Why creators choose Grok Video 1.5

Start Creating

Audio comes built in

Every clip is generated with sound. Effects, ambience, and speech are produced with the visuals, so what comes back is finished rather than a silent draft waiting on an audio pass.

Up to seven references

Feed the model as many as seven reference images and call them out directly in your prompt. Lock a character, a product, or a look and keep it consistent from the first frame to the last.

Built for speed

Short-form output tuned for fast turnaround. Generate, look, adjust, and go again — the loop is quick enough to explore several directions before settling on one.

Start from a still

Drop in an image and let it open the clip. Useful when you already have the shot you want and only need the motion, the sound, and a few seconds of life added to it.

How to create with Grok Video 1.5

Start creating with xAI’s Grok Video 1.5 by following a few simple steps directly inside the DaVinci AI Toolkit.

Start Creating

Who Grok Video 1.5 is for

Grok Video 1.5 by xAI suits creators who need short, sound-complete video quickly, without a separate audio or editing pass.

Try Grok Video 1.5
Content creators

Content creators

Turn a prompt or a single photo into a finished short clip with sound. Well suited to social formats where speed and volume matter more than long runtimes.

Agencies and brands

Agencies and brands

Explore campaign directions fast. Feed product or brand references into the model and generate several variations before committing to a full production.

Social and community teams

Social and community teams

React quickly to whatever is happening. Produce timely, expressive video without waiting on a production cycle or booking a shoot.

Try Grok Video 1.5

Enter a text prompt, upload an image, or add references, and generate a short video with sound in seconds.

Start Creating

Powerful features

Grok Video 1.5 brings together reference-driven consistency, native audio, and fast generation to produce short video from text or images.

Start Creating

Text, image, and reference

Generate from a written prompt, animate a single still, or guide the result with up to seven reference images cited directly in the prompt.

Native audio generation

Sound is produced alongside the visuals rather than layered on afterwards, covering effects, ambience, and speech in a single pass.

Reference-driven consistency

Tag your references in the prompt to hold a subject, a style, or a setting steady across the whole clip instead of hoping the model remembers.

Flexible framing

Choose from a wide set of aspect ratios, from widescreen to square to vertical, so the output already fits the platform you are publishing to.

Design with DaVinci

Create with momentum. Bring your vision to life.

Get Started for Free