Running
1
Clear: on-device speech enhancement
🌊
Twelve real recordings, raw vs cleaned, on device
None defined yet.
A European AI lab building opinionated on-device models and SDKs.
| Model | What it does | Card | Demo | Status |
|---|---|---|---|---|
| Clear | Audio enhancement, a 10-minute clip in ~7 seconds | card | demo | Available |
| Uhm | SOTA filler-word detection, zero inference cost | card | demo | Available |
| Emo | Multi-language emoji suggestions, as fast as you can type | card | demo | Available |
| Who | Fast, on-device audio visual speaker diarization. | Closed Beta | ||
| Eye | Pick the best images or frames. | Closed Beta | ||
| NSFW | On-device nudity detection before upload | Closed Beta | ||
| Shapes | Anyone can draw, with fast cross-platform shape matching | Closed Beta | ||
| Face | Lightning-fast face matching and search in your app | Closed Beta |
Every model, no per-call cost, free up to 100k MAU.
Drop-in SDKs for iOS, Android, and Web are coming soon.
Email contact@desertant.ai for early access.
Twelve real recordings, raw vs cleaned, on device
Every uh, um, hmm tagged at 20 ms, on device, multilingual
On-device emoji suggestions
Speech enhancement in your browser.