Lightricks videoGeneration API
The videoGeneration API from Lightricks — 5 operation(s) for videogeneration.
OpenAPI Specification
openapi: 3.1.0
info:
title: API Reference asyncVideoGeneration videoGeneration API
version: 1.0.0
servers:
- url: https://api.ltx.video
description: Production server
tags:
- name: videoGeneration
paths:
/v1/text-to-video:
post:
operationId: text-to-video
summary: Generate video from text
description: 'Generate a video from a text prompt. Describe the scene, camera motion, and mood — the model returns a video with matching audio.
Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see [v2/text-to-video](/api-documentation/api-reference/async-video-generation/submit-text-to-video).
Billed per second of generated video. See [Pricing](/pricing).
'
tags:
- videoGeneration
parameters:
- name: Authorization
in: header
description: API key authentication
required: true
schema:
type: string
responses:
'200':
description: Video generated successfully
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: The request is invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Authentication failed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: Content rejected by safety filters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'500':
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'504':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/TextToVideoRequest'
/v1/image-to-video:
post:
operationId: image-to-video
summary: Generate video from image
description: 'Animate a still image with realistic motion, depth, and audio. Provide a reference image plus a prompt describing the desired motion. The output preserves the visual identity of the source image.
Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see [v2/image-to-video](/api-documentation/api-reference/async-video-generation/submit-image-to-video).
Billed per second of generated video. See [Pricing](/pricing).
'
tags:
- videoGeneration
parameters:
- name: Authorization
in: header
description: API key authentication
required: true
schema:
type: string
responses:
'200':
description: Video generated successfully
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: The request is invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Authentication failed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: Content rejected by safety filters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'500':
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'504':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ImageToVideoRequest'
/v1/audio-to-video:
post:
operationId: audio-to-video
summary: Generate video from audio
description: 'Generate a video driven by an audio track. Supply dialogue, music, or ambient sound and the model produces visuals synchronized to the audio. Optionally condition on a reference image for visual direction. Output video is 25 fps.
Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see [v2/audio-to-video](/api-documentation/api-reference/async-video-generation/submit-audio-to-video).
Billed per second of input audio. See [Pricing](/pricing).
'
tags:
- videoGeneration
parameters:
- name: Authorization
in: header
description: API key authentication
required: true
schema:
type: string
responses:
'200':
description: Video generated successfully
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: The request is invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Authentication failed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: Content rejected by safety filters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'500':
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'504':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AudioToVideoRequest'
/v1/retake:
post:
operationId: retake
summary: Retake video section
description: 'Re-generate a section of an existing video by replacing either its audio, its video, or both. Iterate on part of a generation without starting over — the rest of the video is preserved. The edited section is defined by the `start_time` and `duration` parameters.
Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see [v2/retake](/api-documentation/api-reference/async-video-generation/submit-retake).
Billed per second of the input video. See [Pricing](/pricing).
'
tags:
- videoGeneration
parameters:
- name: Authorization
in: header
description: API key authentication
required: true
schema:
type: string
responses:
'200':
description: Video edited successfully
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: The request is invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Authentication failed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: Content rejected by safety filters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'500':
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'504':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/EditVideoRequest'
/v1/extend:
post:
operationId: extend
summary: Extend video duration
description: 'Extend a video by generating additional frames at the beginning or end. The model uses context frames from the input to produce a seamless continuation with consistent motion and audio.
> Audio is generated for the extended portion if the input video has audio.
Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see [v2/extend](/api-documentation/api-reference/async-video-generation/submit-extend).
Billed per second, based on the extended portion plus the context frames used from the input video. See [Pricing](/pricing).
'
tags:
- videoGeneration
parameters:
- name: Authorization
in: header
description: API key authentication
required: true
schema:
type: string
responses:
'200':
description: Video extended successfully
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: The request is invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Authentication failed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'422':
description: Content rejected by safety filters
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'500':
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'503':
description: Service temporarily unavailable
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'504':
description: Request timeout
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ExtendVideoRequest'
components:
schemas:
Error:
type: object
properties:
type:
$ref: '#/components/schemas/ErrorType'
description: Response type indicator
error:
$ref: '#/components/schemas/ErrorError'
required:
- type
- error
title: Error
AudioToVideoRequest:
type: object
properties:
audio_uri:
type: string
description: 'Audio file to be used as the soundtrack for the video. Duration must be between 2 and 20 seconds.
See [Input Formats](/input-formats#audio-input) for supported formats and size limits.
'
image_uri:
type: string
description: Input image to be used as the first frame of the video. Required if prompt is not provided. See [Input Formats](/input-formats#image-input) for supported formats and size limits.
prompt:
type: string
description: Text description of how the video should be generated. Required if image_uri is not provided. Can be empty string when image_uri is provided. If image_uri is provided, this describes how the image should be animated. If no image_uri is provided, this describes the video content.
resolution:
$ref: '#/components/schemas/AudioToVideoRequestResolution'
description: 'The resolution of the generated video in WIDTHxHEIGHT format. When omitted, the resolution is automatically determined based on the input image orientation — portrait images produce 1080x1920 video, landscape images produce 1920x1080 video. If no image is provided, defaults to 1920x1080.
