# video-transcription

Pulls speech out of a local or remote video and returns a transcript with timestamps. Useful when you need captions or edit markers.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 27
- Author: PostPlusAI
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/PostPlusAI/postplus-skills/tree/HEAD/skills/40-creative/video-transcription/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/video-transcription

## What it does

The skill fires a hosted transcription job with `postplus media transcribe`. You hand the source straight to `--video`: a local path, an HTTPS link, an existing PostPlus media reference, or a data URI. The CLI checks and prepares local media first, so the hosted submit happens once. Duration has to be derived from the video and passed through `--duration-seconds` for validation.

The job is async. Submit stores the run handle, the current status, and transcript artifacts once they exist. Returned formats vary, so do not count on one fixed transcript schema. While status is pending, the skill keeps the result path and follows the resume command it gets back. Firing a second job is off the table.

Subtitles are a separate, local step. With a timed transcript already in hand, SRT or ASS output is built from the subtitle conversion reference and no further hosted call is made. Working files land in `.postplus/video-transcription`; finished exports for the user stay outside `.postplus`. Semantic visual analysis is not this skill's job, that is `media-analysis`. Runs spend PostPlus credits, and the skill checks price and balance first, stopping when the balance is short.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill video-transcription -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/video-transcription/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/video-transcription/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill video-transcription -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/video-transcription/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill video-transcription -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/video-transcription/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install PostPlusAI/postplus-skills video-transcription
```

2. **Manually: put the files in place**
- File: `.github/skills/video-transcription/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill video-transcription -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/PostPlusAI/postplus-skills --path skills/40-creative/video-transcription
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/video-transcription/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill video-transcription -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/PostPlusAI/postplus-skills/tree/HEAD/skills/40-creative/video-transcription/SKILL.md

## When to use it
- get a timestamped speech transcript from a video file
- turn an existing transcript into SRT or ASS without re-transcribing
- produce edit-prep timestamps
- build captions in another language from a requested transcript
- transcribe speech in a remote video over an HTTPS link

## Example prompts
- Transcribe `./reference.mp4` and give me timestamps
- Build an SRT from the existing transcript `transcript.json`
- Transcribe the video at this link and save the result to `result.json`

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 349800 installs

From the same set: [postplusai/postplus-skills](https://affpapa.org/en/nevibecode/by/postplusai/postplus-skills.md) — 12 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md