Indexing 669GB of GoPro videos on an M1 Mac with local AI
A personal video search tool was built to find useful moments across 2,207 GoPro clips from a cycling journey. The finished run indexed 628 videos, covering 668.68GB and 15 hours, 13 minutes, 18 seconds of footage. turned speech into text.
DeepFace, RetinaFace, and VGG-Face handled . Qwen2.5-VL described scenes, while easyocr read text shown on screen. The indexed results can be searched, and selected clips can be sent straight into a DaVinci Resolve editing timeline.
The main point is that can now make a large private video library searchable on one powerful personal computer.
Key points
- The project indexed 628 GoPro videos totaling 668.68GB and just over 15 hours of footage.
- was used to turn spoken audio into searchable text.
- DeepFace, RetinaFace, and VGG-Face were used for .
- Qwen2.5-VL described scenes, and easyocr read text visible in the video.
- Useful clips could be sent directly into a DaVinci Resolve timeline.