ByteDance's Seedance 2.5 generates 30-second video clips with built-in audio
ByteDance just shipped Seedance 2.5, an AI video model that produces video and audio together in one go. Each clip runs up to 30 seconds, three times what Google's Gemini Omni Flash puts out. Users can feed in dozens of images, videos, and audio files as reference. For ad teams, this could kill the process of cutting together one short clip at a time. The article ByteDance's Seedance 2.5 generates 30-second video clips with built-in audio appeared first on The Decoder .
Follow The Decoder to make it a durable For You signal.
ByteDance released Seedance 2.5, an AI video model that generates synchronized video and audio in a single pass. Each clip can run up to 30 seconds (extendable), three times the length of Google’s Gemini Omni Flash output. Users can upload up to 30 images, 10 video clips, and 10 audio files as reference to produce scenes with multiple characters and camera angles, with improved textures, lighting, and skin detail. The model is currently live on Jimeng AI and Doubao Pro, with API access through BytePlus ModelArk coming later. The previous version, Seedance 2.0, leads the image-to-video leaderboard for models with audio and was used by director Neill Blomkamp to create a 13-minute AI-generated short film. For ad and visual content teams, this allows building complete productions in one pipeline instead of stitching individual clips together.