xAI Expands Grok Think about Video 1.5 with Textual content, Picture, and Voice Inputs

xAI has introduced a serious improve to its Grok Think about Video 1.5 mannequin, introducing help for textual content, picture, and voice references, alongside native 1080p video era. These options goal to strengthen xAI’s place within the more and more aggressive AI video market, the place the mannequin already leads with superior movement coherence, audio synchronization, and speedy era speeds.

The newly added multi-modal capabilities permit customers to create movies by combining parts akin to a textual immediate, a picture, and a voice pattern. For example, customers can move in a personality’s picture and voice, guaranteeing the identical face and voice persist throughout scenes. Multi-reference help permits as much as seven locked parts—akin to faces, places, or objects—providing granular artistic management. These updates are reside on grok.com/think about, xAI’s iOS and Android apps, and the xAI API.

Textual content-to-Video and Native 1080p

One of many standout options of this improve is text-to-video era, which permits customers to explain a scene and generate video immediately from the immediate while not having an preliminary picture. Mixed with native 1080p decision, this function positions Grok Think about Video 1.5 as a device for filmmakers, entrepreneurs, and builders searching for higher-quality outputs. Each options at the moment are usually accessible throughout platforms.

Aggressive Market Place

Grok Think about Video 1.5 has been a major step ahead for xAI since its Could 31, 2026 launch. The mannequin achieved the highest spot on the Picture-to-Video Enviornment leaderboard upon launch, surpassing Google Veo and different opponents with an Elo rating of 1473. Its means to generate synchronized audio, improved movement realism, and quicker manufacturing speeds has already made it a favourite amongst artistic professionals.

These developments come amidst intensifying competitors in AI video era, with Google, OpenAI, and others vying for market share. Nonetheless, xAI has strategically priced its API entry decrease than comparable choices, making it a horny choice for builders needing scalable instruments.

Voice Consistency and API Availability

The brand new voice reference function ensures characters retain constant voices throughout scenes, including one other layer of realism. Whereas this function is presently accessible on request for API customers, text-to-video and picture references are already built-in into the xAI API. These updates make Grok Think about Video 1.5 a compelling production-ready resolution, notably for industries requiring detailed content material customization.

With these enhancements, xAI continues to push the boundaries of AI-generated video, aiming to seize a bigger share of a quickly rising market. Early entry to superior options like multi-reference and voice consistency may appeal to each enterprise shoppers and particular person creators searching for high-quality, versatile options.

For these , the upgraded mannequin is now reside throughout xAI’s internet and cell platforms, with a broader rollout anticipated within the coming days.

Picture supply: Shutterstock