Guozhen AIGlobal AI field notes and model intelligence

Realtime AI News

Suno adds video generation to AI songs, powered by a Chinese open-source model

Suno has begun generating video for AI-created songs, extending its product from audio into visuals. Sohu reports the capability runs on a Chinese open-source model, though the specific model and rollout scope were not disclosed.

Published
Suno 为 AI 歌曲加上视频生成,背后使用中国开源模型
Image source: suno.com

Suno has started generating video for AI-created songs, extending the product from audio into visuals. Instead of a track alone, the output now includes matching imagery.

According to Sohu, the video feature runs on a Chinese open-source model. The report does not name the model and does not say whether Suno hosts the inference itself or calls an outside service.

For Suno, the shift turns a song into something publishable. Short-video feeds are where AI music is most often consumed, and adding visuals changes how far a track travels.

Building the video stage on open-weight models also says something about maturity: video generation is now a component a product team can integrate, not only a demo.

It changes the cost profile as well. Video generation is far heavier than audio, and self-hosting open weights keeps marginal cost predictable at the price of extra engineering and operations work.

Still unclear are access scope, output length, resolution, and commercial licensing terms. The things to watch next are whether Suno names the underlying model and how it prices the video tier.

Why it matters

Turning AI tracks into short videos moves the product into the distribution channel where AI music is actually consumed. Whether Suno discloses the underlying model and prices the video tier will determine how widely the feature reaches users.

SunoAI MusicVideo Generation
Back to realtime news

Nearby Updates

All