# Ltx v2.5 | Audio to Video | fast

LTX 2.5 Audio-to-Video Fast creates synchronized videos from short audio clips with optional image or prompt guidance for fast sound-led generation.

## API Information

- **Model Slug:** ltx-2-5-audio-to-video-fast
- **Branded URL:** https://www.eachlabs.ai/ltx/ltx-v2-5/ltx-2-5-audio-to-video-fast
- **Provider:** Lightricks
- **Category:** Voice to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** $0.13 per second
- **Estimated Processing Time:** 60 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/ltx-2-5-audio-to-video-fast

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.13 per second
- **Pricing Details:** default: $0.13

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| audio_url | string | Yes | - | - | URL of the audio file to generate a video from. Duration must be between 2 and 20 seconds. |
| image_url | string | No | - | - | Optional image URL to use as the first frame of the video. |
| prompt | string | No | - | - | Text description of how the video should be generated. Required when image_url is not provided. |
| aspect_ratio | string | No | auto | auto, 16:9, 9:16 | Aspect ratio of the generated video. |
| guidance_scale | number | No | - | 1–50 | Guidance scale for video generation. 1-50 |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx-2-5-audio-to-video-fast",
  "input": {
    "audio_url": "https://cdn-us.eachlabs.ai/defaults/24366f96094f41788a3b30763bbcf697.mp3"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Ltx v2.5 | Audio to Video | fast Overview**

**Ltx v2.5 | Audio to Video | fast** is an audio-driven video generation model from **LTX**, available on each::labs for creators who want synchronized visuals built from short audio clips. It turns sound into motion with optional image or prompt guidance, which makes it useful when timing, rhythm, or voice cues should shape the final clip. In LTX’s 2.5 family, the fast variant is positioned as the speed-focused option and supports audio-to-video generation at 1080p, with landscape and portrait outputs available through the API.

Compared with generic video generators, **Ltx v2.5 | Audio to Video | fast** stands out for native audio-video alignment, automatic duration handling, and support for higher-resolution output in the fast tier. LTX also describes the family as a model that can generate video and audio jointly, rather than adding sound as a separate post-process.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.