# LTX-2.3 22B Distilled · Audio to Video API

> Conversion audio-vidéo distillée avec intensités réglables du conditionnement audio, de la première image et de la dernière image

Nécessite une `prompt` et un `audio_url`. `audio_strength` (de 0 à 1) détermine si l'audio d'entrée est conservé tel quel ou peut être modifié, tandis que `image_strength` et `end_image_strength` contrôlent les images facultatives de première et de dernière image. Comprend `preprocess_audio`, une échelle LoRA de distillé en seconde passe et `num_frames` de 9 à 481.

- Model id: `ltx-2.3-22b/distilled/audio-to-video`
- Made by: Lightricks
- Category: Lipsync & Avatars
- Output: video
- Price per megapixel of your output video: $0.00121 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-22b/distilled/audio-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/distilled/audio-to-video`
- Docs page: https://doitong.com/fr-FR/developers/models/ltx-2.3-22b/distilled/audio-to-video

## Pricing

Price: **$0.00121 / megapixel of output video**. Price per megapixel of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.269 = 269 API credits (223 MP output video × $0.001205).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/distilled/audio-to-video` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Invite utilisée comme base pour la génération vidéo. |
| `audio_url` | `audio` | string (audio URL) | yes |  |  | URL de l’audio source utilisé pour générer la vidéo. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL d’image facultative définissant la première image de la vidéo. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | URL de l’image définissant la dernière image de la vidéo. |
| `match_audio_length` |  | boolean | no | `true` |  | Option de sélection du nombre d’images : désactivée, elle utilise `num_frames` ; activée, elle calcule le nombre à partir des FPS et de la durée de l’audio. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Nombre d’images de la sortie générée. |
| `video_size` |  | object {width, height} \| enum (string) | no | `landscape_16_9` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensions de la vidéo, avec une taille basée sur l’image d’entrée disponible via `'auto'` lorsqu’une image est fournie. |
| `use_multiscale` |  | boolean | no | `true` |  | Option de génération multi-échelle pour améliorer la cohérence et les détails. Avec `True`, une première vidéo plus petite guide une seconde génération dont la taille est supérieure ou égale aux dimensions demandées. |
| `fps` |  | number | no | `24` | 1 – 60 | Fréquence d’images de la vidéo de sortie, mesurée en images par seconde. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Sélection du scheduler. |
| `acceleration` |  | enum (string) | no | `none` | `none`, `regular`, `high`, `full` | Niveau d’accélération appliqué au traitement. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Sélection de la LoRA de caméra pour contrôler les mouvements de la vidéo générée plus précisément qu’avec les seules invites de mouvement de caméra. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Intensité de la LoRA de caméra pour contrôler les mouvements de la vidéo générée plus précisément qu’avec les seules invites de mouvement de caméra. |
| `negative_prompt` |  | string | no | `news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static` |  | Invite négative utilisée pendant la génération vidéo. |
| `seed` |  | integer \| null | no |  |  | Valeur de graine qui initialise la génération de nombres aléatoires. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Contrôle l’activation de l’expansion de l’invite. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Contrôle l'activation de la vérification de sécurité. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Type de sortie de la vidéo résultante. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Niveau de qualité de la vidéo résultante. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Mode d’écriture de la vidéo résultante. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Contrôle l’échelle de distillation LoRA pour chaque passe après la première. |
| `image_strength` |  | number | no | `1` | 0 – 1 | Influence de l’image sur la génération vidéo. |
| `end_image_strength` |  | number | no | `1` | 0 – 1 | Contrôle l’influence de l’image finale sur la vidéo générée. |
| `audio_strength` |  | number | no | `1` | 0 – 1 | Intensité du conditionnement audio, où exactement 1.0 conserve l’entrée inchangée. Le modèle peut modifier l’audio avec des valeurs inférieures à 1.0. |
| `preprocess_audio` |  | boolean | no | `true` |  | Contrôle le prétraitement de l’audio avant son utilisation pour le conditionnement. |

File parameters (`audio`, `image`, `end_image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/ltx-2.3-22b/distilled/audio-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx-2.3-22b/distilled/audio-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-22b/distilled/audio-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "ltx-2.3-22b/distilled/audio-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ltx-2.3-22b/distilled/audio-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 269,
    "usd": "0.269",
    "charged": 269,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "prompt": "A woman speaks to the camera"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames} | Vidéo produite par le modèle. |
| `seed` | integer | Valeur de seed utilisée pour initialiser la génération de nombres aléatoires. |
| `prompt` | string | Invite utilisée pour guider la génération. |

## Related models

- [LTX-2.3 22B Distilled · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video.md) (`ltx-2.3-22b/distilled/text-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/text-to-video/lora.md) (`ltx-2.3-22b/distilled/text-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video.md) (`ltx-2.3-22b/distilled/image-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/image-to-video/lora.md) (`ltx-2.3-22b/distilled/image-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/reference-video-to-video.md) (`ltx-2.3-22b/distilled/reference-video-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Reference Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/reference-video-to-video/lora.md) (`ltx-2.3-22b/distilled/reference-video-to-video/lora`): $0.00141 / megapixel of output video
- [LTX-2.3 22B Distilled · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video.md) (`ltx-2.3-22b/distilled/video-to-video`): $0.00121 / megapixel of output video
- [LTX-2.3 22B Distilled · Video to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/distilled/video-to-video/lora.md) (`ltx-2.3-22b/distilled/video-to-video/lora`): $0.00141 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-22b/distilled/audio-to-video
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=ltx-2.3-22b/distilled/audio-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-22b/distilled/audio-to-video