Model
Seedance 2.0 Fast Speed-optimized Seedance 2.0 variant for fast, cinematic video generation via Segmind. Supports text-to-video (multi-shot), image-to-video (first frame or first+last frame), and multimodal reference-based generation with optional co-generated audio. Prompt Text describing the video. Required unless you provide a first frame image or reference images.
First Frame Image
Starting frame image URL for image-to-video. Cannot be used with referenceImages.
Last Frame Image
Ending frame image URL. Requires firstFrameUrl. Guides the transition between two frames.
Reference Images
Up to 9 reference images for character/style consistency (cite as image 1, image 2). Cannot be used with firstFrameUrl.
Reference Videos
Up to 3 reference videos (2-15s each) for motion/style transfer (cite as video 1). Billed at the video-to-video rate.
Reference Audios
Up to 3 reference audio files (MP3, cite as audio 1). Requires at least one image/video input.
Duration Video length in seconds (4-15), or Auto.
Resolution Output resolution. Fast supports up to 720p.
Audio Text Optional. Leave empty for no audio. The text is converted to speech (ElevenLabs) and added over the video.
Language Language of the generated voiceover.
Voice Choose a voice or use the default voice for the selected language. You can preview voices before selecting.
Advanced Options Aspect Ratio Output aspect ratio. Use 16:9 for landscape, 9:16 for vertical social video.
Bitrate Mode Output encoding bitrate. "High" gives better visual fidelity and fewer compression artifacts (larger files). Does not affect price.