Skip to content

Ltx 2.3 Quality

POST/v1/run

Ltx 2.3 Quality Audio To Video by Lightricks - advanced AI model for audio-to-video. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to lightricks/ltx-2.3-quality/audio-to-video.

Default: lightricks/ltx-2.3-quality/audio-to-video

stringpromptrequired

The prompt to guide the audio-driven video generation.

stringimagerequired

Optional URL of an image to use as the first frame. When omitted, generation runs from text and audio only.

Optional<string>audio

The URL of the audio track that drives generation.

Optional<string>resolution

Final output size. 'auto' matches the input image aspect ratio when image_url is provided; otherwise it uses a landscape fallback.

Allowed values: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Default: auto

Optional<boolean>generate_audio

Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.

Default: true

Optional<number>guidance_scale

Classifier-free guidance scale. The default is tuned for fast, high-quality generation.

Range: 1 to 20

Default: 1

Optional<integer>num_inference_steps

Number of inference steps. Defaults to 15 and can be increased up to 30.

Range: 8 to 30

Default: 15

Optional<string>video_quality

The quality preset of the generated video.

Allowed values: low, medium, high, maximum

Default: high

Optional<number>frames_per_second

Frames per second of the generated video.

Range: 1 to 60

Default: 24

Optional<boolean>match_audio_length

When enabled, derives the number of frames from the audio duration and frames_per_second. When disabled, uses num_frames.

Default: true

Optional<number>image_strength

Conditioning strength for the optional first frame. 1.0 keeps the image more strictly; lower values give the model more freedom.

Range: 0 to 1

Default: 0.7

Optional<string>video_write_mode

The write mode of the generated video.

Allowed values: fast, balanced, small

Default: balanced

Optional<integer>num_frames

The number of frames to generate.

Range: 9 to 481

Default: 121

Optional<integer>seed

Random seed for reproducibility. If None, a random seed is chosen.

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: audio-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async