LTX-2 Pro is a text-to-video engine that generates synchronized audio and 1080P video from text prompts for production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.06per run·~16 / $1
ExamplesView all
Breathtaking wide establishing shot. A magnificent, ornate airship slowly emerges from thick clouds, approaching a colossal, impossible city floating amongst the clouds, connected by glowing energy bridges. Tiny flying creatures circle the city spires. Epic fantasy, volumetric lighting, masterpiece.
Breathtaking cinematic wide shot. An astronaut in a bulky spacesuit stands dwarfed before a colossal, impossibly ancient alien structure made of shifting, iridescent metal on a desolate Mars-like planet. Strange geometric patterns pulse with faint light across its surface. The astronaut slowly reaches out a gloved hand towards the humming structure. Sense of awe and mystery.
Dynamic action sequence. A character sprints across rooftops at night against a neon-lit city skyline. They perform a desperate, parkour-style leap across a wide gap between buildings, landing hard and rolling. Pursuers' flashlights sweep across the rooftop behind them. Fast-paced, shaky cam effect, high energy.
Vast desert landscape under a blazing sun. A herd of colossal, ancient creatures resembling walking mountains made of rock and sand, slowly trek across the endless dunes, kicking up huge clouds of dust. Drone shot following the herd from above. Photorealistic, sense of immense scale.
Tense first-person POV shot moving slowly down a dark, derelict spaceship corridor. Emergency lights flicker erratically. Wires spark. Suddenly, a grotesque, biomechanical alien creature drops from the ceiling vents right in front of the camera with a screech. Jumpscare, found footage style, claustrophobic.
An extreme close-up on a character's eye, reflecting a battle scene. The camera spins around the character's face as their expression shifts from fear to determination—shallow depth of field, intense emotion.
A city skyline where the buildings are made of giant, vintage Jenga blocks, one tower is slowly and precariously beginning to wobble. Dramatic low angle shot, suspenseful atmosphere.
A dramatic low-angle, slow-motion shot. A figure in a long trench coat runs desperately down a rain-slicked, empty city street during the golden hour. The setting sun creates long, dramatic shadows and intense lens flares. Cinematic, high contrast.
A tiny astronaut sloth, wearing a retro bubble helmet, slowly planting a flag made of a leaf onto a giant, floating donut in a nebula made of coffee and cream. Whimsical, slow motion, cinematic.
A tiny knitted octopus driving a miniature submarine made from a teacup through a bathtub filled with bubbles and rubber ducks. Playful, macro shot.
Related Models
README
lightricks/ltx-2-pro/text-to-video 🎬
LTX-2 Pro is a next-generation AI creative engine by Lightricks, designed for real production workflows where speed and precision matter. It generates high-quality, synchronized audio and video directly from text — delivering cinematic scenes, sound, and motion in perfect harmony.
⚡ Key Highlights
-
🚀 Lightning-Fast Generation Built for production speed — generate vivid, dynamic videos in seconds with minimal latency.
-
🎧 Audio-Video Synchronization Generates perfectly aligned motion, sound, and rhythm, ensuring every visual beat matches its audio cue.
-
🎥 Cinematic Control Understands text prompts describing camera movements, scene composition, and emotional tone, producing smooth and coherent cinematic sequences.
-
🎨 High-Fidelity Visuals Creates photorealistic or stylistic videos with natural lighting, color grading, and motion consistency.
-
🧠 Real-World Workflow Ready Designed for studio, marketing, and creator pipelines, enabling fast iteration and reliable production integration.
⚙️ Parameters
| Parameter | Description |
|---|---|
| prompt* | Describe the scene, action, or atmosphere (e.g., “herd of colossal creatures trekking across sand dunes, cinematic drone shot”). |
| duration | Choose video length in seconds (6s / 8s / 10s). |
💰 Pricing
| Target Resolution | Price per second | Approx. Runtime per $1 |
|---|---|---|
| 1080p | $0.06 / s | ~17 seconds per $1 |
💡 Use Cases
- Film Previsualization — Generate cinematic shots and sequences for storyboards and concept scenes.
- Advertising & Marketing — Create short promotional clips with perfect sound–motion sync.
- Music & Performance Videos — Match rhythm, pacing, and emotion in AI-synchronized productions.
- Creative Storytelling — Produce narrative visuals enhanced with audio atmosphere and motion cues.
Ltx 2 Pro Text To Video API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/lightricks/ltx-2-pro/text-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Ltx 2 Pro Text To Video below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/lightricks/ltx-2-pro/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"generate_audio": true
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("lightricks/ltx-2-pro/text-to-video", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"generate_audio": true
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"lightricks/ltx-2-pro/text-to-video",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"duration": 6,
"generate_audio": true
}
)
print(output["outputs"][0]) # → URL of the generated outputLtx 2 Pro Text To Video API — Frequently asked questions
What is the Ltx 2 Pro Text To Video API?
Ltx 2 Pro Text To Video is a Lightricks model for video generation, exposed as a REST API on WaveSpeedAI. LTX-2 Pro is a text-to-video engine that generates synchronized audio and 1080P video from text prompts for production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Ltx 2 Pro Text To Video API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-pro-text-to-video.
How much does Ltx 2 Pro Text To Video cost per run?
Ltx 2 Pro Text To Video starts at $0.060 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Ltx 2 Pro Text To Video accept?
Key inputs: `prompt`, `duration`, `generate_audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-pro-text-to-video.
How long does Ltx 2 Pro Text To Video take to generate?
Average end-to-end generation time on WaveSpeedAI is around 86 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Ltx 2 Pro Text To Video outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Lightricks). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.