Changelog
Latest updates, new features, and improvements to Hypereal AI.
Virtual Try-On
Upload your photo and try on different outfits with AI. Supports multiple video model options for realistic try-on results.
Visual Workflow Builder
Node-based visual workflow builder for creating complex video generation pipelines. Drag and drop to build your AI workflows.
3D Model Generation
Generate 3D assets from text prompts or images with Meshy6 text-to-3D and image-to-3D models.
Improved API Reliability
Automatic provider fallback ensures your API requests stay reliable. Requests automatically route to backup providers if needed.
Multi-Image Video Generation
Create videos with both start and end frame control using the new last_image parameter.
GLM 4.7 & Grok 4.1 Fast
Added GLM 4.7 with thinking mode for complex reasoning, and Grok 4.1 Fast for high-speed inference.
3D Model Generation API
3 new API endpoints for generating 3D assets programmatically from text or images.
Audio Generation API
Text-to-speech, voice cloning, and speech recognition powered by Fish Audio. Create natural-sounding audio with emotional control.
Kling Motion Control
Precise video generation with motion guidance for more control over your AI-generated videos.
Imagine Video Models
New Imagine T2V for text-to-video and Imagine HQ for high-quality video generation with audio support.
MiniMax Speech Voice Options
Multiple voice presets now available for MiniMax Speech 02, offering more variety for text-to-speech generation.
Qwen3 TTS Flash
Fast and natural text-to-speech generation with the new Qwen3 TTS Flash model.
Want to see older updates? Check our blog for detailed announcements.