InjazAI

OpenAI says Higgsfield used GPT-6 Astra to extend AI-generated video from roughly one minute to more than 10 minutes, alongside GPT-Image-2.5 for sharper visuals and GPT-Live as a path toward voice-driven filmmaking.

1 min read

OpenAI and Higgsfield: AI Video Goes From 1 Minute to Over 10 With GPT-6 Astra

What was announced?

FAQ

What is GPT-6 Astra in Higgsfield's video workflow?

It is the model Higgsfield used to extend AI video generation from roughly one minute to over 10 minutes, according to OpenAI's post.

How does GPT-Image-2.5 differ from GPT-Live?

GPT-Image-2.5 focuses on visual precision and detail within images and scenes, while GPT-Live points toward voice-driven filmmaking.

Should MENA teams adopt this now?

The longer duration makes it viable for short and mid-length content experiments, but quality checks, rights clearance, and local policy compliance remain necessary before full production reliance.

What changes practically between one minute and over 10 minutes?

Longer duration supports multi-scene narratives, short episodes, and coherent ads, reducing the need to stitch separate clips manually.

Source: OpenAI

AI-assisted summary of the source above. High-confidence stories publish automatically; others wait for review. Facts that are not in the source are not added.