'
guidance_scale:
type: number
format: double
description: Optional guidance scale (also known as CFG) for video generation. Higher values make the output more closely follow the prompt but may reduce quality. Defaults to 5 for text-to-video, or 9 when providing an image.
model:
$ref: '#/components/schemas/AudioToVideoRequestModel'
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
required:
- audio_uri
title: AudioToVideoRequest
TextToVideoRequestModel:
type: string
enum:
- ltx-2-fast
- ltx-2-pro
- ltx-2-3-fast
- ltx-2-3-pro
description: 'Model to use for generation. See [Supported Models](/models) for details.
> **Deprecated:** `ltx-2-fast` and `ltx-2-pro` are deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
title: TextToVideoRequestModel
AudioToVideoRequestResolution:
type: string
enum:
- 1920x1080
- 1080x1920
description: 'The resolution of the generated video in WIDTHxHEIGHT format. When omitted, the resolution is automatically determined based on the input image orientation — portrait images produce 1080x1920 video, landscape images produce 1920x1080 video. If no image is provided, defaults to 1920x1080.
'
title: AudioToVideoRequestResolution
TextToVideoRequest:
type: object
properties:
prompt:
type: string
description: Text prompt describing the desired video content
model:
$ref: '#/components/schemas/TextToVideoRequestModel'
description: 'Model to use for generation. See [Supported Models](/models) for details.
> **Deprecated:** `ltx-2-fast` and `ltx-2-pro` are deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
duration:
type: integer
description: Video duration in seconds. See [Supported Models](/models) for available durations per model.
fps:
type: integer
default: 24
description: Frame rate in frames per second. See [Supported Models](/models) for available FPS per model and resolution.
resolution:
type: string
description: Output video resolution. See [Supported Models](/models) for available resolutions per model.
generate_audio:
type: boolean
default: true
description: 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:
$ref: '#/components/schemas/TextToVideoRequestCameraMotion'
description: Apply camera motion effects to the generated video.
required:
- prompt
- model
- duration
- resolution
title: TextToVideoRequest
ErrorError:
type: object
properties:
type:
type: string
description: Error type for programmatic handling
message:
type: string
description: Human-readable error description
required:
- type
- message
title: ErrorError
EditVideoRequest:
type: object
properties:
video_uri:
type: string
description: 'Input video for editing. See [Input Formats](/input-formats#video-input) for supported formats and codecs.
- Maximum resolution: 3840x2160 (4K)
- Minimum frame count: 73 (around 3 seconds at 24fps)
'
prompt:
type: string
description: 'Describing what needs to happen in the generated video in a section
defined by `start_time` and `duration`.
'
start_time:
type: number
format: double
description: 'Start time in seconds, defines the section to be edited in the input video.
The section defined by `start_time` and `duration` should be within the duration of the input video.
If the section extends beyond the duration of the video, it will be clamped to the video duration.
'
duration:
type: number
format: double
description: 'Duration in seconds, defines the duration of the section to be edited
in the input video. Must be at least 2 seconds.
The section defined by `start_time` and `duration` should be within the duration of the input video.
If the section extends beyond the duration of the video, it will be clamped to the video duration.
'
mode:
$ref: '#/components/schemas/EditVideoRequestMode'
description: 'Can be any of the following:
- `replace_audio` - Replace only the audio track
- `replace_video` - Replace only the video track
- `replace_audio_and_video` - Replace both audio and video tracks
The default value is `replace_audio_and_video` if not specified.
'
resolution:
$ref: '#/components/schemas/EditVideoRequestResolution'
description: 'The resolution of the generated video in WIDTHxHEIGHT format. When omitted, the resolution is automatically determined based on the input video orientation — portrait videos produce 1080x1920 output, landscape videos produce 1920x1080 output.
'
model:
$ref: '#/components/schemas/EditVideoRequestModel'
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
required:
- video_uri
- start_time
- duration
title: EditVideoRequest
ImageToVideoRequest:
type: object
properties:
image_uri:
type: string
description: Image to be used as the first frame of the video. See [Input Formats](/input-formats#image-input) for supported formats and size limits.
prompt:
type: string
description: Text description of how the image should be animated, can relate to the details in the image
model:
$ref: '#/components/schemas/ImageToVideoRequestModel'
description: 'Model to use for generation. See [Supported Models](/models) for details.
> **Deprecated:** `ltx-2-fast` and `ltx-2-pro` are deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
duration:
type: integer
description: Video duration in seconds. See [Supported Models](/models) for available durations per model.
fps:
type: integer
default: 24
description: Frame rate in frames per second. See [Supported Models](/models) for available FPS per model and resolution.
resolution:
type: string
description: Output video resolution. See [Supported Models](/models) for available resolutions per model.
generate_audio:
type: boolean
default: true
description: 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.
last_frame_uri:
type: string
description: 'Image to be used as the last frame of the video. When provided, the video will interpolate between the first frame (image_uri) and this last frame. See [Input Formats](/input-formats#image-input) for supported formats and size limits.
