API docs / Video models

PixVerse V6 (Text to video) API

Write the shot; PixVerse V6 renders 1–15 seconds, with audio if you switch it on.

Model id
fal-ai/pixverse/v6/text-to-video
Provider
PixVerse
Output
Video
Price
From 79 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "fal-ai/pixverse/v6/text-to-video". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "fal-ai/pixverse/v6/text-to-video",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Describe the shot: subject, action, camera, and sound. Up to 2,048 bytes; accented letters and emoji use more than one byte.

Up to 2048 characters

aspect_ratiostring

Frame shape of the generated video.

Default: 16:9

One of: 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9

resolutionstring

Output resolution. Higher tiers cost more per second.

Default: 720p

One of: 360p, 540p, 720p, 1080p

duration_secondsnumber

Length of the generated video in whole seconds, from 1 to 15.

Default: 5

Min 1 · Max 15

generate_audioboolean

Generate background music, sound effects, and dialogue with the video.

Default: false

stylestring

Optional style preset. None keeps the look your prompt describes.

Default: none

One of: none, anime, 3d_animation, clay, comic, cyberpunk

seednumber

Reuse a seed with the same prompt and settings to reproduce a result.

Min 0 · Max 2147483647

negative_promptstring

What to keep out of the video.

Default:

Up to 2048 characters

generate_multi_clip_switchboolean

Let the model cut between several camera angles inside one video.

Default: false

thinking_typestring

Let the model rewrite the prompt before rendering: auto decides per prompt, enabled always rewrites, disabled sends your words as written.

Default: auto

One of: auto, enabled, disabled