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

> Trener en LTX 2.3-LoRA som kobler et referanselydklipp til et mållydklipp fra sammenkoblede eksempler

Finjusterer en LoRA for lyd-til-lyd-transformasjon fra en `.zip` med sammenkoblede eksempler i `training_data_url`. `rank` er 8 til 128, `number_of_steps` 100 til 10000, og `audio_duration_seconds` 0.5 til 60. Scenedeling brukes ikke her, så du må sende inn forhåndsdelte klipp. Returnerer LoRA-vektene og en konfigurasjonsfil.

- 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/no/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 til en `.zip` som inneholder treningsdata organisert i henhold til valgt treningsmodus. Hver mediefil kan ha en tilhørende `.txt`-bildetekst med samme basisnavn. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-tilpasningsrangering, som bytter økt minnebruk mot større kapasitet når innstillingen økes. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Totalt antall treningstrinn. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Læringsrate for optimaliseringen. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Antall bilder i hvert treningseksempel. Når antallet deles på 8, må resten være 1; eksempler er 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Målhastighet for bilder per sekund i treningsvideoen. Den opprinnelige hastigheten for LTX-2.3 er 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Treningsoppløsning. Høyere oppløsning øker minnekravene. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Treningssideforhold. |
| `trigger_phrase` |  | string | no | `` |  | LoRA-stilens aktiveringsfrase, satt inn først i bildetekstene under trening. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatisk videojustering for å samsvare med forespurt FPS og antall bilder når aktivert; bildedatasett forblir uendret. |
| `split_input_into_scenes` |  | boolean | no | `false` |  | Kontroll for scenedeling, ignorert under forberedelse av sammenkoblede mål-/referanselydopptak for a2a fordi deling ville usynkronisere paret. Hold den av for a2a og lever klipp som allerede er delt. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Utløser for scenedeling uttrykt som en varighet i sekunder: bare videoer som er lengre enn terskelen, deles. |
| `debug_dataset` |  | boolean | no | `false` |  | Inspeksjonsmodus for forbehandling, for kontroll av videoer, bilder og bildetekster før en full treningskjøring. Når den aktiveres, returnerer treneren det behandlede treningsdatasettet i et nedlastbart arkiv for manuell gjennomgang. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalisering av lydtopper for å opprettholde jevne nivåer gjennom hele datasettet. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Bevaring av tonehøyde ved tilpasning av lydvarighet, i stedet for trimming eller utfylling. |
| `audio_duration_seconds` |  | number | no | `5` | 0.5 – 60 | Bøtte for lydvarighet i sekunder, påkrevd for lydmoduser fordi de mangler et videobildeantall å beregne lengden fra. Dette målet bestemmer klippbehandlingen: overskytende lyd trimmes, mens klipp som er for korte, hoppes over. |
| `validation` |  | array of object {prompt, reference_audio_url} | no | `[]` | ≤ 2 items | Liste over valideringsprompter der hver prompt kobles til et referanselydopptak. |
| `validation[].prompt` |  | string | yes |  |  | Prompt brukt under validering. |
| `validation[].reference_audio_url` |  | string (audio URL) | yes |  | ≥ 1 characters | URL til referanselyd brukt til å styre lydgenerering. |
| `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.` |  | Negativ prompt brukt under validering, som benytter en forhåndsvisningsprosess i ett trinn. Siden denne prosessen tilnærmer destillert produksjonsinferens med to trinn, skiller veiledningen og forhåndsvisningskvaliteten seg fra de endelige resultatene. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Antall bilder i hver valideringsvideo. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Målhastighet for valideringsvideoer, i bilder per sekund; LTX-2.3 kjører opprinnelig med 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Oppløsning brukt under validering. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Sideforhold brukt under validering. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Spatio-Temporal Guidance (STG)-skala, der 1.0 anbefales og 0.0 slår av 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 | Kombinert videoforhåndsvisning fra validering, når tilgjengelig for endepunkter som produserer video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Kombinert lyd fra validering, levert som forhåndsvisning når tilgjengelig for disse lydrutene: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a og /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL til trente LoRA-vekter i .safetensors-format. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfigurasjon for oppsett av inferensendepunkt. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Feilsøkingsutdata tilgjengelig når `debug_dataset` er aktivert: et arkiv som kan lastes ned og inneholder treningsdataene etter forbehandling. |

## 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