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

> Apmāca LTX 2.3 LoRA, kas no pāru piemēriem kartē atsauces audio klipu uz mērķa audio klipu

Precizē LoRA audio pārveidei audio, izmantojot pāru piemēru `.zip` failu laukā `training_data_url`. `rank` ir no 8 līdz 128, `number_of_steps` — no 100 līdz 10000, bet `audio_duration_seconds` — no 0.5 līdz 60. Šeit ainu sadalīšana netiek izmantota, tāpēc jāiesniedz jau sadalīti klipi. Tiek atgriezti LoRA svari un konfigurācijas fails.

- Model id: `ltx23-trainer-v2/a2a`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0023 / step (cheapest run $4.60 (4600 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/a2a`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/a2a`
- Docs page: https://doitong.com/lv/developers/models/ltx23-trainer-v2/a2a

## Pricing

Price: **$0.0023 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $4.60 = 4600 API credits (2000 steps × 2.3 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/a2a` 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 uz `.zip` failu ar apmācības datiem, kas sakārtoti atbilstoši atlasītajam apmācības režīmam. Katram multivides failam var būt pievienots `.txt` apraksts ar atbilstošu pamatnosaukumu. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA adaptācijas rangs: lielāka vērtība palielina kapacitāti, taču arī atmiņas patēriņu. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Kopējais apmācības soļu skaits. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Optimizācijas mācīšanās ātrums. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Kadru skaits katrā apmācības paraugā. Dalot šo skaitu ar 8, atlikumam jābūt 1; piemēri: 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Apmācības video mērķa kadru ātrums kadros sekundē. LTX-2.3 pamata kadru ātrums ir 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Apmācības izšķirtspēja. Lielāka izšķirtspēja palielina atmiņas prasības. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Apmācības malu attiecība. |
| `trigger_phrase` |  | string | no | `` |  | LoRA stila aktivizēšanas frāze, kas apmācības laikā tiek ievietota aprakstu sākumā. |
| `auto_scale_input` |  | boolean | no | `false` |  | Ja iespējots, automātiski pielāgo video pieprasītajam FPS un kadru skaitam; attēlu datu kopas paliek nemainītas. |
| `split_input_into_scenes` |  | boolean | no | `false` |  | Ainu sadalīšanas iestatījums, kas tiek ignorēts, sagatavojot pārī savienotu mērķa un atsauces audio režīmam a2a, jo sadalīšana izjauktu pāra sinhronizāciju. Režīmā a2a atstājiet to izslēgtu un nodrošiniet iepriekš sadalītus klipus. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Ainu sadalīšanas slieksnis, kas izteikts kā ilgums sekundēs: tiek sadalīti tikai video, kas ir garāki par slieksni. |
| `debug_dataset` |  | boolean | no | `false` |  | Priekšapstrādes pārbaudes režīms video, attēlu un aprakstu pārbaudei pirms pilna apmācības cikla. Ja iespējots, apmācības rīks atgriež apstrādāto apmācības datu kopu lejupielādējamā arhīvā manuālai pārbaudei. |
| `audio_normalize` |  | boolean | no | `true` |  | Audio maksimumlīmeņa normalizēšana, lai uzturētu vienādus līmeņus visā datu kopā. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Skaņas augstuma saglabāšana, pielāgojot audio ilgumu, nevis to apgriežot vai papildinot. |
| `audio_duration_seconds` |  | number | no | `5` | 0.5 – 60 | Audio ilguma grupa sekundēs; obligāta tikai audio režīmiem, jo tiem nav video kadru skaita, no kura aprēķināt garumu. Šī mērķvērtība nosaka klipu apstrādi: liekais audio tiek apgriezts, bet pārāk īsi klipi tiek izlaisti. |
| `validation` |  | array of object {prompt, reference_audio_url} | no | `[]` | ≤ 2 items | Validācijas uzvedņu saraksts, kurā katrai uzvednei ir piesaistīts atsauces audio klips. |
| `validation[].prompt` |  | string | yes |  |  | Validācijā izmantotā uzvedne. |
| `validation[].reference_audio_url` |  | string (audio URL) | yes |  | ≥ 1 characters | Atsauces audio URL, ko izmanto kā nosacījumu audio ģenerēšanai. |
| `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.` |  | Negatīvā uzvedne, ko piemēro validācijā, izmantojot vienposma priekšskatījuma procesu. Tā kā šis process aptuveni atdarina destilētu divposmu inferenci produkcijas vidē, tā vadība un priekšskatījuma kvalitāte atšķiras no gala rezultātiem. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Kadru skaits katrā validācijas video. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Validācijas video mērķa kadru ātrums kadros sekundē; LTX-2.3 pamata kadru ātrums ir 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Validācijā izmantotā izšķirtspēja. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Validācijā izmantotā malu attiecība. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Telpiskās un laika vadības (STG) mērogs; ieteicams 1.0, savukārt 0.0 izslēdz 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/a2a?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/a2a?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/a2a", 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/a2a",
      "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/a2a",
  "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": 4600,
    "usd": "4.60",
    "charged": 4600,
    "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 | Apvienots validācijas video priekšskatījums, ja tas ir pieejams galapunktiem, kas veido video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Apvienots validācijas audio, kas tiek nodrošināts kā priekšskatījums, ja pieejams šiem tikai audio maršrutiem: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a un /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | Apmācīto LoRA svaru URL .safetensors formātā. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurācija inferenču galapunkta iestatīšanai. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Atkļūdošanas izvade, kas pieejama, ja ir iespējots `debug_dataset`: lejupielādējams arhīvs ar apmācības datiem pēc priekšapstrādes. |

## 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 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
- [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/a2a
- 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/a2a
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/a2a