Is the audio generated or dubbed?

Generated. The model produces audio with the picture, and it follows the scene. Plan a fallback sound bed for content that needs continuous audio.

Which licence covers LTX-2.5?

The LTX-2 Community License, as published by Lightricks. Read it before building a product on the model.

How much does LTX-2.5 cost on Windflow?

LTX-2.5 costs $0.0040 per billable session-second ($14.40/hr of billable time). Billing starts at the session's first generation_started event and stops when the session is released or ends. Queueing, worker startup, time before generation starts and the documented reconnect grace are not billed. After generation starts, paused or unwatched time remains billable; release the owner session to stop the meter. There is no subscription.

How do I get access to LTX-2.5?

Windflow is in private beta. Request access from the sign-up page, or ask for a live demo of LTX-2.5. Approved accounts start with $5 and four concurrent sessions.

Is LTX-2.5 always running?

No. Model capacity is brought up on demand rather than kept standing. Live readiness for each model is published at api.windflow.online/v1/status, and a live demo can be arranged on request.

← Models

Realtime video generation

LTX-2.5 API

Video on main_video and the audio generated with it on main_audio, aligned per window. Served on Windflow as a realtime session you can plug into your product and pay for by the second.

Start a session Request access

Overview

What LTX-2.5 does

LTX-2.5 is Lightricks' 22-billion-parameter joint audio-and-video diffusion model. On Windflow it generates a stream window by window from a text prompt and an optional reference still, delivering video on main_video and the audio generated with it on main_audio, aligned per window.

A session keeps the model running: connect once, steer it with text prompts and a reference image while it runs, and receive the live stream back on a named output track.

Every model in the catalog speaks the same typed session protocol, so switching between models changes the controls you send, not how you integrate.

Architecture: 22B joint audio+video DiT, two-stage, generated one window at a time
Resolution: 832 × 448 measured; the canvas is configurable in multiples of 64
Playout: 24
Chunk: 241 frames per window (10.04 s)
Control latency: A whole window: the pipeline does not yield progressively, so time-to-first-frame equals one window's generation time. The reference still is published while it runs.
Inputs: A text prompt and an optional reference still
Outputs: Video on main_video and the audio generated with it on main_audio, aligned per window
Delivery: WebRTC
Session protocol: sdk.realtime.v2
Price: $0.0040 per billable second

$0.0040

Per billable second

Meter starts when generation begins

$14.40

Per billable hour

The same rate, held for an hour

Production

Runtime status

Capacity is brought up on demand

Private beta

Access

Request access or a live demo

Use cases

What teams build with LTX-2.5

Audio-visual scenes where sound is generated with the picture rather than dubbed after.
Continuous AI television or channel formats built from successive windows.
Reference-still-anchored characters and settings across windows.
Comparing a joint audio-video model with video-only alternatives on one protocol.

Provenance

Where LTX-2.5 comes from

The model and its code are published by the upstream authors. Windflow runs it behind one session API and bills per billable second.

Lightricks/LTX-2 on GitHubLicence · LTX-2 Community License
Lightricks/LTX-2.5 on Hugging Face

Compare

LTX-2.5 next to similar models

Model	Inputs	Output	Price per billable second
LTX-2.5	A text prompt and an optional reference still	Video on main_video and the audio generated with it on main_audio, aligned per window	$0.0040
Helios	Text prompt (required before start) and an optional reference image for image-to-video	One continuous, steerable clip on the main_video track	$0.0017
LongLive-2.0	Text shot prompts only — no reference image in this release	A multi-shot clip on main_video; chunk_index resets per scene while session_chunk keeps counting	$0.0021
MiniMax FastH3	A text prompt with visual, dialogue, soundscape, and music direction	Video on main_video and generated audio downmixed to mono on main_audio, aligned per window	$0.0069

FAQ

Questions about LTX-2.5

Is the audio generated or dubbed?: Generated. The model produces audio with the picture, and it follows the scene. Plan a fallback sound bed for content that needs continuous audio.
Which licence covers LTX-2.5?: The LTX-2 Community License, as published by Lightricks. Read it before building a product on the model.
How much does LTX-2.5 cost on Windflow?: LTX-2.5 costs $0.0040 per billable session-second ($14.40/hr of billable time). Billing starts at the session's first generation_started event and stops when the session is released or ends. Queueing, worker startup, time before generation starts and the documented reconnect grace are not billed. After generation starts, paused or unwatched time remains billable; release the owner session to stop the meter. There is no subscription.
How do I get access to LTX-2.5?: Windflow is in private beta. Request access from the sign-up page, or ask for a live demo of LTX-2.5. Approved accounts start with $5 and four concurrent sessions.
Is LTX-2.5 always running?: No. Model capacity is brought up on demand rather than kept standing. Live readiness for each model is published at api.windflow.online/v1/status, and a live demo can be arranged on request.

Guides and comparisons

Other models

Realtime video generationHelios Realtime video generationLongLive-2.0 Live video transformationSANA-Streaming Live video transformationEdenLive Live video transformationJoyAI-Video-Edit Navigable world modelLingBot-World 2.0 Neural game renderingMatrix-Game 4.0 Navigable world modelDreamX-World-5B Navigable world modelABot-World-0-5B Realtime video generationMiniMax FastH3 Navigable world modelHy-Nomas

Run LTX-2.5 inside your product.

Request a live demo See pricing