inthepond/ff-toolkit

README excerpt

ff-toolkit FFmpeg operations as LLM-callable tools. Stop hand-writing FFmpeg subprocess calls and JSON tool schemas. ff-toolkit gives you 5 production-ready media operations, dual-format LLM schemas (OpenAI + Anthropic), and an MCP server — all in one pip install . Real-World Use Cases "My agent pipeline needs to process uploaded videos" — Give your agent openai tools() or anthropic tools() and let it decide how to clip, transcode, or extract audio. The dispatch() function handles execution. "I need to batch-extract 16kHz WAV for ASR" — One line: extract audio("video.mp4", "out.wav", codec="pcm s16le", sample rate=16000, channels=1) "I want FFmpeg tools in Claude Desktop / Cursor" — Add the MCP server config (3 lines of JSON) and Claude can edit your videos directly. "I want FFmpeg tools in DeepSeek Harness" — dsh plugin add dsh-ffkit installs the native plugin from integrations/deepseek-harness. "I'm tired of writing the same FFmpeg commands" — Use the CLI: ffkit clip input.mp4 output.mp4 --start 00:01:00 --duration 30 60-Second Quick Start Python API CLI With OpenAI (3 lines to integrate) With Anthropic (3 lines to integrate) As an MCP Server (Claude Desktop / Cursor) Add to your…

Category