ffmpeg-skill

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

★ 4,454 stars, verified 2026-11-04Category: Voice: TTS / STT / CloningGitHub repository ↗

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

Text-to-speech, speech-to-text, and voice cloning, open source.

Stack & tags

agent-skillsai-agentsaudio-processingcaptionsclaude-codecodexcoding-agentcursor

Similar open-source projects

Whisper

★ 109,795

OpenAI's open-source speech recognition model — the benchmark for multilingual STT

Voice: TTS / STT / CloningGitHub ↗

GPT-SoVITS

★ 62,271

TTS/cloning trainable on 1 minute of audio — a legendary Chinese-community project

Voice: TTS / STT / CloningGitHub ↗