VideoShorts Transcriber

SkillMedia

Video transcription via faster-whisper. JSON + SRT with timecodes.

Use VideoShorts Transcriber in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add VideoShorts Transcriber and connect your AI. About a minute.

Then ask your AI: use the VideoShorts Transcriber skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

VideoShorts TranscriberStart free

The instructions your AI receives, as published by horosheff/hyperion-reels in skills/videoshorts-transcriber/SKILL.md and read by Ahel’s review.

cd scripts
python transcribe.py "<video_path>" -o "../videoshorts-memory/transcripts/<stem>" -m <model>

Проверить артефакты:
- transcript.json — segments + опционально words[] / _words (karaoke ASS)
- transcript.srt
- audio.wav

VIDEOSHORTS_WHISPER_WORD_TIMESTAMPS=1 (default) — word-level для субтитров
VIDEOSHORTS_WHISPER_LANGUAGE=ru — только реальный ISO-код (ru, en, …)
Brief / UI language: auto → не передавать --language auto и не ставить env в auto/detect/none
Автоопределение = language=None в faster-whisper (omit --language / unset env)
Worker нормализует auto/detect/пустую строку → None (не падает ValueError)

При падении Whisper — записать INC в pipeline-fix-queue.md, incident_report со ссылкой.

Advanced