fal.ai·Video generation

Seedance 1.0 Pro

/fal-ai/bytedance/seedance/v1/pro/text-to-videoasync$3.75 / million video tokens

Seedance 1.0 Pro, a high quality video generation model developed by Bytedance. Returns hosted file URLs (download promptly; fal keeps them for a limited time). Billed per million video tokens.

Charged per million video tokens produced; a call that produces nothing is charged one unit.

Input

enable_safety_checkerboolean
If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked. (default true)
promptstringrequired
The text prompt used to generate the video
aspect_ratiostring
The aspect ratio of the generated video (default "16:9")
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
camera_fixedboolean
Whether to fix the camera position (default false)
resolutionstring
Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality (default "1080p")
480p, 720p, 1080p
num_framesany
The number of frames to generate. If provided, will override duration.
seedany
Random seed to control video generation. Use -1 for random.
durationstring
Duration of the video in seconds (default "5")
2, 3, 4, 5, 6, 7, 8, 9, …

Field	Type	Required	Description
enable_safety_checker	boolean	—	If set to true, the safety checker will be enabled. Disabling it requires account authorization; unauthorized requests are always checked. (default true)
prompt	string	yes	The text prompt used to generate the video
aspect_ratio	string (21:9, 16:9, 4:3, 1:1, 3:4, 9:16)	—	The aspect ratio of the generated video (default "16:9")
camera_fixed	boolean	—	Whether to fix the camera position (default false)
resolution	string (480p, 720p, 1080p)	—	Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality (default "1080p")
num_frames	any	—	The number of frames to generate. If provided, will override duration.
seed	any	—	Random seed to control video generation. Use -1 for random.
duration	string (2, 3, 4, 5, 6, 7, 8, 9, …)	—	Duration of the video in seconds (default "5")

Run it

curl -s https://sooma.dev/v1/run \ -H "Authorization: Bearer $SOOMA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"provider":"fal","endpoint":"/fal-ai/bytedance/seedance/v1/pro/text-to-video","input":{"prompt":"A cinematic photo of a lighthouse at dawn, soft light"}}'

Or ask your agent: it will call inspect for this schema and run it over MCP.