# LTX 2.5 Pro Audio-to-Video — Atlas Cloud API

> LTX-2.5 Pro audio-to-video (Lightricks LTX-2 native API): generate video synchronized to a driving audio track (dialogue/music/ambient); the audio sets the length. Up to 4K at 24/48 fps.

This is the machine-readable API reference for **LTX 2.5 Pro Audio-to-Video** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `ltx/ltx-2.5-pro/audio-to-video`
- **Built by**: LTX
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/ltx/ltx-2.5-pro/audio-to-video
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.12 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "ltx/ltx-2.5-pro/audio-to-video"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video ltx/ltx-2.5-pro/audio-to-video -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `ltx/ltx-2.5-pro/audio-to-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"ltx/ltx-2.5-pro/audio-to-video"`

- **`audio`** (`string`, _required_):
  Driving audio track (MP3 / M4A / OGG). WAV is only supported when it wraps AAC-LC / MP3 / Vorbis / FLAC — plain PCM WAV is rejected. Audio duration must be within 10 seconds.

- **`image`** (`string`, _optional_):
  Optional first-frame image (URL / Base64 / asset://) for visual direction. Required if prompt is empty.

- **`last_image`** (`string`, _optional_):
  Optional last-frame image (URL / Base64 / asset://); requires image. When set, the clip interpolates from the first frame to this frame.

- **`prompt`** (`string`, _optional_):
  Text prompt. Required if image is not provided; when image is set, describes how the image should be animated (may be empty).
  - Default: `"A person speaking to camera, natural expression, cinematic lighting."`

- **`resolution`** (`string`, _optional_):
  Output resolution tier. Combined with aspect_ratio to select the exact frame size (720p→1280x720, 1080p→1920x1080, 1440p→2560x1440, 4k→3840x2160; portrait 9:16 swaps width/height). If omitted, LTX derives it from the input image.
  - Default: `"1080p"`
  - Options: "720p", "1080p", "1440p", "4k"

- **`aspect_ratio`** (`string`, _optional_):
  Frame orientation: 16:9 landscape or 9:16 portrait.
  - Default: `"16:9"`
  - Options: "16:9", "9:16"

- **`fps`** (`integer`, _optional_):
  Frames per second. Defaults to 24.
  - Default: `24`
  - Options: 24, 25, 48, 50

- **`camera_motion`** (`string`, _optional_):
  Optional camera movement directive applied to the shot.
  - Options: "dolly_in", "dolly_out", "dolly_left", "dolly_right", "jib_up", "jib_down", "static", "focus_shift"



**Required Parameters Example**:

```json
{
  "model": "ltx/ltx-2.5-pro/audio-to-video",
  "audio": ""
}
```


**Full Example**:

```json
{
  "model": "ltx/ltx-2.5-pro/audio-to-video",
  "audio": "",
  "image": "",
  "last_image": "",
  "prompt": "A person speaking to camera, natural expression, cinematic lighting.",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "fps": 24,
  "camera_motion": "dolly_in"
}
```


### Output Schema

The API returns the following output format:


- **`code`** (`integer`, _optional_):

- **`message`** (`string`, _optional_):

- **`data`** (`string`, _optional_):



**Example Response**:

```json
{
  "code": 0,
  "message": "",
  "data": null
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx/ltx-2.5-pro/audio-to-video",
  "audio": "",
  "image": "",
  "last_image": "",
  "prompt": "A person speaking to camera, natural expression, cinematic lighting.",
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "fps": 24,
  "camera_motion": "dolly_in"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/ltx/ltx-2.5-pro/audio-to-video)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

#### 1. Introduction

**LTX-2.5 Pro Audio-to-Video** is served through the native Lightricks LTX-2 API (`api.ltx.io`). This README covers a single API model identifier:

- `ltx/ltx-2.5-pro/audio-to-video`

Audio-to-video generates visuals **synchronized to a driving audio track** — dialogue, music, or ambient sound. The audio sets the length of the generated video. Optionally condition on a first-frame image for visual direction, a last frame for interpolation, and a camera-motion directive. Requests are processed asynchronously (submit + poll) and delivered as a finished MP4 on AtlasCloud storage.

#### 2. Key Features

- **Audio-Driven Generation**: Visuals are synchronized to the supplied `audio`; the audio also sets the output length.
- **Optional Image Conditioning**: Provide `image` (first frame) for visual direction, and `last_image` to interpolate first→last. If no image is given, `prompt` drives the content.
- **Up to 4K, 24/48 fps**: 720p / 1080p / 1440p / 4K in landscape (16:9) or portrait (9:16).
- **Camera Control**: Optional `camera_motion` directive (dolly, jib, focus shift, static).
- **Billed by Input Audio**: Charged per second of the input audio (which equals the output length).

#### 3. Support Matrix

| Resolution | Landscape | Portrait | Max input audio |
|---|---|---|---|
| 720p  | 1280x720  | 720x1280  | 10s |
| 1080p | 1920x1080 | 1080x1920 | 10s |
| 1440p | 2560x1440 | 1440x2560 | 10s |
| 4K    | 3840x2160 | 2160x3840 | 10s |

Either `prompt` or `image` must be provided. The input audio duration must not exceed the maximum shown for the chosen resolution.

#### 4. Parameters

The request body matches this model's schema exactly:

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/ltx/ltx-2.5-pro/audio-to-video · Docs: https://www.atlascloud.ai/docs