LTX-2 Fast is a production-grade text-to-video engine that creates synchronized audio and 1080p video from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.04per run·~25 / $1
ExamplesView all
Action scene! Steampunk airship pirates, wearing goggles and leather gear, swing on ropes from their rickety airship onto the deck of a massive, opulent passenger dirigible amidst clouds. Cannons fire in the background. Dynamic, adventurous.
Black and white film noir. A lone detective in a fedora and trench coat stands under a flickering streetlamp on a rain-soaked cobblestone street late at night. Shadows are long and deep. He lights a cigarette, the flame briefly illuminating his weary face. Moody, atmospheric.
Dynamic chase sequence. A sleek, neon-lit hovercar weaves dangerously through dense flying traffic between towering, rain-slicked skyscrapers in a futuristic megacity. Sparks fly as it narrowly avoids collisions. Blade Runner aesthetic, fast-paced.
Tense handheld camera shot, POV style. Peeking through a dusty, grimy window into an abandoned, dark house. The only light comes from the camera's weak flashlight beam, sweeping nervously across dilapidated furniture covered in white sheets. Suddenly, the beam catches a pair of eyes reflecting back from the deep darkness at the end of the hallway before darting away.
Cinematic sci-fi horror. Inside a vast, dark server room filled with humming racks. A single, massive spherical AI core pulsates with an ominous red light. Sparks erupt erratically from nearby consoles. Suddenly, all the server lights go dark except for the core's intense red glow. A cold, synthetic voice echoes (implied): "I am awake." Volumetric smoke, oppressive atmosphere.
Related Models
README
lightricks/ltx-2-fast/text-to-video ⚡🎬
LTX-2 Fast is a high-speed variant of the LTX-2 AI creative engine from Lightricks, built for creators and production teams that need rapid, synchronized text-to-video generation. It delivers cinematic motion, matching sound, and consistent visual style — all in a fraction of the time compared to standard models.
Now support 20s generation!!
🌟 Key Features
-
🚀 Ultra-Fast Inference Generates full-quality videos in seconds, optimized for low latency and quick iteration in real workflows.
-
🎧 Audio–Video Synchronization Maintains perfect timing between motion, rhythm, and sound, ensuring seamless A/V alignment across every frame.
-
🎥 Realistic Cinematic Motion Handles camera pans, dolly shots, zooms, and character movement smoothly, with stable frame transitions and natural lighting.
-
🎨 Style-Preserving Generation Keeps your intended color palette, tone, and artistic mood consistent throughout the clip.
-
⚙️ Lightweight & Efficient Designed for production pipelines that need fast turnaround, predictable cost, and dependable visual quality.
⚙️ Parameters
| Parameter | Description |
|---|---|
| prompt* | Describe scene, action, camera and mood. |
| duration | Choose up to 20s. |
| audio (optional) | Upload .wav/.mp3 to drive A/V synchronization. |
💰 Pricing
| Target Resolution | Price per second | Approx. Runtime per $1 |
|---|---|---|
| 1080p | $0.04 / s | ~25 seconds per $1 |
💡 Use Cases
- Marketing & Ad Creatives — Generate high-quality short-form visuals with synchronized soundtracks.
- Content Production — Prototype or produce story snippets, intros, and transitions in minutes.
- Film Previz & Concept Design — Quickly visualize scripts or moodboards with cinematic pacing.
- Education & Training — Turn scripts or lesson outlines into dynamic, synchronized explainer clips.
🧠 Example Prompt
Cinematic aerial shot of a futuristic city at sunrise, warm golden light reflecting off glass towers, gentle camera tilt, ambient soundtrack in sync.
Ltx 2 Fast Text To Video API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/lightricks/ltx-2-fast/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 Fast Text To Video below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/lightricks/ltx-2-fast/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-fast/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-fast/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 Fast Text To Video API — Frequently asked questions
What is the Ltx 2 Fast Text To Video API?
Ltx 2 Fast Text To Video is a Lightricks model for video generation, exposed as a REST API on WaveSpeedAI. LTX-2 Fast is a production-grade text-to-video engine that creates synchronized audio and 1080p video from text prompts. 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 Fast 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-fast-text-to-video.
How much does Ltx 2 Fast Text To Video cost per run?
Ltx 2 Fast Text To Video starts at $0.040 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 Fast 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-fast-text-to-video.
How long does Ltx 2 Fast Text To Video take to generate?
Average end-to-end generation time on WaveSpeedAI is around 95 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 Fast 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.