Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

LTX 2 PRO Text To VideoCinematic Videos From Text

Try LTX 2 PRO Text To VideoAPI Documentation

Generate Pro Video Fast

4K Resolution

Native 2160p Output

Produce 1080p to 2160p videos at 25-50 fps with LTX 2 PRO Text To Video model.

Synced Audio

Single-Pass Generation

Create video and audio together using LTX 2 PRO Text To Video API for perfect alignment.

Cinematic Control

Prompt-Driven Motion

Control camera, lighting, and style via detailed prompts in LTX 2 PRO Text To Video.

Examples

See what LTX 2 PRO Text To Video can create

Copy any prompt below and try it yourself in the playground.

City Timelapse

“Aerial drone shot over futuristic city at dusk, neon lights reflecting on skyscrapers, smooth camera pan right, cinematic lighting, 4K, 50fps, ambient electronic music synced to motion.”

Ocean Waves

“Powerful waves crashing on rocky cliff, slow motion foam spray, golden hour sunlight, dramatic low-angle camera rise, natural wave sounds and wind, professional cinematic style, 2160p.”

Mountain Flight

“Eagle soaring through misty mountain peaks at dawn, dynamic tracking shot following flight path, volumetric fog and god rays, orchestral swelling score, ultra realistic, 4K 50fps.”

Desert Dune

“Wind sculpting golden sand dunes at sunset, time-lapse with gentle camera dolly forward, warm color grading, subtle wind audio with distant horizon glow, cinematic 1440p.”

For Developers

A few lines of code.
Video generation. One call.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/text-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "A cinematic skincare commercial featuring a stunning female model with flawless glowing skin and wet, brushed-back hair. Begin with close-up shots of fresh water splashing in slow motion, soft daylight reflections, and droplets gliding over smooth skin. Transition to the model gently touching her face, smiling confidently, holding a premium facewash bottle beside her cheek. Show her applying the facewash with delicate hand movements, water running over her skin, highlighting hydration and purity. Use soft natural lighting, minimal clean background, and elegant product focus. Include aesthetic shots of the facewash bottle rotating in light, product texture visuals, and final hero shot of the model holding the product with a gentle smile. Mood: Fresh, luxurious, pure, premium skincare. Ultra-realistic, beauty commercial style, 4K, smooth transitions, slow motion.",
  "duration": "6"
}
)
print(response.json())

FAQ

Common questions about LTX 2 PRO Text To Video

Read the docs

LTX 2 PRO Text To Video generates high-fidelity 4K videos with synced audio from text prompts. It supports 1080p-2160p resolutions at 25-50 fps. Commercial use permitted via API.

Send detailed text prompts describing scenes, camera moves, and style to the ltx 2 pro text to video api endpoint. Receive MP4 output with coherent motion and audio. Duration 6-20 seconds.

Available options: 1080p, 1440p, 2160p at 16:9 aspect ratio. Frame rates configurable to 25 or 50 fps. Cost scales with resolution from $0.06 per second.

LTX 2 PRO Text To Video offers native 4K, synced audio, and cinematic control as open-source alternative. Single-pass generation beats multi-step pipelines. Apache 2.0 licensed.

Yes, produces synchronized dialogue, music, and effects aligned to video action. Asymmetric architecture handles video and audio streams together. No separate audio generation needed.

Primary input is detailed text prompts for actions and style. Optional image keyframes or conditioning for layout control. Parameters include duration, seed, and steps.

Ready to create?

Start generating with LTX 2 PRO Text To Video on ModelsLab.

Try LTX 2 PRO Text To VideoAPI Documentation