Ltx 2.5 Text To Video API Documentation

Ltx 2.5 Text To Video API Documentation

Playground

LTX 2.5 Text-to-Video generates high-fidelity synchronized audio-video content from text prompts, with flexible duration and 720P / 1080P / 2K / 4K output for cinematic videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

LTX-2.5 Text-to-Video generates synchronized video and audio directly from a text prompt. It supports multiple resolutions, landscape or vertical aspect ratios, and prompt-guided control over scene composition, subject motion, camera movement, and audio direction.

Why Choose This?

• Text-to-video generation
  Generate videos directly from natural-language prompts.

• Native audio generation
  Create synchronized audio together with the video output.

• Multiple resolution options
  Choose from 720p, 1080p, 2k, or 4k depending on quality and cost needs.

• Landscape and vertical formats
  Use 16:9 for landscape video or 9:16 for vertical content.

• Controlled duration
  Generate videos from 5 to 20 seconds.

• Seed control
  Use a fixed seed for more reproducible prompt testing and variation comparison.

Parameters

How to Use

1. Write your prompt — Describe the subject, action, setting, camera movement, lighting, mood, and audio direction.
2. Choose resolution — Select 720p, 1080p, 2k, or 4k.
3. Choose aspect ratio — Use 16:9 for landscape video or 9:16 for vertical content.
4. Set duration — Choose a video length from 5 to 20 seconds.
5. Set seed optional — Use a fixed seed for more reproducible outputs, or -1 for a random seed.
6. Submit — Generate the final text-to-video output with synchronized audio.

Pricing

Pricing is based on generated video duration and selected resolution.

Native audio is included at every resolution and does not add a separate charge.

Best Use Cases

• Cinematic scene generation — Create short visual scenes from detailed prompts.
• Social media content — Generate landscape or vertical clips for different platforms.
• Marketing videos — Produce promotional clips, product scenes, and campaign visuals.
• Storyboarding — Turn written scene ideas into motion previews.
• Creative prototyping — Test motion, camera direction, audio style, and pacing from text.
• Prompt iteration — Compare different visual and audio directions with controlled seeds.

Pro Tips

• Include subject, setting, action, camera movement, lighting, mood, and audio cues in the prompt.
• Use 9:16 for vertical mobile content and 16:9 for landscape video.
• Use shorter durations for quick prompt testing and longer durations when the scene needs more time.
• Use 720p for lower-cost iteration and higher resolutions for final-quality outputs.
• Set a fixed seed when comparing prompt variations.
• Keep the prompt focused on one main scene or action for stronger motion coherence.

## Authentication

For authentication details, please refer to the [Authentication Guide](/api-authentication).

## API Endpoints

### Submit Task & Query Result

<ApiTabs submitUrl={model.submitUrl} resultUrl={model.resultUrl} payload={model.defaultValues} />

## Parameters

### Task Submission Parameters

#### Request Parameters

<RequestParams params={model.params} />

#### Response Parameters

<SubmitResponse />

#### Result Request Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| id | string | Yes | - | Task ID |

#### Result Response Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., "success") |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array&lt;string \| object&gt; | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: `created`, `processing`, `completed`, or `failed` |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |