V2A

One of the next significant steps in bringing generated movies to life is creating soundtracks for these silent videos.

Today, we're sharing advancements in our video-to-audio (V2A) technology, which enables synchronized audiovisual generation. V2A uses video pixels and natural language text prompts to produce rich soundscapes that match the on-screen action.

Our V2A technology can be paired with video generation models like Veo to create scenes with dramatic scores, realistic sound effects, or dialogue that aligns with the characters and tone of a video.

It can also produce soundtracks for various traditional footage, including archival material and silent films, expanding creative possibilities.