# ffmpeg-skill — AI Coding Tool Review & Pricing

> ffmpeg-skill is an agent skill and MCP server that gives Claude Code, Cursor, Codex or any MCP client a local video editor. It ships 42 FFmpeg tools and teaches the agent a fixed probe, edit, check and verify workflow, with a machine-readable contract derived from the tools' own CLI parsers.

Source: https://ai.dosa.dev/tools/ffmpeg-skill · Updated Nov 15, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: ffmpeg-skill
- **Company**: kajisho5
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Open Source
- **Official website**: https://kajisho5.github.io/ffmpeg-skill/

## Key features

- 42 FFmpeg tools for cutting, joining, silence and filler removal, captions, overlays, loudness and platform exports
- Install with `npx ffmpeg-skill` for Claude Code, Cursor or Codex, or as a Claude Code, Codex or Gemini CLI plugin
- Every tool also exposed as an MCP tool, with a core set of 12 advertised by default
- Machine-readable contract (`npx ffmpeg-skill contract --json`) generated from the argparse CLI definitions
- `--dry-run`, `--json` and `--plan` on every tool, plus `doctor` to check the local FFmpeg build
- Optional local transcription for captions via faster-whisper, whisper or Parakeet
- Python standard library only; tested in CI against FFmpeg 6.1 to 9.x

## Pricing

**Model**: Open Source

ffmpeg-skill is free and open-source under the MIT licence. It runs locally on your own FFmpeg and Python with no cloud service, account or API key; optional speech transcription uses a local engine you install.

## Who it is for

- **Best for**: Developers and creators who want a coding agent to edit, caption and export video on their own machine with verifiable results and no uploads.
- **Not ideal for**: People who want a graphical timeline editor or rendered motion graphics from code, or machines where FFmpeg 6.1+ and Python 3.10+ cannot be installed.

## Verdict

A carefully engineered, local-first way to hand video editing to a coding agent, with unusually strong verification and contract discipline.

## Recent updates

v3.9.0, v3.9.1 and v3.9.2 were all released on November 15, 2026; the repository was trending on GitHub on November 15, 2026, with more than 5,800 stars.

## Frequently asked questions

### Is ffmpeg-skill free?

Yes - ffmpeg-skill is Open Source. ffmpeg-skill is free and open-source under the MIT licence. It runs locally on your own FFmpeg and Python with no cloud service, account or API key; optional speech transcription uses a local engine you install.

### Is ffmpeg-skill open source?

Yes - ffmpeg-skill is open source. ffmpeg-skill is free and open-source under the MIT licence. It runs locally on your own FFmpeg and Python with no cloud service, account or API key; optional speech transcription uses a local engine you install.

### Who is ffmpeg-skill best for?

Developers and creators who want a coding agent to edit, caption and export video on their own machine with verifiable results and no uploads.

### Who is ffmpeg-skill not ideal for?

People who want a graphical timeline editor or rendered motion graphics from code, or machines where FFmpeg 6.1+ and Python 3.10+ cannot be installed.

### What are the best ffmpeg-skill alternatives?

The closest ffmpeg-skill alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes ffmpeg-skill?

ffmpeg-skill is developed by kajisho5. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine.
- Full alternatives guide: https://ai.dosa.dev/tools/ffmpeg-skill/alternatives
