whisper-transcription
Turn podcasts, interviews, and videos into searchable text using OpenAI's Whisper model. Choose from multiple output formats—plain text, SRT subtitles, JSON, and more—with adjustable accuracy levels to match your needs. Handles batch processing and automatic language detection.
Whisper Transcription converts audio and video files to text using OpenAI's Whisper model for podcasts, interviews, and video subtitles.
AI-generated summary based on this skill's SKILL.md
Install
guia-matthieu/clawfu-skills/whisper-transcription · repository language: Python
git clone https://github.com/guia-matthieu/clawfu-skills
cp -r clawfu-skills/skills/automation/whisper-transcription ~/.claude/skills/whisper-transcriptionnpx skillfed install guia-matthieu/clawfu-skills/whisper-transcriptionFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does whisper-transcription convert audio and video files to searchable, editable text transcripts?
whisper-transcription uses OpenAI's Whisper model to automatically convert audio and video files into searchable text transcripts. The tool processes your media, detects the language automatically, and outputs editable text with optional timestamps. You can adjust accuracy levels to balance speed and precision, making your recordings fully searchable and ready for editing or repurposing.
Can whisper-transcription generate video subtitles automatically?
Yes, whisper-transcription generates video subtitles automatically in multiple formats including SRT, which is compatible with most video platforms. The tool extracts audio from your video files, transcribes the content with timestamps, and outputs subtitle files ready for upload to YouTube, Vimeo, or other platforms. This makes adding captions to your videos quick and efficient.
What formats does whisper-transcription support for batch transcribing multiple audio files?
whisper-transcription supports batch processing of multiple audio files in formats like MP3 and MP4. You can process several files efficiently in one operation, with output available in plain text, SRT subtitles, JSON, and other formats. The batch feature is ideal for handling large volumes of podcasts, interviews, or recordings without processing them individually.
How can I convert a podcast to text for repurposing into a blog post?
whisper-transcription converts podcasts to text by extracting the audio, transcribing it with the Whisper model, and outputting editable text. You can then repurpose this transcript into blog posts, articles, or other written content. The tool's adjustable accuracy levels and multiple output formats make it easy to get clean, usable text from your podcast episodes.
Does whisper-transcription support transcribing and translating foreign language audio?
whisper-transcription includes automatic language detection and can transcribe foreign language recordings. While primary focus is on transcription, the tool's flexibility with multiple output formats and accuracy controls allows you to work with international audio content and create multilingual transcripts for global audiences.
What license does whisper-transcription use?
whisper-transcription is released under the MIT license, making it open-source and freely available for both personal and commercial use. The MIT license allows you to use, modify, and distribute the tool with minimal restrictions, provided you include the original license notice.
SKILL.md
rendered from the published skill — quoted content, verbatim
Whisper Transcription
> Transcribe any audio or video to text using OpenAI's Whisper model - the same technology powering ChatGPT voice features.
When to Use This Skill
- Podcast repurposing - Convert episodes to blog posts, show notes, social snippets
- Video subtitles - Generate SRT/VTT files for YouTube, social media
- Interview extraction - Pull quotes and insights from recorded calls
- Content audit - Make audio/video libraries searchable
- Translation - Transcribe and translate foreign language content
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Structures production workflow | Final creative direction |
| Suggests technical approaches | Equipment and tool choices |
| Creates templates and checklists | Quality |
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 3 files
skills/automation/whisper-transcription/SKILL.md
skills/automation/whisper-transcription/scripts/main.py
skills/automation/whisper-transcription/scripts/requirements.txt