Seedance 3.0

Verified capabilities

• Multimodal video generation

  Creates videos from text, images, video, and audio references, allowing users to guide characters, settings, visual effects, mood, framing, rhythm, and sound.[1]

• Synchronized audio generation

  Generates voices, environmental ambience, and sound effects alongside visuals so the audio matches the scene atmosphere and storytelling intent.[1]

• Longer connected narratives

  Supports up to 30 seconds of video and audio in one generation, with controls for pacing, action, camera direction, connected shots, and scene changes.[1]

• Reference consistency

  Uses shared references to carry character appearance, clothing, props, scene details, voices, color palettes, lighting, and visual style across connected shots.[1]

• Cinematic motion direction

  Lets users guide choreography, character actions, framing, pacing, tracking shots, push-ins, energetic reveals, and other camera movement with reference videos and prompts.[1]

• Video extension and editing

  Can continue an existing video with new action and connected scenes or rework visual and audio content using written instructions and references.[1]

• Batch generation

  Supports generating multiple videos in one batch with the same settings, up to 10 videos according to the official page excerpt.[1]

• Creative output controls

  The creation interface shown in the official page excerpt includes controls for resolution, duration, aspect ratio, prompt, image upload, end frame, and batch generation.[1]