Mlx Whisper
Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).
clawhub install mlx-whisperOpenAI Whisper:使用 Whisper 模型进行视频语音识别和转录。
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install openai-whisper # Then just tell Claude: "use Openai Whisper to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install openai-whisper
This Skill is compatible with the OpenClaw standard. After installation, a SKILL.md file is auto-generated, usable by any OpenClaw-compatible AI Agent (Claude Code, Cursor, Windsurf, etc.).
whisper to transcribe audio locally.whisper /path/audio.mp3 --model medium --output_format txt --output_dir .whisper /path/audio.m4a --task translate --output_format srt~/.cache/whisper on first run.--model defaults to turbo on this install.clawhub install openai-whisper
clawhub run openai-whisper --input meeting.mp3 --language auto --format jsonLocal speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).
clawhub install mlx-whisper