VideoTranscribe
One-command video/audio to clean text via subtitle scrape or Gemini
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 024c6b9
Ran the bundled transcribe.py live on a real YouTube lecture: it scraped and de-duplicated the auto-captions into a clean 5,300-character transcript at zero API cost, output a plain assistant cannot produce unaided. But it needs a manual yt-dlp and ffmpeg install, the audio path requires a Gemini API key wired into ~/.shared-skills/api-registry/.env, and the workflow files hard-code a ~/.shared-skills/VideoTranscribe path that does not match a normal ~/.claude/skills install, so a verbatim follow breaks until you fix the path.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What VideoTranscribe does
Transcribes local video/audio files or online URLs (YouTube, Bilibili, and other yt-dlp platforms) to text, preferring free subtitle scraping and falling back to Gemini 2.5 Flash or offline mlx-whisper. Triggers on requests to transcribe, caption, or summarize a video or audio source. Requires yt-dlp and ffmpeg installed, plus a Gemini API key for the audio path.
How to install VideoTranscribe
git clone https://github.com/Jane-xiaoer/claude-skill-video-transcribe
mkdir -p ~/.claude/skills
cp -r claude-skill-video-transcribe ~/.claude/skills/videotranscribe
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger VideoTranscribe
-
/videotranscribeOne-command video/audio to clean text via subtitle scrape or Gemini
It also activates on plain-language prompts like these:
-
Transcribe this YouTube lecture into clean text for me. -
Get me a transcript of this Bilibili video without paying for an API. -
Caption this local audio file using the offline whisper fallback.
Frequently asked questions
- Is the VideoTranscribe skill free?
- Yes. The skill itself is free from Jane-xiaoer/claude-skill-video-transcribe. SkillProof publishes the install command and an independent test verdict at no cost.
- Does VideoTranscribe work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Ran the bundled transcribe.py live on a real YouTube lecture: it scraped and de-duplicated the auto-captions into a clean 5,300-character transcript at zero API cost, output a plain assistant cannot produce unaided. But it needs a manual yt-dlp and ffmpeg install, the audio path requires a Gemini API key wired into ~/.shared-skills/api-registry/.env, and the workflow files hard-code a ~/.shared-skills/VideoTranscribe path that does not match a normal ~/.claude/skills install, so a verbatim follow breaks until you fix the path.
- What is the VideoTranscribe SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install VideoTranscribe?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use VideoTranscribe with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.