Show HN: WTFfmpeg

Summary

wtffmpeg - Natural Language to FFmpeg Translator wtffmpeg is a command-line tool that uses a local Large Language Model (LLM) to translate plain English descriptions of video and audio tasks into executable ffmpeg commands. Stop searching through Stack Overflow and documentation for that one specific ffmpeg flag. Just ask for what you want. Example: > wtff " convert my_video.avi to mp4 with no sound " Loading model... (this may take a moment) Model loaded. Generating command... --- Generated ffmpeg Command --- ffmpeg -i my_video.avi -an -c:v libx264 my_video.mp4 ------------------------------ Execute this command ? [y/N] y Executing: ffmpeg -i my_video.avi -an -c:v libx264 my_video.mp4 ffmpeg version N-100029-g040e989223 Copyright (c) 2000-2020 the FFmpeg developers ... Features Natural Language Interface: Describe complex ffmpeg operations in plain English. Local First: Runs entirely on your local machine. No data is sent to external APIs. Interactive Execution: Reviews the generated command before giving you the option to execute it. GPU Accelerated: Leverages llama-cpp-python to offload model layers to your GPU for faster inference. Customizable: Easily swap out different LLM models or customize the system prompt to improve accuracy for your specific needs. Installation This project uses Python 3.8+ and is packaged with pyproject.toml. Clone the Repository git clone https://github.com/scottvr/wtffmpeg.git cd wtffmpeg Create a Virtual Environment It is highly recommended to install the packages in a virtual environment. python3 -m venv .venv source .venv/bin/activate Install llama-cpp-python with Hardware Acceleration This is the most critical step. For the best performance, you should install llama-cpp-python with the correct build flags for your hardware before installing the project. For NVIDIA GPUs (CUDA): CMAKE_ARGS= " -DLLAMA_CUBLAS=on " pip install llama-cpp-python For Apple Silicon (Metal): CMAKE_ARGS= " -DLLAMA_METAL=on " pip install llama-cpp-python For ...