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.)

A Raspberry Pi 5 running llama.cpp, Speaches, and Open WebUI powers a fully local voice assistant. The setup uses Qwen3.5-2B for LLM inference, faster-distil-whisper-small.en for speech-to-text, and Kokoro-82M-v1.0-ONNX for text-to-speech. Response times range from 35 to 70 seconds per prompt.
Tap to vote and see what everyone thinks.
Summary by ByteBrief