openai-whisper
Local speech-to-text with the Whisper CLI (no API key).
When & Why to Use This Skill
The OpenAI Whisper CLI skill enables powerful, local speech-to-text capabilities directly within your AI workflow. It provides high-fidelity transcription and translation of audio files without requiring an internet connection or external API keys. By leveraging the industry-standard Whisper model locally, it ensures maximum data privacy and cost-efficiency while transforming voice recordings into structured text, subtitles (SRT), or translated documents seamlessly.
Use Cases
- 1. Meeting & Interview Transcription: Convert recorded business meetings, academic lectures, or journalistic interviews into accurate text for documentation and analysis.
- 2. Automated Subtitling: Generate synchronized SRT or VTT subtitle files for video content to improve accessibility and SEO for video platforms.
- 3. Secure Data Processing: Transcribe sensitive or confidential audio recordings locally to comply with strict data privacy regulations, ensuring no data is uploaded to the cloud.
- 4. Multilingual Translation: Directly translate foreign language audio files into English text, streamlining cross-border communication and content research.
| name | openai-whisper |
|---|---|
| description | Local speech-to-text with the Whisper CLI (no API key). |
| homepage | https://openai.com/research/whisper |
| metadata | {"clawdbot":{"emoji":"🎙️","requires":{"bins":["whisper"]},"install":[{"id":"brew","kind":"brew","formula":"openai-whisper","bins":["whisper"],"label":"Install OpenAI Whisper (brew)"}]}} |
Whisper (CLI)
Use whisper to transcribe audio locally.
Quick start
whisper /path/audio.mp3 --model medium --output_format txt --output_dir .whisper /path/audio.m4a --task translate --output_format srt
Notes
- Models download to
~/.cache/whisperon first run. --modeldefaults toturboon this install.- Use smaller models for speed, larger for accuracy.