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

> 训练 LTX 2.3 LoRA，根据起始图像和条件音频生成视频

根据 `training_data_url` 中的 `.zip` 训练用于音频转视频生成的 LoRA。`rank` 为 8 到 128，`number_of_steps` 为 100 到 10000，`number_of_frames` 为 9 到 121。`validation` 最多接受 2 个条目，每个条目包含条件音轨。输出 LoRA 权重、配置文件和可选预览。

- Model id: `ltx23-trainer-v2/a2v`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.006 / step (cheapest run $12.00 (12000 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/a2v`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/a2v`
- Docs page: https://doitong.com/zh/developers/models/ltx23-trainer-v2/a2v

## Pricing

Price: **$0.006 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $12.00 = 12000 API credits (2000 steps × 6 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/a2v` 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 |  |  | 包含训练数据的 `.zip` URL，数据按所选训练模式组织。每个媒体文件可以附带一个同名的 `.txt` 字幕文件。 |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA 适配秩；该值越高，容量越大，但内存消耗也越高。 |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | 训练步数总数。 |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | 优化学习率。 |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | 每个训练样本的帧数。将该数量除以 8 必须余 1；示例包括 1、9、17、25、33、41、49、57、65、73、81、89、97。 |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | 训练视频的目标帧率，以每秒帧数为单位。LTX-2.3 的原生帧率为 24。 |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | 训练分辨率。提高分辨率会增加内存需求。 |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | 训练宽高比。 |
| `trigger_phrase` |  | string | no | `` |  | LoRA 样式激活短语，训练期间插入字幕开头。 |
| `auto_scale_input` |  | boolean | no | `false` |  | 启用后自动调整视频，以匹配请求的 FPS 和帧数；图像数据集保持不变。 |
| `split_input_into_scenes` |  | boolean | no | `false` |  | 拆分超过时长阈值的合成训练视频场景。为 true 时，会在组合起始图像和音频后进行拆分。 |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | 以秒数表示的场景拆分触发阈值：只有超过该时长的视频才会被拆分。 |
| `debug_dataset` |  | boolean | no | `false` |  | 用于在完整训练运行前检查视频、图像和字幕的预处理检查模式。启用后，训练器会将处理后的训练数据集返回为可下载存档，以便手动检查。 |
| `audio_normalize` |  | boolean | no | `true` |  | 条件音频峰值归一化，用于保持整个数据集的音量一致。 |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | 调整音频以匹配视频长度时保留音高，而不是裁剪或填充。 |
| `validation` |  | array of object {prompt, image_url, audio_url} | no | `[]` | ≤ 2 items | 验证提示词列表，每个提示词与一个条件音频轨道配对。 |
| `validation[].prompt` |  | string | yes |  |  | 验证期间使用的提示词。 |
| `validation[].image_url` |  | string (image URL) | yes |  | ≥ 1 characters | 图像 URL，a2v 会直接将其用作第一帧，而不是生成该帧。a2v 图像+音频 -> 视频流程会同时使用所提供的音频和该图像作为条件。 |
| `validation[].audio_url` |  | string (audio URL) | yes |  | ≥ 1 characters | 用于驱动视频生成的条件音频 URL。 |
| `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.` |  | 验证期间应用的负面提示词，验证使用单阶段预览流程。由于该流程近似于两阶段的蒸馏生产推理，其引导方式和预览质量与最终结果不同。 |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | 每个验证视频的帧数。 |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | 验证视频的目标帧率，以每秒帧数为单位；LTX-2.3 的原生帧率为 24。 |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | 验证期间使用的分辨率。 |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | 验证期间使用的宽高比。 |
| `stg_scale` |  | number | no | `1` | 0 – 3 | 时空引导（STG）缩放，建议使用 1.0，使用 0.0 可关闭 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/a2v?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/a2v?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/a2v", 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/a2v",
      "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/a2v",
  "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": 12000,
    "usd": "12.00",
    "charged": 12000,
    "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 | 验证生成的合并视频预览；适用于可用的视频生成端点。 |
| `audio` | object {url, content_type, file_name, file_size} \| null | 验证生成的合并音频；适用于以下音频专用路由时会作为预览提供：/audio-inpaint、/audio-extend-suffix、/audio-extend-prefix、/t2a、/a2a 和 /v2a。 |
| `lora_file` | object {url, content_type, file_name, file_size} | 采用 .safetensors 格式的已训练 LoRA 权重 URL。 |
| `config_file` | object {url, content_type, file_name, file_size} | 推理端点设置的配置。 |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | 启用 `debug_dataset` 后可用的调试输出：一个可下载的存档，其中包含预处理后的训练数据。 |

## 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) - 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/a2v
- 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/a2v
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/a2v