Tencent open-sources AuK audio model: great voice cloning, but its Chinese sounds foreign
dotey · x · 2026-09-13
- Tencent has open-sourced AuK, pitched as "nano banana for audio": a unified foundation model for speech generation and editing, now on HF Daily Papers with a public demo.
- A blogger tested it for video translation dubbing: voice cloning quality is solid, but the generated Chinese carries an obvious foreign accent — demonstrated with "Bill Gates speaking Chinese."
- The tester suspects wrong parameters and is asking the Hunyuan team for tips.
Related event: Tencent open-sources AuK audio editing model(2 posts)→
More from Fun
- 'My smart switch': finger flips it, Siri does nothing — michalmalewicz · 2026-10-31
- MIT CSAIL shares the 1977 ARPANET logical map, a rare snapshot of the Internet's precursor — MIT_CSAIL · 2026-10-31
- AI-generated Haribo Starmix bean bag product shot looks like a real catalog page — Delahuntagram · 2026-10-30
- AI virtual influencers return with Halloween episode of Ghost Chasers — AIandDesign · 2026-10-30
- Simulon turns a single image into a 3D neural asset that rides an RC car and reacts to the real world — Scobleizer · 2026-10-30
- Screenshot Shows ChatGPT 'Sent from Another Chat' User Steering Messages — Dimillian · 2026-10-30