GET

/v1/schemas/fal/video/fal-ai%2Fltx-2-19b%2Faudio-to-video

kind inputactivity videohash 5c6d67e7extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

26 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
audio_url*stringThe URL of the audio to generate the video from.
prompt*stringThe prompt to generate the video from.
num_inference_stepsintegerThe number of inference steps to use.8 ≤ n ≤ 50 · default: 40
preprocess_audiobooleanWhether to preprocess the audio before using it as conditioning.default: true
enable_prompt_expansionbooleanWhether to enable prompt expansion.default: true
enable_safety_checkerbooleanWhether to enable the safety checker.default: true
end_image_strengthnumberThe strength of the end image to use for the video generation.0 ≤ n ≤ 1 · default: 1
camera_lora_scalenumberThe scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.0 ≤ n ≤ 1 · default: 1
video_sizeImageSize | enumThe size of the generated video. Use 'auto' to match the input image dimensions if provided.default: "landscape_4_3"
guidance_scalenumberThe guidance scale to use.1 ≤ n ≤ 10 · default: 3
video_output_typeenumThe output type of the generated video.X264 (.mp4) | VP9 (.webm) | PRORES4444 (.mov) | GIF (.gif) · default: "X264 (.mp4)"
video_qualityenumThe quality of the generated video.low | medium | high | maximum · default: "high"
accelerationenumThe acceleration level to use.none | regular | high | full · default: "regular"
seedintegerThe seed for the random number generator.nullable
end_image_urlstringThe URL of the image to use as the end of the video.nullable
fpsnumberThe frames per second of the generated video.1 ≤ n ≤ 60 · default: 25
image_urlstringOptional URL of an image to use as the first frame of the video.nullable
negative_promptstringThe negative prompt to generate the video from.default: "blurry, out of focus, overexpos…
image_strengthnumberThe strength of the image to use for the video generation.0 ≤ n ≤ 1 · default: 1
camera_loraenumThe camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.dolly_in | dolly_out | dolly_left | dolly_right | jib_up | jib_down · +2 more · default: "none"
use_multiscalebooleanWhether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.default: true
video_write_modeenumThe write mode of the generated video.fast | balanced | small · default: "balanced"
match_audio_lengthbooleanWhen enabled, the number of frames will be calculated based on the audio duration and FPS. When disabled, use the specified num_frames.default: true
sync_modebooleanIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.default: false
num_framesintegerThe number of frames to generate.9 ≤ n ≤ 481 · default: 121
audio_strengthnumberAudio conditioning strength. Values below 1.0 will allow the model to change the audio, while a value of exactly 1.0 will use the input audio without modification.0 ≤ n ≤ 1 · default: 1

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/ltx-2-19b/audio-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}