ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
Moonshine AI runs a voice control toolkit entirely locally on a Raspberry Pi Pico 2 W. The system uses voice activity detection, SpellingCNN speech-to-text with up to 50 tokens, and neural text-to-speech. It consumes 3.6 MiB of 4 MiB FLASH and 468 KiB SRAM, leaving minimal space for extra software.
Tap to vote and see what everyone thinks.
Summary by ByteBrief