Vidu Q3 🧠 Model Freemium
ShengShu's video model with native audio and 16-second multi-shot scenes
- Maker
- ShengShu Technology
- Latest release
- 2026-01
- Weights
- Closed
- Licence
- –
- Apps offering it
- 4
Where you can use Vidu Q3
Apps in this directory that let you generate with Vidu Q3, from their own documentation. You can also call it directly through the maker's API.
Good for
About Vidu Q3
What it is
Vidu is the video model from ShengShu Technology, a Beijing lab linked to Tsinghua University. Vidu Q3 launched in January 2026. It generates up to 16 seconds of 1080p video with dialogue, voiceover, sound effects and music in one pass. In April 2026 ShengShu added Q3 Reference-to-Video, which builds scenes from several reference subjects, props and styles.
Key features
- Up to 16-second multi-shot sequences at 1080p
- Native dialogue, voiceover, SFX and music
- Reference-to-video from subjects, environments, costumes and props
- Six cinematic effect types: particles, fluids, camera moves, transitions, lighting
- Strong at anime and comic-drama styles
Where you can use it
The Vidu app (vidu.com) and the Vidu API platform. Krea lists Vidu Q3 and Q2 among its video models, so you can compare Vidu against Kling or Veo in one workspace.
Pricing and rights
Vidu sells credits through subscriptions in its app, but the pricing page would not load for us, so plan prices, watermark rules and commercial-use terms are not verified here. We also found no published API rate.
Who it is for
Creators of serialised short dramas, anime-style clips and story shorts who want sound and several shots from one prompt.
Verdict
Vidu Q3 is a capable storytelling model with native audio, and ShengShu said it placed high on Artificial Analysis at launch. It is offered in fewer Western apps than Kling or Seedance, and we could not confirm its pricing and rights terms.
Pros
- Native audio in one pass
- 16-second multi-shot scenes
- Rich reference-to-video mode
- Good for anime and comic dramas
Cons
- Pricing and rights terms not verified
- Offered in few third-party apps
- 1080p cap
Similar AI models
All video models →Veo 3.1 🧠 ModelPaid
Google DeepMind's text- and image-to-video model with native sound, up to 4K
Kling 3.0 🧠 ModelFreemium
Kuaishou's video model with native multilingual audio, lip sync and 15-second clips
Seedance 2.5 🧠 ModelPaid
ByteDance's video model: 30-second clips with audio, many references and local edits
MiniMax H3 (Hailuo 3.0) 🧠 ModelFreemium
MiniMax's open-weight video model: native 2K, stereo sound, 15-second clips
Runway Gen-4.5 🧠 ModelFreemium
Runway's own video model, now with native audio and one-minute multi-shot scenes
Wan 3.0 🧠 ModelOpen source
Alibaba's video family: open-weight Wan 2.x and the 30-second Wan 3.0 API