Chinese tech companies are stepping up their game in the highly competitive AI’s field. One of the most exciting developments recently is the release of MiniMax‘s new tool, Video-01. This advanced text-to-video generator is the latest innovation from one of China’s top AI startups and is set to intensify competition with global leaders, including OpenAI, which recently teased its own video-generation platform, Sora.

MiniMax’s Video-01: A New Milestone in AI Video Generation

MiniMax, which has earned its spot among China’s AI elite alongside other innovators like Zhipu AI, Baichuan, and Moonshot AI, has made Video-01 available to the public. Launched during the company’s inaugural developer conference in Shanghai, this tool allows users to convert text descriptions into short, high-quality videos, up to six seconds long, within just two minutes. This is a significant breakthrough, as it opens up a new frontier for quick and accessible video creation.

According to MiniMax’s CEO, Yan Junjie, Video-01 is only the beginning. Future iterations will introduce more complex capabilities, such as video creation from images and integrated video editing features. The ambition here is clear—MiniMax is laying the groundwork to be a leading player in this space as text-to-video technology becomes more integral to the digital landscape.

How to acces MiniMax

To access MiniMax Video-01, users can log in using their cellular phone number directly on the official platform. Although the website may experience some delays due to bugs, it remains functional. If the webpage appears in Chinese, it’s recommended to use Chrome or any Chromium-based browser for seamless translation, though Safari is also a suitable alternative. One minor issue involves country codes, so it’s advised to manually type the correct one when logging in. Once you’re in, you can start experimenting with text prompts to generate videos, making the most of MiniMax’s innovative features.

Key Features of MiniMax Video-01

One of the key strengths of MiniMax Video-01 is its ability to produce high-resolution videos at 1280 x 720 pixels with a frame rate of 25 FPS, ensuring crisp and professional outputs. The text-to-video generation feature is particularly useful for content creators aiming to quickly transform text ideas into visual content, saving time and effort. Additionally, while the platform offers free access, there are usage limits for unregistered users to maintain optimal performance and prevent overload. The tool also supports a wide range of video styles and perspectives, giving users creative flexibility in their projects.

China’s AI Revolution: Rising to Meet U.S. Competition

The release of Video-01 is more than just a product launch, it signals China’s determination to compete head-to-head with the U.S. in the AI video generation space. Just months earlier, OpenAI revealed its Sora video tool, setting a new benchmark for AI-driven content creation. However, Sora remains unavailable to the public, while MiniMax has moved quickly to ensure Video-01 is accessible, highlighting China’s focus on rapidly developing consumer-ready AI products.

Founded in late 2021, MiniMax is aggressively expanding its Hailuo AI platform, a suite that includes tools for generating text, music, and now, video content. By consistently broadening its offering, MiniMax is becoming a formidable force in the global AI market.

Major Backing Propels MiniMax Forward

MiniMax’s rapid rise has been driven by substantial investment from some of China’s most influential tech giants, including Alibaba, Tencent Holdings, and miHoYo, the studio behind the global sensation Genshin Impact. In March, Alibaba led a funding round that pushed MiniMax’s valuation to over $2 billion, signaling widespread confidence in the startup’s potential.

Meanwhile, Alibaba is developing its own video-generation tool, Tora, which is expected to be built on the OpenSora foundational model. At the same time, Kuaishou Technology, the company behind one of China’s most popular short-video platforms, introduced a subscription model for its own text-to-video tool, Kling, in June. These initiatives signal a future where AI-powered media content will become more accessible and pervasive.