Hackernews posts about Qwen3-Omni

1. 01
   

   newQwen3-Omni: Native Omni AI model for text, image and videogithub.com

   ▲ 571meetpateltech410d💬 142savesaved
2. 02
   

   newQwen3-Omni-Flash-2025-12-01：a next-generation native multimodal large modelqwen.ai

   ▲ 316pretext331d💬 106savesaved
3. 03
   

   newQwen3-Omni – the first natively AI unifying text, image, audio and videotwitter.com

   ▲ 13amrrs410d💬 1savesaved
4. 04
   

   newSpeech to Speech Qwen3-Omni visualization toolqwen3-omni-mechanics-gui-website.vercel.app

   ▲ 9AndreSlavescu326d💬 1savesaved
5. 05
   

   newShow HN: Live Qwen3-Omni API (open-source speech-to-speech)models.hathora.dev

   ▲ 5dsiddharth339ddiscusssavesaved
6. 06
   

   newQwen3-Omni: first multimodal model with SoTA text, image, audio, and video perfarxiv.org

   ▲ 2walterbell406ddiscusssavesaved
7. 07
   

   newQwen3-Omnihuggingface.co

   ▲ 1speedyboi410ddiscusssavesaved
8. 08
   

   newAsk HN: What's the current best local/open speech-to-speech setup?

   ▲ 265dsrtslnd23287d💬 71savesaved
9. 09
   

   newShow HN: Ramener – An AI-powered PDF renamer for macOS with Finder integrationgithub.com

   ▲ 3jollychang386d💬 1savesaved

· edit