# LTX 2.3 Trainer (V2) - Audio-to-Video API

> Trainéiert eng LTX 2.3 LoRA, déi aus engem Startbild a Bedéngungsaudio e Video erstellt

Trainéiert eng LoRA fir Audio-zu-Video-Generatioun aus engem `.zip` an `training_data_url`. `rank` ass 8 bis 128, `number_of_steps` 100 bis 10000, an `number_of_frames` 9 bis 121. `validation` akzeptéiert bis zu 2 Entréen, all mat enger Bedéngungs-Audiostreck. D'Outputen sinn d'LoRA-Gewiichter, d'Konfiguratiounsdatei an eng optional Preview.

- Model id: `ltx23-trainer-v2/a2v`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.006 / step (cheapest run $12.00 (12000 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/a2v`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/a2v`
- Docs page: https://doitong.com/lb/developers/models/ltx23-trainer-v2/a2v

## Pricing

Price: **$0.006 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $12.00 = 12000 API credits (2000 steps × 6 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/a2v` 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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | URL op e `.zip` mat Trainingsdaten, organiséiert no dem ausgewielten Trainingsmodus. All Medien-Datei kann eng zousätzlech `.txt`-Caption mat passendem Basisnumm hunn. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-Adaptatiounsrang, bei deem méi héije Wäerter méi Kapazitéit géint méi héije Memoryverbrauch ofwiichten. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Gesamtzuel vun Trainingsschrëtt. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Léierquote fir d'Optimiséierung. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Framezuel pro Trainingssample. D'Deelung vun der Zuel duerch 8 muss e Rescht vun 1 loossen; Beispiller sinn 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Zil-Frame-Rate vum Trainingsvideo a Frames pro Sekonn. Déi native Rate fir LTX-2.3 ass 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Trainingsopléisung. Eng Erhéijung vun der Opléisung erhéicht d'Memoryufuerderungen. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Trainingsaspektverhältnis. |
| `trigger_phrase` |  | string | no | `` |  | LoRA-Stil-Aktivéierungsphrase, déi beim Training um Ufank vun de Captions agefouert gëtt. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatesch Videoanpassung un déi ugefrote FPS- a Framezuel beim Aktivéiere; Bilddatensätz bleiwen onverännert. |
| `split_input_into_scenes` |  | boolean | no | `false` |  | Szenendeelung fir synthetiséiert Trainingsvideoen, déi de Schwellwäert vun der Dauer iwwerschreiden. Wann true, geschitt d'Deelung no der Zesummesetzung vum Startbild an Audio. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger fir d'Szenendeelung als Dauer a Sekonnen: nëmme Videoe méi laang wéi de Schwellwäert ginn gedeelt. |
| `debug_dataset` |  | boolean | no | `false` |  | Inspektiounsmodus vun der Virveraarbechtung fir Videoen, Biller a Captions virun engem kompletten Training ze kontrolléieren. Beim Aktivéiere gëtt den veraarbechten Trainingsdatensaz an engem erofluedbaren Archiv fir d'manuell Iwwerpréiwung zeréckginn. |
| `audio_normalize` |  | boolean | no | `true` |  | Peak-Normaliséierung vum Conditioning-Audio, fir konsequent Niveauen iwwer den ganzen Datensaz ze behalen. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Erhale vun der Tonhéicht beim Upasse vum Audio un d'Videolängt amplaz en ofzeschneiden oder opzefëllen. |
| `validation` |  | array of object {prompt, image_url, audio_url} | no | `[]` | ≤ 2 items | Lëscht vu Validatiouns-Prompts, bei där all Prompt mat engem Conditioning-Audio-Track gepaart gëtt. |
| `validation[].prompt` |  | string | yes |  |  | Prompt, dee während der Validatioun benotzt gëtt. |
| `validation[].image_url` |  | string (image URL) | yes |  | ≥ 1 characters | URL vun engem Bild, dat a2v direkt als éischte Frame benotzt, amplaz dëse Frame ze generéieren. Den a2v-Bild+Audio -> Video-Prozess benotzt souwuel de geliwwerten Audio wéi dëst Bild als Conditioning. |
| `validation[].audio_url` |  | string (audio URL) | yes |  | ≥ 1 characters | Conditioning-Audio-URL, déi d'Videogeneratioun steiert. |
| `validation_negative_prompt` |  | string | no | `blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.` |  | Negative Prompt während der Validatioun, déi en einstufege Virschauprozess benotzt. Well dëse Prozess d'distilléiert Produktiounsinferenz mat zwou Stufen approximéiert, ënnerscheede sech seng Guidance an d'Virschauqualitéit vun de Schlussresultater. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Framezuel fir all Validatiounsvideo. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Zil-Frame-Rate fir Validatiounsvideoen a Frames pro Sekonn; LTX-2.3 leeft nativ mat 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Opléisung, déi während der Validatioun benotzt gëtt. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Aspektverhältnis, dat während der Validatioun benotzt gëtt. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Spatio-Temporal-Guidance-(STG)-Skala, mat 1.0 recommandéiert an 0.0 fir STG auszeschalten. |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

## 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.com/v1/run/ltx23-trainer-v2/a2v?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.com/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/ltx23-trainer-v2/a2v?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx23-trainer-v2/a2v", 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.com/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": "ltx23-trainer-v2/a2v",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "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": "ltx23-trainer-v2/a2v",
  "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": 12000,
    "usd": "12.00",
    "charged": 12000,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "debug_dataset": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} \| null | Kombinéiert Video-Virschau aus der Validatioun, wa verfügbar fir Endpunkten, déi Video produzéieren. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Kombinéierten Audio aus der Validatioun, als Virschau geliwwert, wa verfügbar fir dës Audio-only-Routen: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a an /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL fir trainéiert LoRA-Gewiichter am .safetensors-Format. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguratioun fir d'Ariichtung vum Inferenz-Endpunkts. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Debug-Output, verfügbar wann `debug_dataset` aktivéiert ass: en erofluedbart Archiv mat den Trainingsdaten no der Virveraarbechtung. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step
- [LTX 2.3 Trainer (V2) - Forward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-prefix.md) (`ltx23-trainer-v2/audio-extend-prefix`): $0.0022 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-trainer-v2/a2v
- 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=ltx23-trainer-v2/a2v
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/a2v