audio-transcribe
由 aktheknight 提供
Media & Streaming简介
Auto-transcribe voice messages using faster-whisper (local, no API key needed).
描述
该技能的功能
Transcribes audio files locally using faster-whisper, a CPU-compatible Whisper implementation. No API key or internet connection is required for transcription. Clawdbot can auto-transcribe incoming voice messages when the skill is enabled.
Runs entirely on-device, so audio never leaves the machine and there are no per-request costs or usage limits.
何时使用
- Transcribing voice notes sent over messaging apps
- Converting recorded calls or meetings to text
- Archiving voice memos as searchable transcripts
- Captioning audio files for accessibility reviews
- Processing voice messages without uploading to external services
示例工作流
User asks: transcribe this voice message at /tmp/message.ogg
- 1
Locate the audio file at the specified path
- 2
Run transcribe.py with the file path as argument
- 3
faster-whisper loads the configured model (small by default)
- 4
Model processes the audio locally and outputs a text transcript
Plain text transcript of the audio content
安装
clawhub install aktheknight/audio-transcribe运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。