# Ltx 2.3 Quality · Text to Audio · LoRA API

> Tekst-til-lyd-generering med opptil 3 egendefinerte LoRA-er

Genererer lyd fra en tekstlig `prompt` og krever en `loras`-liste med opptil 3 egendefinerte LoRA-er, hver på opptil 3 GB. Varigheten er omtrent `num_frames` delt på `frames_per_second`, med `num_frames` mellom 9 og 481. Godtar også `negative_prompt`, `seed` og `guidance_scale` fra 1 til 20.

- Model id: `ltx-2.3-quality/text-to-audio/lora`
- Made by: Lightricks
- Category: Audio
- Output: audio
- Estimated price per run: from $0.70 / run (cheapest run $0.70 (700 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-quality/text-to-audio/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-quality/text-to-audio/lora`
- Docs page: https://doitong.com/no/developers/models/ltx-2.3-quality/text-to-audio/lora

## Pricing

Price: **from $0.70 / run** (the lowest tier; the quote prices your exact input). Estimated from the typical cost of one run. The quote is exactly what the run charges.

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `num_frames` > 363: base price × 4
- When `num_frames` ≤ 363: base price × 3
- When `num_frames` ≤ 242: base price × 2

The full example input below costs $0.70 = 700 API credits (1 request × 700 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.ru/v1/quote/ltx-2.3-quality/text-to-audio/lora` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt som beskriver lyden som skal genereres. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Lydvarighet angitt som et antall LTX-videobilder; del `num_frames` på `frames_per_second` for å få omtrentlig lengde i sekunder. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Bildehastighet som brukes til å beregne varigheten til lydutdataene. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Totalt antall inferenssteg. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Styrken til klassifikatorfri veiledning. |
| `negative_prompt` |  | string | no | `pc game, console game, video game, cartoon, childish, ugly` |  | Negativ prompt som angir hva genereringen skal unngå. |
| `seed` |  | integer \| null | no |  |  | Seed som gjør genereringen reproduserbar. Hvis den settes til None, velges en seed tilfeldig. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Styrer om promptutvidelse er aktivert. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Styrer om sikkerhetskontroll er aktivert. |
| `loras` |  | array of object {path, scale, transformer} | yes |  | ≤ 3 items | LoRA-tillegg for LTX-2.3, hvert begrenset til 3 GB, med maksimalt 3 tillatte oppføringer. Innlasting skjer først etter at registerets SSRF-sikre nedlaster har hentet hver bane. |
| `loras[].path` |  | string | yes |  | ≤ 2048 characters | Direkte HTTP(S)-URL til en LoRA .safetensors-fil på maksimalt 3 GB. Innlasting innledes med henting via en SSRF-sikker nedlaster. |
| `loras[].scale` |  | number | no | `1` | 0 – 2 | LoRA-påvirkningen på den genererte videoen øker når denne styrken økes innenfor området 0.0–2.0. |
| `loras[].transformer` |  | enum (string) | no | `both` | `high`, `low`, `both` | Flagg for valg av transformer: 'both' passer nesten alle som bruker LTX-2.3, fordi modellen bare har én transformer. Flagget finnes for å støtte fremtidige arkitekturer med flere transformere. |

## Example input

Required parameters only:

```json
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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.ru/v1/run/ltx-2.3-quality/text-to-audio/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/ltx-2.3-quality/text-to-audio/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "loras": [
        {
            "path": "https://example.com/your-file.safetensors",
        },
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-quality/text-to-audio/lora", 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.ru/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": "ltx-2.3-quality/text-to-audio/lora",
      "input": {
        "loras": [
          {
            "path": "https://example.com/your-file.safetensors"
          }
        ],
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "ltx-2.3-quality/text-to-audio/lora",
  "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": 700,
    "usd": "0.70",
    "charged": 700,
    "refunded": 0
  },
  "input": {
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | Lyd produsert av modellen. |
| `seed` | integer | Faktisk seed som brukes under genereringen. |
| `prompt` | string | Genereringsprompt, inkludert eventuell utvidelse som er brukt før den tas i bruk. |

## Related models

- [Ltx 2.3 Quality · Text to Video](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video.md) (`ltx-2.3-quality/text-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video/lora.md) (`ltx-2.3-quality/text-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video.md) (`ltx-2.3-quality/image-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video/lora.md) (`ltx-2.3-quality/image-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Ingredient](https://doitong.com/developers/models/ltx-2.3-quality/ingredient.md) (`ltx-2.3-quality/ingredient`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md) (`ltx-2.3-quality/clean-plate`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md) (`ltx-2.3-quality/colorization`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md) (`ltx-2.3-quality/cross-eyed`): $0.00241 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-quality/text-to-audio/lora
- 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=ltx-2.3-quality/text-to-audio/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-quality/text-to-audio/lora