MiniMax H3 Video Model Launches with Native Stereo Audio and Multimodal References
smtabatabaie · x · 2026-07-31
Hailuo AI (MiniMax) has released its next-generation multimodal video model, H3, now available Day 0 on the Scenario platform.
The model features robust multimodal inputs and native stereo audio generation. Users can leverage text, images (including first and last frames), and up to 9 images, 3 videos, and 3 audio clips as references, maintaining high consistency throughout. It also supports 2K resolution, 7000-character prompts, and 15-second videos at 24 FPS.
Related event: MiniMax Launches Omni-Modal Model H3 with Native 2K Stereo Video(17 posts)→
More from Models
- Hands-on with GPT-5.6 Luna: Matches Sol in Knowledge Work at a Fraction of the Cost — BenBajarin · 2026-08-01
- GPT-5.6 Series Benchmarks Leak: Sol Hits Top 10, Luna Wins on Cost-Efficiency — arena · 2026-08-01
- Claude 3 Opus Usage Tip: Low Thinking Effort Yields Better Manageability — brandon_galang · 2026-08-01
- Comparison Chart Reveals: DeepSeek Performance Surpasses Llama — teortaxesTex · 2026-08-01
- DeepSeek V4 Flash undercuts GPT-5.6 Luna: 2.3x cheaper with similar intelligence — zainhas · 2026-08-01
- DeepSeek V4 Flash's low price sparks debate: OpenAI margins called excessive — teortaxesTex · 2026-08-01