Seedance 2.5

Cinematic multi-shot video generation with native audio and up to 4K output.

Fast multimodal video generation with consistent subjects across shots.

Realistic movement, synchronized audio and native 1080p video output.

Photorealistic generation and precise image editing with strong typography.

Fast image generation with accurate text and stable character consistency.

Full vocal and instrumental tracks with coherent musical progression.

Expressive multilingual dialogue with natural delivery and voice control.

Advanced reasoning and long-context synthesis for demanding workflows.

General-purpose multimodal intelligence for agents and complex analysis.

Production-ready image to image with normalized inputs, predictable task states, and unified billing.

Production-ready text to video with normalized inputs, predictable task states, and unified billing.

Production-ready text to image with normalized inputs, predictable task states, and unified billing.

Production-ready chat with normalized inputs, predictable task states, and unified billing.

Production-ready video to video with normalized inputs, predictable task states, and unified billing.

Production-ready lip sync with normalized inputs, predictable task states, and unified billing.

Production-ready speech to video with normalized inputs, predictable task states, and unified billing.

Production-ready text to speech with normalized inputs, predictable task states, and unified billing.

Production-ready video editing with normalized inputs, predictable task states, and unified billing.

Production-ready image editing with normalized inputs, predictable task states, and unified billing.

Production-ready text to music with normalized inputs, predictable task states, and unified billing.