> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ekly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LTX Video 2.3 Audio-to-Video

> Generate video driven by an audio clip (2-20s) with LTX-2.3 — lip-sync and motion follow the sound.

Generate video driven by an audio clip (2-20s) with LTX-2.3 — lip-sync and motion follow the sound. Optionally condition on a starting image.

| | |
| - | - |
| Model id | `ltx-2.3-audio-fal` |
| Media | video |
| Submit to | `POST /v1/videos` |
| Price | 80 credits per\_generation before discounts |
| Typical time | about 60.0 s |

## Request

**Required:** `prompt`, `audio`\
**Optional:** `aspect_ratio`, `first_frame`

```json theme={null}
{
  "model": "ltx-2.3-audio-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "aspect_ratio": "auto",
  "audio": "asset_…"
}
```

| Field | Allowed | Default |
| - | - | - |
| `aspect_ratio` | `auto`, `16:9`, `9:16` | `"auto"` |
| `audio` | asset id (up to 1) | |
| `first_frame` | asset id (up to 1) | |

Reference inputs take asset ids from [`POST /v1/uploads`](/uploads) or an earlier output's `asset_id`.
Prices and allowed values come from the live catalog; `GET /v1/models/ltx-2.3-audio-fal` is always current.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.