Shreyas Karnik
@KarnikShreyas
Voice notes that file themselves 📥
d1-omni-600M sorts what you say into reminders, lists, messages, travel, questions or music in ~160 ms, entirely in your browser on WebGPU.
No transcript, nothing generated, just typed JSON. Your voice never leaves the tab.
Try it 👇
🎙️
d1-omni-600M sorts what you say into reminders, lists, messages, travel, questions or music in ~160 ms, entirely in your browser on WebGPU.
No transcript, nothing generated, just typed JSON. Your voice never leaves the tab.
Try it 👇
🎙️
0:40
Liquid AI@liquidai · Oct 7d1-omni-600M is an experimental 600M-parameter model for text + image or text + audio.
It combines LFM2.5-Encoder-350M with vision and audio encoders, and leads our text benchmark comparison in toxicity detection and paraphrase identification.
Use it for voice-command routing,
It combines LFM2.5-Encoder-350M with vision and audio encoders, and leads our text benchmark comparison in toxicity detection and paraphrase identification.
Use it for voice-command routing,
Open quoted post →
2 96