with timestamps)

Features

• 🍎 Apple Silicon optimized — MLX framework, fast inference on M1/M2/M3/M4
• 🌍 Multi-language — auto-detects language, strong Chinese/English/Japanese support
• 📺 Multi-platform — YouTube, Bilibili, Xiaohongshu, Douyin, and 1000+ sites
• 📁 Local files — MP4, MP3, WAV, M4A, etc.
• ⏱️ Timestamps — JSON output includes per-segment timing
• 🤖 OpenClaw ready — drop into skills/ and let your AI agent transcribe & summarize

Performance

On Mac mini M4 (16GB):

| Video Length | Time (medium model) | |-------------|-------------------| | 5 min | ~30-40s | | 10 min | ~60-90s | | 30 min | ~3-4 min | | 60 min | ~6-8 min |

See SKILL.md for full docs, model options, and integration guide.

License

MIT