Elon Musk's xAI launches faster Grok Imagine Video 1.5 with improved audio and physics

xAI has unveiled Grok Imagine Video 1.5 with faster generation and built-in audio. The release underlines the intensifying race to make AI video tools more realistic and creator-friendly.

In Short

• xAI launches Grok Imagine Video 1.5
• New model promises better motion, physics, audio and faster video creation
• xAI adds projects, parallel agents and search to boost creativity

The AI race is getting more intense. While OpenAI and Google have already rolled out increasingly capable text-to-video generation models, Elon Musk-owned xAI is trying to stay in the competition. The company has just unveiled its new Grok Imagine Video 1.5 model, betting that creators want not just better-looking videos, but also faster results and more creative control. According to xAI, Grok Imagine Video 1.5 is its "best image-to-video model yet," offering better motion, better physics, better audio and faster speeds.

The announcement comes at a time when AI companies are competing aggressively to turn a simple prompt or image into realistic videos. But generating convincing videos remains one of the toughest challenges in AI.

Better videos, with sound built in

xAI says the new model improves across every dimension that matters for real creative work. Compared to the previous version, users will get better sound effects, ambience and dialogue, all generated in the same pass and synchronised with the action. The company also says speech is now clearer and better synced with videos.

This is significant because audio is often treated as a separate layer in AI-generated videos. xAI is instead aiming to create visuals and sound together so that the final output feels more natural.

Fixing one of AI video's biggest problems

Physics is another area where AI models have long struggled. Users have often complained about videos where objects bend unnaturally, characters float awkwardly or movements appear unrealistic. According to xAI, Grok Imagine Video 1.5 addresses some of these issues with fewer warps and more believable weight and momentum.

Whether that translates into noticeably better videos will ultimately depend on how users respond, but the company is making physics one of the model's biggest selling points.

Faster video generation

xAI is also focusing on speed. The company says Grok Imagine Video 1.5 Fast nearly doubles generation speed. It can create 6-second videos at 720p resolution in about 25 seconds, down from more than 40 seconds in the previous model.

In the fast-moving AI market, shaving seconds off generation time can make a big difference, especially for creators who generate multiple versions before settling on the final output.

New tools for creators

Alongside Imagine Video 1.5, xAI is rolling out several new features over the next few days to improve users' creative workflow. Users will be able to organise their work into Projects that appear on the left sidebar. The company is also introducing parallel agents, allowing users to run multiple prompts at once instead of waiting for one generation to finish before starting another.

Another addition is search. Users will be able to find any image or video they have created by searching their library instead of scrolling through older creations.

Imagine Video 1.5 is now out of preview and generally available in the xAI API as "grok-imagine-video-1.5". Users can provide a starting image, describe the motion and choose the video's resolution and duration.

xAI has also rolled out Video 1.5 Fast on grok.com/imagine and its iOS and Android apps.

- Ends