Explore All AI Models

From image generation to voice synthesis to video transcription — deAPI gives you a single, unified API to access the best open-source models.

Text-to-Video

Create dynamic videos from text prompts. Generate engaging visual content without cameras or editing software.

LTX-2.3 22B Text-to-Video

Up to 1024×1024 resolution. 49–241 frames at 24 fps (2–10 sec). Single-step distilled inference (INT8). Generates synchronized video with matching audio from text.

Sample Output

Sample Prompt

Extreme macro shot of a single drop of honey falling in slow motion onto a stack of golden pancakes, the thick amber liq... Extreme macro shot of a single drop of honey falling in slow motion onto a stack of golden pancakes, the thick amber liquid stretching and pooling outward, steam rising from the warm surface, shallow depth of field with creamy bokeh, warm morning sunlight from the right, the sound of sizzling butter and a soft drip, smooth overhead camera slowly pushing in, food commercial cinematography
Playground Coming Soon View Pricing Model Details
LTX-2 19B Distilled FP8 Text-to-Video

Up to 1024x1024 resolution. 24–240 frames at 24fps (4–10 sec). Text-to-video and image-to-video modes. Single-step distilled inference. Audio generation included – produces video with matching sound.

Sample Output

Sample Prompt

A slow-motion close-up of a Japanese tea ceremony in a traditional wooden room. An elderly woman in a silk kimono carefu... A slow-motion close-up of a Japanese tea ceremony in a traditional wooden room. An elderly woman in a silk kimono carefully pours steaming matcha from a bamboo ladle into a ceramic bowl. Wisps of steam curl upward, catching the soft golden light filtering through shoji screens. The gentle sounds of water pouring, the soft clink of ceramic, and distant wind chimes create a meditative atmosphere. Shallow depth of field, warm color palette, Wes Anderson symmetry, cinematic 35mm film grain.
Playground Coming Soon View Pricing Model Details
LTX-Video 13B Text-to-Video

Up to 768×768 resolution. 30–120 frames at 30fps (1–4 sec). Text-to-video and image-to-video modes. Single-step distilled inference.

Sample Output

Sample Prompt

A woman with light skin, wearing a blue jacket and a black hat with a veil, looks down and to her right, then back up as... A woman with light skin, wearing a blue jacket and a black hat with a veil, looks down and to her right, then back up as she speaks; she has brown hair styled in an updo, light brown eyebrows, and is wearing a white collared shirt under her jacket; the camera remains stationary on her face as she speaks; the background is out of focus, but shows trees and people in period clothing; the scene is captured in real-life footage.
Playground Coming Soon View Pricing Model Details