Top AI Product

MiniMax dropped H3 (Hailuo 3.0) on July 31 and says the weights land within days. That’s the headline: China’s open-source wave, which already flooded text and image models, just reached video generation for the first time. H3 is a text/image/video/audio-to-video model that outputs native 2K clips at 24fps, 5–15 seconds long, with stereo audio — dialogue, sound effects, and ambience baked into the same pass instead of dubbed on later.

What makes it different

Two features do the heavy lifting. Omni-reference lets you feed up to 9 images, 3 video clips, and 3 audio clips in one generation to lock character, style, motion, and voice. Instruction-level editing means you swap a character, change the scene, or fix a sound effect without regenerating the whole clip. MiniMax claims 2K costs under a third of mainstream rivals — pitching it straight at ads, e-commerce, and game studios.

API and access

It’s live now through MiniMax’s official API and fal.ai, with downloadable weights days away under a community license (commercial use free under $20M revenue). Pricing runs around $0.13 per second of 2K. Early third-party benchmarks already put H3 at #1 in video editing.

You Might Also Like

• Minimax m2 5 Just Dropped and Open Source ai Will Never be the Same
• Omni Just Made Enterprise ai Search Stupidly Simple With one Postgres Database
• Minimax m2 7 Scores 56 on swe pro and it Helped Build Itself
• Google Gemini Omni Flash Drops Video Generation to 0 10 a Second