Best-in-class open source model with integrated audio generation.
Key Features
Includes audio generation.
High-quality video output.
Excellent prompt adherence.
Open source foundation.
Model Deep Dive
An advanced open-source model that excels in creating video with synchronized audio, offering a new level of immersion for generated content.
Video without sound feels empty. Wan 2.5 tackles this by generating audio that matches the video content. If you generate a video of a roaring fire, you'll hear the crackle. If it's a busy street, you'll hear the traffic. This multimodal approach saves you the hassle of finding stock sound effects later, making it a complete package for quick content creation.
Pricing
$0.10 - $0.20
per second
Price varies by resolution.
Technical Details
Max Duration
10s
Resolution
480p, 720p, 1080p
Frame Rate
24 FPS
Audio
Supported
Model Deep Dive
An advanced open-source model that excels in creating video with synchronized audio, offering a new level of immersion for generated content.
Video without sound feels empty. Wan 2.5 tackles this by generating audio that matches the video content. If you generate a video of a roaring fire, you'll hear the crackle. If it's a busy street, you'll hear the traffic. This multimodal approach saves you the hassle of finding stock sound effects later, making it a complete package for quick content creation.
