| |
Desert Ant Labs, a European AI lab, has launched 18 specialized on-device models for audio, vision, and text that run directly on devices without cloud dependency, offering millisecond response times and no token costs. The models are compact enough for five-year-old phones and outperform larger alternatives—for example, their transcription model is 4.7x faster than Whisper and their language identifier achieves 93.3% accuracy at just 2MB. The service is free for up to 100,000 monthly active devices, with SDKs available for Swift, Kotlin, and JavaScript.
Read Full Article →
← More Tech news