Video Generation With Audio

Seedance 2.0

Generate high-quality videos from text prompts, images, or multimodal inputs. Supports text-to-video, image-to-video, and advanced multimodal generation with reference images, videos, and audio.

Typical generation time: 30-60 seconds

Model

Text describing the video. Use Shot 1:, Shot 2: for multi-shot sequences.

First Frame Image

  • Uploaded image

Starting frame image URL for image-to-video. Cannot be used with referenceImages.

Last Frame Image

  • Uploaded image

Ending frame image URL. Requires firstFrameUrl. Guides transitions between frames.

Reference Images

Maximum file size: 10 MB

Up to 9 reference images for character/style consistency. Cite as "image 1", "image 2" in prompt. Cannot be used with firstFrameUrl.

Reference Videos

Maximum file size: 100 MB

Up to 3 reference videos for motion transfer. Cite as "video 1" in prompt.

Reference Audio

Maximum file size: 50 MB

Up to 3 reference audio files. Cite as "audio 1" in prompt.

Video length in seconds. Use 5s for quick clips, 15s for cinematic narratives.

Output resolution. Use 480p for drafts, 720p for final renders.

Optional. Leave empty for no audio. The text is converted to speech (ElevenLabs) and added over the video.

Language of the generated voiceover.

Choose a voice or use the default voice for the selected language. You can preview voices before selecting.

Output aspect ratio. Use 16:9 for landscape, 9:16 for vertical social video.

Co-generate synchronized audio (dialogue, SFX, ambient, music) in the same pass. Default: false per Segmind API.

Reproducibility seed. Use -1 for random output, set a fixed value to iterate on the same scene.

Returns the final video frame as an image URL. Use to chain clip sequences.

Explore example prompts and their results.

  • Text-to-VideoVideo
  • Image-to-VideoVideo
  • Multimodal with Reference ImagesVideo

Similar Models

Community