> Note: Only supported by `ltx-2-3` models (`ltx-2-3-fast`, `ltx-2-3-pro`).
'
camera_motion:
$ref: '#/components/schemas/ImageToVideoRequestCameraMotion'
description: Apply camera motion effects to the generated video.
required:
- image_uri
- prompt
- model
- duration
- resolution
title: ImageToVideoRequest
ExtendVideoRequestModel:
type: string
enum:
- ltx-2-pro
- ltx-2-3-pro
default: ltx-2-3-pro
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
title: ExtendVideoRequestModel
EditVideoRequestResolution:
type: string
enum:
- 1920x1080
- 1080x1920
description: 'The resolution of the generated video in WIDTHxHEIGHT format. When omitted, the resolution is automatically determined based on the input video orientation — portrait videos produce 1080x1920 output, landscape videos produce 1920x1080 output.
'
title: EditVideoRequestResolution
ExtendVideoRequest:
type: object
properties:
video_uri:
type: string
description: 'Input video for extending. See [Input Formats](/input-formats#video-input) for supported formats and codecs.
- Supported aspect ratios: 16:9 and 9:16
- Maximum resolution: 3840x2160 (4K)
- Minimum frame count: 73 (around 3 seconds at 24fps)
The output video preserves the input video''s resolution.
'
prompt:
type: string
description: 'Description of what should happen in the extended portion of the video.
'
duration:
type: number
format: double
description: 'Duration in seconds to extend the video. Minimum 2 seconds, maximum 20 seconds (480 frames at 24fps).
'
mode:
$ref: '#/components/schemas/ExtendVideoRequestMode'
description: 'Where to extend the video:
- `end` (default): Extends the video at the end.
- `start`: Extends the video at the beginning.
'
model:
$ref: '#/components/schemas/ExtendVideoRequestModel'
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
context:
type: number
format: double
description: '**Advanced parameter:** Number of seconds from the input video to use as context for the extension (maximum 20 seconds).
The model uses context frames from the input video to generate a more coherent extension.
The sum of `context` + `duration` (converted to frames using the input video''s FPS) cannot exceed 505 frames (~21 seconds at 24fps). For higher-FPS inputs, the maximum total duration in seconds will be proportionally lower; for lower-FPS inputs, it will be proportionally higher.
If not provided, defaults to maximize available context within the 505 frame limit while respecting the 20-second cap.
'
required:
- video_uri
- duration
title: ExtendVideoRequest
ImageToVideoRequestModel:
type: string
enum:
- ltx-2-fast
- ltx-2-pro
- ltx-2-3-fast
- ltx-2-3-pro
description: 'Model to use for generation. See [Supported Models](/models) for details.
> **Deprecated:** `ltx-2-fast` and `ltx-2-pro` are deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
title: ImageToVideoRequestModel
TextToVideoRequestCameraMotion:
type: string
enum:
- dolly_in
- dolly_out
- dolly_left
- dolly_right
- jib_up
- jib_down
- static
- focus_shift
description: Apply camera motion effects to the generated video.
title: TextToVideoRequestCameraMotion
ErrorType:
type: string
enum:
- error
description: Response type indicator
title: ErrorType
AudioToVideoRequestModel:
type: string
enum:
- ltx-2-pro
- ltx-2-3-pro
default: ltx-2-3-pro
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
title: AudioToVideoRequestModel
ImageToVideoRequestCameraMotion:
type: string
enum:
- dolly_in
- dolly_out
- dolly_left
- dolly_right
- jib_up
- jib_down
- static
- focus_shift
description: Apply camera motion effects to the generated video.
title: ImageToVideoRequestCameraMotion
ExtendVideoRequestMode:
type: string
enum:
- start
- end
default: end
description: 'Where to extend the video:
- `end` (default): Extends the video at the end.
- `start`: Extends the video at the beginning.
'
title: ExtendVideoRequestMode
EditVideoRequestModel:
type: string
enum:
- ltx-2-pro
- ltx-2-3-pro
default: ltx-2-3-pro
description: 'Model to use for video generation.
> **Deprecated:** `ltx-2-pro` is deprecated. See the [LTX-2 Deprecation Notice](/ltx-2-deprecation).
'
title: EditVideoRequestModel
EditVideoRequestMode:
type: string
enum:
- replace_audio
- replace_video
- replace_audio_and_video
default: replace_audio_and_video
description: 'Can be any of the following:
- `replace_audio` - Replace only the audio track
- `replace_video` - Replace only the video track
- `replace_audio_and_video` - Replace both audio and video tracks
The default value is `replace_audio_and_video` if not specified.
'
title: EditVideoRequestMode
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: API key authentication