| 164 |
Eye Contact Correction: Redirecting the eyes to look at the camera |
2024-10-16 |
| 77 |
Show HN: Processing 24 hours of video in ten minutes |
2022-01-11 |
| 8 |
Show HN: State of the art audio enhance (open source AudioSR and DeepFilterNet) |
2023-10-19 |
| 4 |
SieveSync: High-quality, zero-shot lipsync built with MuseTalk and LivePortrait |
2024-09-17 |
| 3 |
Running Meta's SAM2 2x faster |
2024-08-27 |
| 3 |
AI active speaker detection on video with a 90% speedup |
2024-02-28 |
| 3 |
The most cost-effective audio transcription API |
2023-12-12 |
| 2 |
State of the art AI dubbing, built for developers |
2024-06-20 |
| 2 |
Improving on open-source for fast, high-quality AI lipsyncing |
2023-11-22 |
| 2 |
Show HN: A Twitter bot that responds with AI generated avatar videos |
2023-02-28 |
| 1 |
Guide to pure-audio and audiovisual speaker recognition techniques |
2024-11-05 |
| 1 |
Finding highlights in long-form video automatically with custom search terms |
2024-04-03 |
| 1 |
AI-generated sound effects for stock videos using CogVLM and AudioLDM |
2024-03-13 |
| 1 |
Building a robust ball tracking system for sports with SAM 2 |
2024-12-19 |