What is SeedAudio?
SeedAudio 1.5 is an upcoming AI audio model that creates full scenes in one pass. It can generate dialogue, music, ambience, and sound effects together, instead of handling each layer separately. The product also supports reference-guided voices, video-aware dubbing, timestamp control, and separate stem tracks for easier mixing. It is designed for things like audio dramas, short videos, game scenes, ads, podcasts, and guides. The site currently lets people try Seed Audio 1.0 while SeedAudio 1.5 is coming soon. Published specs say 1.5 will support up to six minutes of audio, six references, four input modes, and 30 languages with regional variants.
Key features
- Generates dialogue, music, ambience, and sound effects together.
- Supports reference-guided voices for more controlled results.
- Uses video input for dubbing that follows the picture.
- Outputs separate stems for dialogue, ambience, effects, and music.
- Handles up to six minutes and six audio references.
Category
Website
Links
Location
Founder
griffin Peter
