Transcribe audio or video into SRT subtitles using Whisper and wsp2srt.py.
npx skills add https://github.com/tpott/pub_musings --skill transcribe-srt
Please help me install this Agent Skill. Skill: transcribe-srt Source: https://github.com/tpott/pub_musings/tree/main/cc_plugins/skills/transcribe-srt Command: npx skills add https://github.com/tpott/pub_musings --skill transcribe-srt
Transcribes audio or video content into subtitle text, enabling you to generate SRT files for media that has no existing subtitles.
Provide a video or audio file and run whisper-cli to generate a transcript, then convert it to SRT with wsp2srt.py.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio or video into subtitles by running Whisper on the media file to generate a transcript, then formatting the output into SRT format using a Python script.
The best way to generate SRT subtitles for podcasts or lectures is using a Whisper-based workflow, which automatically transcribes spoken content and formats it into timestamped, synchronized subtitle text.
Yes, Whisper supports common media formats and can automatically create timed text for movies lacking existing captions, converting the spoken content into an SRT subtitle file.
The transcription process converts spoken content into an SRT file by first using Whisper to generate a timestamped transcript, which is then formatted into ready-to-use SRT subtitles via a Python formatter.
No specific external dependencies are required beyond the core environment, as the transcription workflow relies on Whisper and a Python-based SRT formatter to process media files.
SpillwaveSolutionsTranscribe audio and video to text using Whisper with markdown context grounding.
dkyazzentwatwaAdd text overlays and captions to video files using moviepy.
lordmacuExtract frames and audio tracks from video files using ffmpeg.
rollratDownload YouTube video transcripts and subtitles as text, SRT, or JSON.
