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

> Iħarreġ LoRA għall-ġenerazzjoni minn test għal awdjo li jitgħallem ħoss jew stil mill-klipps tal-awdjo tiegħek

Jirfina LoRA minn arkivju `.zip` mogħti f’`training_data_url` sabiex il-mudell ikun jista’ jiġġenera awdjo minn test. L-għażliet speċifiċi għall-awdjo jinkludu `audio_duration_seconds` (0.5 sa 60, default 5), `audio_normalize` u `audio_preserve_pitch`. It-taħriġ juża 2000 pass b’mod awtomatiku (100 sa 10000), b’`rank` minn 8 sa 128. Jirritorna l-fajl tal-piżijiet LoRA, fajl ta’ konfigurazzjoni u previews tal-validazzjoni.

- Model id: `ltx23-trainer-v2/t2a`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0022 / step (cheapest run $4.40 (4400 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/t2a`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/t2a`
- Docs page: https://doitong.com/mt/developers/models/ltx23-trainer-v2/t2a

## Pricing

Price: **$0.0022 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $4.40 = 4400 API credits (2000 steps × 2.2 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/t2a` 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 għal `.zip` li fih dejta tat-taħriġ, organizzata skont il-modalità tat-taħriġ magħżula. Kull fajl tal-midja jista' jkollu caption `.txt` akkumpanjata bl-istess isem bażi. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rank tal-adattament LoRA, li jiskambja konsum akbar tal-memorja għal kapaċità akbar hekk kif jiżdied l-issettjar. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Għadd totali ta' passi tat-taħriġ. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Rata tat-tagħlim tal-ottimizzazzjoni. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Għadd ta' frejms għal kull kampjun tat-taħriġ. Id-diviżjoni tal-għadd bi 8 trid tħalli fdal ta' 1; eżempji jinkludu 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Rata tal-frejms fil-mira tal-vidjo tat-taħriġ f'frejms kull sekonda. Ir-rata nattiva għal LTX-2.3 hija 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Riżoluzzjoni tat-taħriġ. Żieda fir-riżoluzzjoni żżid ir-rekwiżiti tal-memorja. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Proporzjon tal-aspett tat-taħriġ. |
| `trigger_phrase` |  | string | no | `` |  | Frażi ta' attivazzjoni tal-istil LoRA, imdaħħla fil-bidu tal-captions waqt it-taħriġ. |
| `auto_scale_input` |  | boolean | no | `false` |  | Aġġustament awtomatiku tal-vidjo biex jaqbel mal-FPS u mal-għadd ta' frejms mitlubin meta jkun attivat; datasets tal-immaġni jibqgħu mhux mibdulin. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Diviżjoni tax-xeni għal vidjos li jaqbżu limitu tat-tul, attivata meta tkun true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger tad-diviżjoni tax-xeni espress bħala tul f'sekondi: vidjos biss itwal mil-limitu jinqasmu. |
| `debug_dataset` |  | boolean | no | `false` |  | Modalità ta' spezzjoni tal-ipproċessar minn qabel għall-iċċekkjar tal-vidjos, l-immaġnijiet u l-captions qabel ġirja sħiħa tat-taħriġ. L-attivazzjoni tagħha tagħmel lit-trainer jirritorna d-dataset tat-taħriġ ipproċessat f'arkivju li jista' jitniżżel għal reviżjoni manwali. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalizzazzjoni tal-quċċati tal-awdjo biex jinżammu livelli konsistenti fid-dataset kollu. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Żamma tal-pitch waqt it-tqabbil tat-tul tal-awdjo, minflok qtugħ jew padding. |
| `audio_duration_seconds` |  | number | no | `5` | 0.5 – 60 | Bucket tat-tul tal-awdjo, speċifikat bħala tul fil-mira f'sekondi: klipps li jaqbżuh jinqatgħu biex joqogħdu, filwaqt li klipps li ma jistgħux jimlewh jinqabżu. |
| `validation` |  | array of object {prompt} | no | `[]` | ≤ 2 items | Lista ta' prompts ta' validazzjoni użata biex jiġi ġġenerat awdjo għal kull entrata. |
| `validation[].prompt` |  | string | yes |  |  | Prompt użat waqt il-validazzjoni. |
| `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.` |  | Prompt negattiv applikat waqt il-validazzjoni, li tuża proċess ta' preview bi stadju wieħed. Peress li dak il-proċess japprossima l-inferenza tal-produzzjoni distillata b'żewġ stadji, il-gwida u l-kwalità tal-preview tiegħu jvarjaw mir-riżultati finali. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Għadd ta' frejms għal kull vidjo ta' validazzjoni. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Rata tal-frejms fil-mira għall-vidjos ta' validazzjoni, f'frejms kull sekonda; LTX-2.3 jaħdem b'mod nattiv b'24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Riżoluzzjoni użata waqt il-validazzjoni. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Proporzjon tal-aspett użat waqt il-validazzjoni. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala ta' Spatio-Temporal Guidance (STG), b'1.0 rakkomandat u 0.0 jitfi STG. |

## 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/t2a?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/t2a?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/t2a", 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/t2a",
      "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/t2a",
  "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": 4400,
    "usd": "4.40",
    "charged": 4400,
    "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 | Preview kombinat tal-vidjo mill-validazzjoni, meta jkun disponibbli għal endpoints li jipproduċu vidjo. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Awdjo kombinat mill-validazzjoni, ipprovdut bħala preview meta jkun disponibbli għal dawn ir-rotot awdjo biss: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a, u /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL għal piżijiet LoRA mħarrġa f'format .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurazzjoni għas-setup tal-endpoint tal-inferenza. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Output ta' debug disponibbli meta `debug_dataset` ikun attivat: arkivju li jista' jitniżżel u fih id-dejta tat-taħriġ wara l-ipproċessar minn qabel. |

## 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) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / 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

## Links

- HTML page: https://doitong.com/developers/models/ltx23-trainer-v2/t2a
- 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/t2a
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/t2a