falText to videoComing soon

fal-ai/pixverse/v6/text-to-video

Name: fal-ai/pixverse/v6/text-to-video
Brand: fal

fal-ai/pixverse/v6/text-to-video is a text to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0065 per second. Billed on duration, default 5. The final charge comes from usage.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Text prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
`aspect_ratio`	one of 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9	16:9	The aspect ratio of the generated video
`resolution`	one of 360p, 540p, 720p, 1080p	720p	The resolution of the generated video
`duration`	number (whole) 1 to 15	5	The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds
`negative_prompt`	text		Negative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
`style`	one of anime, 3d_animation, clay, comic, cyberpunk	—	The style of the generated video
`seed`	number (whole)	—	The same seed and the same prompt given to the same version of the model will output the same video every time.
`generate_audio_switch`	true or false	false	Enable audio generation (BGM, SFX, dialogue)
`generate_multi_clip_switch`	true or false	false	Enable multi-clip generation with dynamic camera changes
`thinking_type`	one of enabled, disabled, auto	—	Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/pixverse/v6/text-to-video",
    "input": {
      "prompt": "Epic low-cut camera capture of a girl clad in ultraviolet threads, Peter Max art style depiction, luminous diamond skin glistening under a vast moon'\''s radiance,…"
    }
  }'