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

> Trenira LoRA za generiranje zvuka iz teksta koja iz vaših zvučnih isječaka uči zvuk ili stil

Dodatno trenira LoRA iz `.zip` arhive navedene u `training_data_url` kako bi model mogao generirati zvuk iz teksta. Opcije specifične za zvuk uključuju `audio_duration_seconds` (0.5 do 60, zadano 5), `audio_normalize` i `audio_preserve_pitch`. Treniranje prema zadanim postavkama traje 2000 koraka (100 do 10000), uz `rank` od 8 do 128. Vraća datoteku težina LoRA, konfiguracijsku datoteku i validacijske pretpreglede.

- 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/hr/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 datoteke `.zip` koja sadrži podatke za obuku, organizirane prema odabranom načinu obuke. Uz svaku medijsku datoteku može biti priložen opis `.txt` s odgovarajućim osnovnim nazivom. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rang LoRA prilagodbe, pri čemu veća postavka povećava kapacitet uz veću potrošnju memorije. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Ukupan broj koraka obuke. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Stopa učenja optimizacije. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Broj sličica za svaki uzorak obuke. Dijeljenjem broja s 8 ostatak mora biti 1; primjeri uključuju 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Ciljna brzina sličica videozapisa za obuku u sličicama u sekundi. Izvorna brzina za LTX-2.3 iznosi 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Razlučivost obuke. Povećanje razlučivosti povećava zahtjeve za memorijom. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Omjer stranica obuke. |
| `trigger_phrase` |  | string | no | `` |  | Izraz za aktivaciju LoRA stila, umetnut na početak opisa tijekom obuke. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatsko prilagođavanje videa traženom FPS-u i broju sličica kada je omogućeno; skupovi podataka slika ostaju nepromijenjeni. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Dijeljenje scena za videozapise koji premašuju prag trajanja, omogućeno kada je true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Okidač dijeljenja scena izražen trajanjem u sekundama: dijele se samo videozapisi dulji od praga. |
| `debug_dataset` |  | boolean | no | `false` |  | Način pregleda pretprocesiranja za provjeru videozapisa, slika i opisa prije potpunog pokretanja obuke. Njegovim omogućivanjem alat za obuku vraća obrađeni skup podataka za obuku u arhivi dostupnoj za preuzimanje radi ručnog pregleda. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalizacija vršnih vrijednosti audija radi održavanja ujednačenih razina kroz cijeli skup podataka. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Očuvanje visine tona tijekom prilagođavanja trajanja audija, umjesto obrezivanja ili dodavanja tišine. |
| `audio_duration_seconds` |  | number | no | `5` | 0.5 – 60 | Spremnik trajanja audija, naveden kao ciljna duljina u sekundama: isječci koji je premašuju obrezuju se radi uklapanja, a isječci koji je ne mogu ispuniti preskaču se. |
| `validation` |  | array of object {prompt} | no | `[]` | ≤ 2 items | Popis promptova za provjeru koji se koristi za generiranje audia za svaki unos. |
| `validation[].prompt` |  | string | yes |  |  | Prompt koji se upotrebljava tijekom provjere. |
| `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.` |  | Negativni prompt primijenjen tijekom provjere, koja upotrebljava proces pregleda u jednoj fazi. Budući da taj proces približno oponaša destilirano produkcijsko zaključivanje u dvije faze, njegovo usmjeravanje i kvaliteta pregleda razlikuju se od konačnih rezultata. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Broj sličica za svaki video za provjeru. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Ciljna brzina sličica za videozapise provjere, u sličicama u sekundi; LTX-2.3 izvorno radi pri 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Razlučivost koja se upotrebljava tijekom provjere. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Omjer stranica koji se upotrebljava tijekom provjere. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala prostorno-vremenskog usmjeravanja (STG), pri čemu se preporučuje 1.0, a 0.0 isključuje 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 | Kombinirani pregled videa iz provjere, kada je dostupan za krajnje točke koje proizvode video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Kombinirani audio iz provjere, dostupan kao pregled za ove rute samo s audiom: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a i /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL LoRA težina za obuku u formatu .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguracija postavljanja krajnje točke za zaključivanje. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Otklanjanje pogrešaka dostupno kada je omogućeno `debug_dataset`: arhiva koja se može preuzeti i sadrži podatke za obuku nakon pretprocesiranja. |

## 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