byjlw/video-analyzer
Analyze videos using LLMs, Computer Vision and Automatic Speech Recognition
Extracts keyframes via OpenCV and transcribes audio with Whisper, then feeds frames sequentially to vision LLMs (Llama 3.2 11B or GPT-4o) with contextual awareness of previous frames to build coherent video narratives. Supports both local inference via Ollama and cloud-based APIs (OpenAI, OpenRouter), with configurable prompts and automatic optimization via DSPy for domain-specific use cases.
1,321 stars. No commits in the last 6 months.
Stars
1,321
Forks
183
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/byjlw/video-analyzer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
XnneHangLab/XnneHangLab
不会聊天的字幕提取器不是一个好 B 站下载器~
harry0703/AudioNotes
快速提取音视频内容，整理成一份结构化的markdown笔记
bakaburg1/minutemaker
Generate meeting minutes starting from an audio recording or a transcripts using speech-to-text and LLMs.
yufan-aslp/AliMeeting
The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party...
kromme/Teams-Notetaker
Let AI create the notes of your Teams Meeting