Video Transcription

Turns video files into timed transcripts using hosted Whisper, with timestamps enabled by default so you can hand off to subtitle tools or use for edit prep. The async flow writes everything under `.postplus/video-transcription` and gives you a generation handle, so you're not stuck polling in the conversation. It calculates duration from the source before submitting for billing preflight, and the handoff to `subtitle-packager` is built in when you need SRT or ASS output. The stop conditions are strict: if the CLI fails or required inputs are missing, it reports and stops rather than guessing or falling back to workarounds. Good for speech extraction and caption generation when you want structured, timestamped text out of video.

skills.sh installs: 1.2K
GitHub stars: 27
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add postplusai/postplus-skills --skill video-transcription --agent claude-code

Installs into .claude/skills of the current project.

Files

Video Transcription

Use When

The input is a video file and the goal is speech extraction, timed transcript, caption generation, multilingual transcript, or edit-prep timestamps.
Use media-analysis instead when the user needs semantic visual analysis.

If a timed transcript already exists and only subtitle output is requested, skip transcription and read the local subtitle conversion reference.

Do Not Use When

The task needs new creative generation or visual analysis rather than speech or subtitles.
Required inputs are missing and guessing would change the result.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly