LTX 2.3 Fast Text to Video

LTX 2.3 Fast Text to Video is a text-to-video creation endpoint in the LTX 2.3 family. It is built for creators who need to turn a concrete creative brief into a controlled visual sequence: the request establishes the source material, the intended subject behavior, the camera language, and the atmosphere of the finished shot. The fast route keeps that workflow explicit instead of hiding its input assumptions behind a generic video-generation label.

In practice, this route accepts a written prompt as creative context and exposes duration, resolution, aspect ratio, generate audio for delivery planning. That makes it suitable for shot-based pipelines where teams must preserve a source, direct a transformation, or control the final format without losing sight of the model's central task. Write prompts as a compact shot plan—subject, action, setting, camera, light, and timing—then use the structured fields for constraints that should remain deterministic across iterations.

Highlights

• Scene built from language. No source image is required: the prompt defines subject, action, environment, camera, light, and temporal progression.
• Purposeful camera direction. Camera movement can be written directly into the shot prompt alongside action and staging.
• Native soundtrack option. generate_audio can request sound as part of the same generated scene.
• Fast-route duration matrix. The schema offers 6–20 second choices; clips above 10 seconds are restricted to 1080p at 25 FPS, while shorter clips can use the documented higher resolutions. For lightricks/ltx-2.3-fast/text-to-video, this task-specific control is documented alongside the route’s own required inputs.

Pricing

The request price is calculated with params.resolution == "2160p" ? params.duration * 0.16 : params.resolution == "1440p" ? params.duration * 0.08 : params.duration * 0.04.

The model card records a base price of $0.040000; the formula above determines usage-priced requests.

When to Use

Prompt Guide

For text-to-video creation, describe one coherent shot rather than a list of visual keywords. Put the main subject and action first, follow with location and staging, then add camera movement, lens or framing, lighting, mood, and any timed change. Keep URLs and hard delivery choices in their dedicated fields.

{
  "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",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "21:9",
  "generate_audio": true
}

Technical Specs

Request fields

Related Models

• lightricks/ltx-2.3-fast/image-to-video
• lightricks/ltx-2.5/text-to-video/pro
• lightricks/ltx-2.5/text-to-video/fast
• lightricks/ltx-2.3-quality/text-to-video