LTX-2.5 AI Video Generator

Cinematic video with native audio and multi-shot continuity

Lightricks' LTX-2.5 on Moosky: text-to-video or start-frame clips with joint audio-video generation, 480P-720P, 4-20 seconds. The LTX family's newest generation - a step up from LTX-2.3.

Generate with LTX-2.5 Explore AI Video

MoModesT2V, I2V, FFLF

ReResolution480P to 720P

DuDuration4-20s, native audio

Model Overview

LTX-2.5

LTX-2.5 generates video with native synchronized audio from a prompt or a single start frame. It is the newest generation of Moosky's LTX video family: joint audio-video, multi-shot continuity, and a newer diffusion decoder over LTX-2.3's strengths in dialogue scenes, talking heads, and cinematic motion.

Text-to-video, or image-to-video from an optional start frame

Joint audio-video generation: dialogue, ambience, and SFX in one pass

480P and 720P in landscape, portrait, square, and adaptive aspect

4-20 second clips with optional first-to-last-frame control

Why use it on Moosky AI?

Model-specific controls with no subscription, clean outputs, and a workflow built for fast creative iteration.

Native joint audio

Generate dialogue, ambience, and SFX synchronized with the video in a single pass.

Text-to-video

Write a prompt and generate a clip - no starting frame required.

Start-frame I2V

Optionally anchor the opening from a still image, with adaptive aspect.

Multi-shot continuity

Newer diffusion decoder keeps subjects and motion coherent across beats.

Clean outputs

Optional watermark control for final, brand-ready clips.

Fine control

Seed, length (4-20s), resolution, and first-to-last-frame options.

How it works

Three focused steps from setup to finished output.

1. Add inputs

Start from a prompt alone, or attach a start (and optional last) frame.

2. Describe the scene

Write the motion, camera, dialogue, and audio you want.

3. Generate and download

Render the clip with native audio and download when processing finishes.

Credit-based

Simple, honest pricing

No subscriptions. No hidden costs. Pay only for the credits you use.

paidPay as you goOnly pay for what you generate.

event_busyNo monthly feesNo subscriptions. No commitments.

verifiedCredits never expireUse your credits whenever you want.

business_centerCommercial useUse your videos for commercial projects.

View credits & pricing

More from Moosky AI

Explore our full suite of AI tools.

AI Video Project Director AI Image Upscaling Editing

Frequently Asked Questions

Does LTX-2.5 require a starting image?

No. LTX-2.5 supports text-to-video directly. You can optionally attach a start frame (and a last frame) to steer the opening composition.

Can LTX-2.5 generate speech?

Yes. Include quoted dialogue in your prompt and LTX-2.5 generates synchronized speech, ambience, and sound effects in the same pass as the video.

What resolutions does LTX-2.5 support?

LTX-2.5 supports 480P and 720P in landscape, portrait, square, and adaptive orientation.

When should I choose LTX-2.5 over LTX-2.3 or Seedance?

Choose LTX-2.5 for LTX-family clips that want native joint audio and multi-shot continuity at 480P-720P. Move to Seedance 2.5 when you need 1080P, 16-30 second single shots, or large reference kits.