Lightricks
Lightricks

LTX 2.3 Audio to Video

Key Features of LTX 2.3 Audio to Video

Ground-level tracking and hyper-detail slow motion

Dense prompts translate into dynamic movement, atmosphere control, and lens-aware composition.

Prompt

Snorkel lens ground-scraping tracking shot following a barefoot Ethiopian long-distance runner training on a dirt road at dawn, camera inches from the ground racing alongside, her feet kicking up red dust in slow motion at 240fps, Rift Valley landscape blurred in the background, the texture of earth and callused skin in hyper-detail, 40mm snorkel lens at ground height, Nike Running documentary meets Lubezki natural light, the poetry of human endurance

Result

FPV drone spiral and atmospheric decay

Dense prompts translate into dynamic movement, atmosphere control, and lens-aware composition.

Prompt

Drone descent through the open oculus of a derelict Soviet-era radio telescope dish, spiraling downward into the rusted parabolic bowl where a lone botanist catalogs wildflowers growing through cracked concrete, her red jacket the only color against oxidized metal and grey sky, 24mm on a caged FPV drone, the descent creating a vertigo spiral, Tarkovsky Stalker zones of alien beauty reclaiming technology, science swallowed by nature

Result

Through-fabric focus and warm intimate lighting

Dense prompts translate into dynamic movement, atmosphere control, and lens-aware composition.

Prompt

Through-the-veil shot of a bride's face during an Indian wedding ceremony, camera positioned behind the sheer red dupatta fabric, the embroidered pattern creating a textured overlay on her face, her eyes lined with kohl looking down at henna-covered hands, marigold garlands in soft background bokeh, 85mm f/1.2 focused through the fabric layer, warm tungsten and candlelight, Mira Nair Monsoon Wedding intimacy

Result

Native audio from a simple prompt

Dense prompts translate into dynamic movement, atmosphere control, and lens-aware composition.

Prompt

A woman whispering into the microphone

Result

How To Use LTX 2.3 Audio to Video AI Video Model on skills.video

01

Select the LTX 2.3 Audio to Video model

Head to the create page and choose this model from the dropdown list.

02

Input your detailed prompt

Describe the scene, style, and motion you want. Adjust settings as needed.

03

Download your video

Click create, then download or share once the generation finishes.

FAQs

What is LTX-2.3?
LTX-2.3 is the latest open-source video generation model from Lightricks. It uses a DiT-based architecture with a new VAE for sharper details, native audio generation, and support for up to 20-second clips at up to 4K resolution.
What's new in LTX-2.3 compared to previous versions?
LTX-2.3 adds a sharper VAE, cleaner native audio, improved image-to-video quality, better prompt understanding, last-frame interpolation, 9:16 portrait support, and 24/48 FPS options.
What endpoints are available?
LTX-2.3 endpoints include text-to-video, image-to-video, audio-to-video, extend-video, and retake-video. Text-to-video and image-to-video also provide fast variants optimized for speed.
How long can generated videos be?
LTX-2.3 supports generation up to 20 seconds in a single run, and longer outputs can be built using the extend-video workflow.
Does LTX-2.3 support audio?
Yes. LTX-2.3 supports native audio generation and also offers a dedicated audio-to-video endpoint where visuals are generated from an input audio clip.
Can I fine-tune LTX-2.3?
Yes. LTX-2.3 supports LoRA fine-tuning, so you can adapt style, character identity, or domain-specific aesthetics.
How do I get started with the API?
Use the fal.ai SDK (Python or JavaScript), create an API key, then call the endpoint with your prompt and optional media inputs.
How much does LTX-2.3 cost on fal.ai?
Audio-to-video, extend-video, and retake-video are priced at $0.10 per output second on fal.ai. Text-to-video and image-to-video have separate pricing by quality and resolution tier.
Can I use LTX-2.3 for commercial projects?
LTX-2.3 is open source and can be used for commercial workflows under its license terms, while usage through fal.ai is also subject to fal.ai terms of service.