Remix.run Logo
▲ InsidiousWombat 4 hours ago

Native apps should probably just run local voice recognition AI

▲Sean-Der 3 hours ago | parent | next [-]

Size is the tough part. These models require 256GB+ of vram, but other then that I think it's possible!

▲14u2c 3 hours ago | parent [-]

Transcription models certainly don't require that ram. Parakeet even runs the CPU while generally outperforming Whisper.

▲cush 3 hours ago | parent | prev [-]

This is for communicating with agents and inference, not just dictation.