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.)

Soul AI Lab open-sourced SoulX-Podcast, a voice podcast generation model. It supports multi-speaker, multi-turn dialogues in Mandarin, English, and Chinese dialects, generating over 60 minutes of natural conversation. The model replicates laughter and sighs, performs zero-shot cross-dialect voice cloning, and briefly topped Hugging Face's trending charts.
Tap to vote and see what everyone thinks.
Summary by ByteBrief