# Scribiz

Get the transcript, on-screen text, summary, and chapters of any video or audio with...

- Repository: https://github.com/Illyism/seo-skills (695 stars)
- Category: Writing
- License: see repository
- Last updated: 2026-10-30
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Illyism/seo-skills --skill scribiz -g -a claude-code -y`
Codex: `npx skills add Illyism/seo-skills --skill scribiz -g -a codex -y`
Cursor: `npx skills add Illyism/seo-skills --skill scribiz -g -a cursor -y`
Gemini CLI: `npx skills add Illyism/seo-skills --skill scribiz -g -a gemini-cli -y`

## Description

Get the transcript, on-screen text, summary, and chapters of any video or audio with Scribiz. Use when the user wants to transcribe a YouTube, TikTok, Instagram, podcast, or local media file, generate SRT or VTT subtitles, summarize a video, ask questions about a video, or turn a video into a blog post, show notes, or social posts.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Scribiz

[Scribiz](https://scribiz.com) turns a video or audio link, or a local file, into a transcript with speakers and timestamps, the text shown on screen, a summary, and chapters. It works when a video has no captions.

Docs: [scribiz.com/docs](https://scribiz.com/docs). Every docs page is also Markdown: add `.md` to the path.

## Pick a way in

```
What does the agent have?
├── An MCP client (Claude Code, Cursor, Codex) and a link
│   └── Use the MCP server. Best for questions, summaries and search.
├── A shell and a link or local file
│   └── Use the CLI. Best for subtitles, files on disk and batch jobs.
└── Neither
    └── Send the user to scribiz.com to paste the link.
```

## MCP server

Hosted at `https://scribiz.com/mcp` (Streamable HTTP). No key needed to start.

```bash
# Claude Code
claude mcp add --transport http scribiz https://scribiz.com/mcp
```

Cursor, in `~/.cursor/mcp.json`:

```json
{ "mcpServers": { "scribiz": { "url": "https://scribiz.com/mcp" } } }
```

```toml
# Codex: ~/.codex/config.toml
[mcp_servers.scribiz]
url = "https://scribiz.com/mcp"
```

Tools:

- `get_video_context`: summary, chapters and key moments in under 2,000 tokens. Start here.
- `search_video`: find where a phrase is said and read only those minutes.
- `ask_video`: an answer with 3, 5 cited moments, each a timestamp link.
- `get_transcript`: the full transcript, when you really need all of it.
- `get_job`: check a running job.

Without a key the server reads captions, videos already processed and, within a small daily allowance, the link itself. It never looks at the picture. With an API key (`Authorization: Bearer $SCRIBIZ_API_KEY`) it uses the account's minutes and can read the screen. Other clients: [MCP install](https://scribiz.com/docs/mcp/install.md).

Prefer `get_video_context` then `search_video` over pulling the whole transcript. A two-hour talk is more than 25,000 tokens.

## CLI

The rest: https://github.com/Illyism/seo-skills/blob/HEAD/content/scribiz/SKILL.md