lightricks/ltx-2.5-audio-to-video
LTX-2.5 Pro generates video timed to a supplied audio track, optionally starting from an image.
Model Inputs
Audio that sets the timing (.mp3/.wav/.flac/.m4a/.ogg). 2-20 seconds; the Pro tier caps it at 10
Drag & drop a file here, or click to select
Supported formats: MP3, WAV, FLAC, M4A, OGG (max 10MB)
Optional first frame (.jpg/.png/.webp). Without it, prompt is required
Drag & drop a file here, or click to select
Supported formats: JPG, PNG, WEBP (max 10MB)
Text description of how the video should be generated. Required if image_url is not provided. When image_url is provided, this describes how the image should be animated.
Guidance scale for video generation. Higher values make the output more closely follow the prompt. Defaults to 5 for text-to-video, or 9 when providing an image.
The aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input image, or defaults to 16:9 if no image is provided.
Result
Pricing
lightricks/
ltx-2.5-audio-to-video
You are billed for what this model actually produces — by the second — so a shorter request costs less and you never pay for idle time.
For example, a request of 60 seconds costs about $10.20.
You are charged for what the request actually produces, so the final amount scales with the seconds you use.
| Provider | Price ($) | Saving (%) |
|---|---|---|
| Synexa | $0.17 | - |
| fal | $1.02 | 83.3% |
Comparison prices are for an equivalent request.
Readme
This endpoint drives LTX-2.5 Pro from audio: the supplied track sets the timing and the model generates picture to match, keeping the original audio in the output.
Audio must be 2-20 seconds long, and the Pro tier caps it at 10 seconds. Supply image_url to fix the first frame, in which case the prompt describes how that image is animated; without an image, the prompt is required and describes the whole scene.
guidance_scale defaults to 5 for text-driven generation and 9 when an image is supplied.