Sign in

v1

latestOpenAPI 3.1.02026-08-04143345.6 KB
asyncVideoGeneration

Generate video from text

Generate a video from a text prompt. Describe the scene, camera motion, and mood — the model returns a video with matching audio.

Responds immediately with the job id and created_at timestamp. Poll GET /v2/text-to-video/{id} until the status is completed, then download from result.video_url.

Billed per second of generated video. See Pricing.

post/v2/text-to-video

Headers

Authorizationstring required

API key authentication

Request body

promptstring required

Text prompt describing the desired video content

model'ltx-2-fast' | 'ltx-2-pro' | 'ltx-2-3-fast' | 'ltx-2-3-pro' required

Model to use for generation. See Supported Models for details.

Deprecated: ltx-2-fast and ltx-2-pro are deprecated. See the LTX-2 Deprecation Notice.

durationinteger required

Video duration in seconds. See Supported Models for available durations per model.

fpsinteger

Frame rate in frames per second. See Supported Models for available FPS per model and resolution.

resolutionstring required

Output video resolution. See Supported Models for available resolutions per model.

generate_audioboolean

Generate audio for the video. When true, the generated video will include AI-generated audio matching the scene. When false, only silent video is generated.

camera_motion'dolly_in' | 'dolly_out' | 'dolly_left' | 'dolly_right' | 'jib_up' | 'jib_down' | 'static' | 'focus_shift'

Apply camera motion effects to the generated video.

Response

Job submitted successfully

idstring required

Unique job identifier. Use this to poll for status.

created_atstring date-time required

ISO 8601 timestamp of when the job was created.