Mirage, a 22 MB vision model by Cactus A 51M-parameter vision model that describes, detects, reads text, segments and decides in 1 pass, in 22 MB, on a phone or a laptop. Apache 2.0.
Whistle, a 16.9 MB speech model by Cactus An open speech-to-text model in 16.9 MB: 7 languages, word timestamps, keyword biasing, CPU only, first token in 11 ms. Apache 2.0.
Google AI Edge Eloquent Google's free on-device AI dictation app that cleans up speech into polished text, powered by Gemma running locally on Mac and iPhone.