Video generation
Available now

LTX 2.3

by Lightricks

Lightricks' open‑source audio‑visual model.
Synced video and sound in one pass, native vertical output up to 4K at 50 fps.

LTX 2.3

by Lightricks

Key features

Technical specifications

Up to 4K

Native vertical 1080×1920+

Up to 50 fps

Smooth motion ceiling

Up to 20s

Per-clip generation length

LTX-2 Community

Open weights, community license

Use cases

Vertical short-form video

Native 9:16 generation up to 1080×1920 is the right shape and res for TikTok, Reels, YouTube Shorts, and other vertical surfaces.

Music and audio-led content

Use audio-to-video mode to generate visuals that match a specific track, dialogue read, or sound design, the audio drives the timing.

Ad creative with native sound

Generate short ad clips with dialogue, ambient sound, and SFX in one pass, ready to publish without a separate audio mix.

Production iteration

Higher frame rate and resolution ceiling makes LTX 2.3 a fit for iterative creative work where output needs to hold up beyond rough cut.

Prompt examples

Vertical short

Vertical close-up, hand pouring matcha into a ceramic cup, gentle morning light, soft pouring sound, 6 seconds, 9:16

Edit prompt

Audio-led

Generate a video to match this audio track, urban skate session at golden hour, vertical, energetic cuts implied by the rhythm

Edit prompt

Cinematic ad

Slow push-in on a leather sneaker on a wet city street, neon reflections, distant traffic sound, vertical 1080×1920

Edit prompt

Overview

LTX 2.3 is Lightricks' open-source audio-visual video generation model, the latest in the LTXV family. The model generates synchronized video and audio in a single forward pass, supports native vertical output up to 4K at up to 50 fps, and includes a dedicated audio-to-video mode where an input audio clip drives visual timing. With a 22B-parameter Diffusion Transformer, a rebuilt variational autoencoder, and openly published weights on Hugging Face under the LTX-2 Community License, LTX 2.3 is one of the few production-grade video models that's both open and audio-native, available hosted on Morphic without infrastructure to manage.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is LTX 2.3?
LTX 2.3 is Lightricks' open-source audio-visual video generation model. It generates synchronized video and audio in a single pass, supports native vertical output up to 4K, and runs at up to 50 fps.
How is LTX 2.3 different from earlier LTX versions?
2.3 ships a rebuilt variational autoencoder, a quadrupled text encoder built on Gemma 3 12B, and a gated-attention text connector for better prompt adherence. Resolution, frame rate, and audio quality all step up over LTX-2.
Does LTX 2.3 support vertical video?
Yes, natively. The model generates 9:16 directly at full resolution rather than cropping a horizontal frame, which keeps detail and composition right for vertical-first surfaces.
What does audio-to-video do?
Feed in an audio clip and LTX 2.3 generates matching visuals timed to the audio. Useful for music-driven content, ads keyed to a track, or dialogue-led shorts where the audio sets the pacing.
How do I use LTX 2.3 on Morphic?
Open Copilot, describe the shot or attach an audio track, and pick LTX 2.3. For vertical short-form, audio-led content, or anything that benefits from native sound generation, LTX 2.3 is the right pick.
Is LTX 2.3 really open weights?
Yes. Lightricks publishes the weights on Hugging Face under the LTX-2 Community License. On Morphic you use the hosted version, no infrastructure to manage, but the underlying model is openly available for local or on-prem use.

Other models

Explore the rest of the Morphic model catalog.

See all models →

ChatGPT Images 2.5

OpenAI

OpenAI's image model, released September 2026. Sharper detail, precise edits, faster.

Lyria 3.5

Google DeepMind

Google's best-sounding music model. Full songs with structure, vocals, and lyrics.

MiniMax H3 Max Turbo

fal.ai

The fast tier of fal's post-trained H3. Twice the speed, nearly the same look.

Inworld TTS 2

Inworld

Ninety-five voices, 100+ languages. Speech that starts in under a second.