# Ltx 2.3 Quality · Audio to Video · LoRA API

> Vidéo guidée par l’audio avec première image facultative et jusqu’à 3 LoRAs personnalisées pour le style ou l’identité

Même flux audio-vidéo que la variante de base, avec une liste `loras` obligatoire contenant jusqu’à 3 LoRAs personnalisées appliquées au modèle. Un `prompt` textuel et `audio_url` sont requis, et `image_url` peut facultativement définir la première image. `match_audio_length` lie le nombre d’images à la durée audio; sinon, utilisez `num_frames` (9 à 481). Chaque LoRA est limitée à 3 GB.

- Model id: `ltx-2.3-quality/audio-to-video/lora`
- Made by: Lightricks
- Category: Lipsync & Avatars
- Output: video
- Price per megapixel of your output video: $0.00271 / megapixel of output video (cheapest run $0.003 (3 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-quality/audio-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/audio-to-video/lora`
- Docs page: https://doitong.com/fr-CA/developers/models/ltx-2.3-quality/audio-to-video/lora

## Pricing

Price: **$0.00271 / 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 $0.604 = 604 API credits (223 MP output video × $0.002708).

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-quality/audio-to-video/lora` 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 guidant la génération vidéo pilotée par l’audio. |
| `audio_url` | `audio` | string (audio URL) | yes |  |  | URL de la piste audio utilisée pour piloter la génération. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Image de la première image fournie par URL pour compléter une génération qui utilise autrement uniquement le texte et l’audio; sa fourniture est facultative. |
| `match_audio_length` |  | boolean | no | `true` |  | Mode de nombre d’images qui utilise `num_frames` lorsqu’il est désactivé. Lorsqu’il est activé, le nombre est calculé à partir de `frames_per_second` et de la durée de l’audio. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Nombre d’images de la sortie générée. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensions finales de sortie, avec un format paysage pour 'auto' sauf si `image_url` est fourni. Avec cette image, 'auto' adopte son format. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Fréquence d’images de la vidéo de sortie, mesurée en images par seconde. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Définissez le nombre de pas d’inférence à exécuter, jusqu’à 30; si vous ne le modifiez pas, 15 pas sont utilisés. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Ajustez le guidage sans classificateur à l’aide de cette échelle; son réglage par défaut vise à la fois une qualité élevée et une génération rapide. |
| `generate_audio` |  | boolean | no | `true` |  | Interrupteur de la piste audio du MP4 retourné : désactivé, il produit un fichier vidéo seulement; activé, il inclut l’audio. |
| `image_strength` |  | number | no | `0.7` | 0 – 1 | Intensité facultative du conditionnement de la première image : réduisez-la pour accorder davantage de liberté au modèle ou utilisez 1.0 pour une adhérence plus stricte à l’image. |
| `negative_prompt` |  | string | no | `color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards` |  | Invite négative indiquant ce que la génération doit éviter. |
| `seed` |  | integer \| null | no |  |  | Graine qui rend la génération reproductible. La définir sur None sélectionne une graine aléatoirement. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Contrôle l’activation de l’expansion de l’invite. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Contrôle si la vérification de sécurité est activée. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Préréglage de qualité appliqué à la vidéo de sortie. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Mode d’écriture de la vidéo résultante. |
| `loras` |  | array of object {path, scale, transformer} | yes |  | ≤ 3 items | Ajouts LoRA pour LTX-2.3, limités à 3 GB chacun, avec au plus 3 entrées autorisées. Le chargement a lieu uniquement après que le téléchargeur sécurisé contre les SSRF du registre a récupéré chaque chemin. |
| `loras[].path` |  | string | yes |  | ≤ 2048 characters | URL HTTP(S) directe vers un fichier LoRA .safetensors d’au plus 3 GB. Le chargement est précédé d’une récupération au moyen d’un téléchargeur sécurisé contre les SSRF. |
| `loras[].scale` |  | number | no | `1` | 0 – 2 | L’influence de la LoRA sur la vidéo générée augmente avec cette intensité dans la plage 0.0–2.0. |
| `loras[].transformer` |  | enum (string) | no | `both` | `high`, `low`, `both` | Indicateur de sélection du transformeur : 'both' convient à presque tous les utilisateurs de LTX-2.3, car le modèle ne possède qu’un seul transformeur. L’indicateur existe pour prendre en charge les futures architectures comportant plusieurs transformeurs. |

File parameters (`audio`, `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
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "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
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "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-quality/audio-to-video/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "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-quality/audio-to-video/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "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 = {
    "loras": [
        {
            "path": "https://example.com/your-file.safetensors",
        },
    ],
    "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-quality/audio-to-video/lora", 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-quality/audio-to-video/lora",
      "input": {
        "loras": [
          {
            "path": "https://example.com/your-file.safetensors"
          }
        ],
        "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-quality/audio-to-video/lora",
  "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": 604,
    "usd": "0.604",
    "charged": 604,
    "refunded": 0
  },
  "input": {
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "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
    },
    "seed": 42,
    "prompt": "string"
  },
  "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} | Vidéo produite par le modèle. |
| `seed` | integer | Valeur de départ réellement appliquée pendant la génération. |
| `prompt` | string | Invite de génération, y compris toute expansion appliquée avant son utilisation. |

## Related models

- [Ltx 2.3 Quality · Text to Video](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video.md) (`ltx-2.3-quality/text-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video/lora.md) (`ltx-2.3-quality/text-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video.md) (`ltx-2.3-quality/image-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video/lora.md) (`ltx-2.3-quality/image-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Ingredient](https://doitong.com/developers/models/ltx-2.3-quality/ingredient.md) (`ltx-2.3-quality/ingredient`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md) (`ltx-2.3-quality/clean-plate`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md) (`ltx-2.3-quality/colorization`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md) (`ltx-2.3-quality/cross-eyed`): $0.00241 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-quality/audio-to-video/lora
- 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-quality/audio-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-quality/audio-to-video/lora