PixVerse launches V6 video model
PixVerse has released V6, a video generation model that produces multi-shot clips with native audio from a single prompt and can be called by coding agents through a command-line interface.
Singapore-based PixVerse announced V6, the latest version of its flagship video generation model, on 30 March 2026. It is available to all PixVerse users, with launch discounts for individual and enterprise subscribers.
The biggest functional change is multi-shot generation with native audio. PixVerse says V6 can produce a short multi-shot film, such as a product advertisement, from a single prompt, generating audio and video together. That removes the separate editing and audio production steps such work usually needs.
The company also says the model improves:
- Camera work: tracking shots, perspective shifts and environmental reveals, with fewer artifacts
- Character continuity: facial expressions and body language stay consistent across scene changes
- Physics: collisions and spatial relationships between objects look more realistic
- On-screen text: multilingual text in English, Chinese and other languages, with consistent placement and style
V6 can also be used through PixVerse's CLI, which the company says works with coding agents including Claude Code, Codex, Cursor and OpenClaw. That lets development teams build video generation into automated pipelines.
PixVerse released no benchmarks or independent evaluations, so the claimed improvements can't be verified from the announcement. The company says precise directional control in complex scenes and consistency across large spatial changes still need work.
Founded in 2023, PixVerse says it has more than 100 million users across 175 countries. It launched R1, which it calls a real-time world model, in January 2026, and says it reached unicorn status after closing a Series C round in March 2026. It did not say how much it raised.