# Elevenlabs API

> 텍스트와 voice ID 쌍 목록을 여러 화자의 대화 오디오 트랙으로 변환

각 항목이 텍스트와 voice ID를 연결하는 필수 목록 `inputs`에서 대화 음성을 생성합니다. `stability`(0~1)와 `use_speaker_boost`로 음성 동작을 조정할 수 있습니다. `language_code`로 언어를 강제하고 최대 3개의 발음 사전 locator를 적용할 수 있습니다. 재현성을 위해 `seed`를 사용할 수 있으며 오디오와 함께 반환됩니다.

- Model id: `elevenlabs/text-to-dialogue/eleven-v3`
- Made by: ElevenLabs
- Category: Text to Speech
- Output: audio
- Estimated price per run: $0.10 / run (cheapest run $0.10 (100 API credits))
- Run: `POST https://api.doitong.ru/v1/run/elevenlabs/text-to-dialogue/eleven-v3`
- Quote: `POST https://api.doitong.ru/v1/quote/elevenlabs/text-to-dialogue/eleven-v3`
- Docs page: https://doitong.com/ko/developers/models/elevenlabs/text-to-dialogue/eleven-v3

## Pricing

Price: **$0.10 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.10 = 100 API credits (1 request × 100 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/elevenlabs/text-to-dialogue/eleven-v3` 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 |
|---|---|---|---|---|---|---|
| `inputs` |  | array of object {text, voice} | yes |  |  | 음성으로 합성할 대화 항목입니다. 각 항목은 텍스트와 음성 ID의 쌍으로 구성됩니다. |
| `inputs[].text` |  | string | yes |  |  | 대화가 포함된 텍스트입니다. |
| `inputs[].voice` |  | string | yes |  |  | 생성에 선택된 음성 이름 또는 ID입니다. |
| `stability` |  | number \| null | no |  | 0 – 1 | 생성 간 음성의 안정성과 변형 정도입니다. 0.0, 0.5 또는 1.0만 사용할 수 있으며, 이 범위를 벗어난 입력은 가장 가까운 허용 값으로 반올림됩니다. 설정이 높으면 감정 표현이 제한되고 단조롭게 들릴 수 있으며, 낮으면 음성의 감정 범위가 넓어집니다. |
| `use_speaker_boost` |  | boolean \| null | no |  |  | 계산 부하가 약간 증가하여 지연 시간이 늘어나는 화자 유사도 향상 기능입니다. 활성화하면 음성이 원래 화자와 더 비슷해집니다. |
| `pronunciation_dictionary_locators` |  | array of object {pronunciation_dictionary_id, version_id} | no | `[]` |  | 텍스트에 적용할 순서대로 최대 3개의 발음 사전 위치를 제공합니다. 각 위치는 id와 version_id로 사전을 식별합니다. |
| `pronunciation_dictionary_locators[].pronunciation_dictionary_id` |  | string \| null | no |  |  | 발음 사전의 식별자입니다. |
| `pronunciation_dictionary_locators[].version_id` |  | string \| null | no |  |  | ID로 특정 발음 사전 버전을 선택하거나, 최신 버전을 사용하려면 설정하지 않습니다. |
| `seed` |  | integer \| null | no |  |  | 재현 가능한 결과를 위해 무작위성을 제어하는 시드입니다. |
| `language_code` |  | string \| null | no |  |  | ISO 639-1 코드로 필요한 모델 언어를 지정합니다. 모델이 해당 코드를 지원하지 않으면 요청이 오류와 함께 실패합니다. |

## Example input

Required parameters only:

```json
{
  "inputs": [
    {
      "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
      "voice": "Aria"
    },
    {
      "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
      "voice": "Charlotte"
    }
  ]
}
```

A fuller example:

```json
{
  "inputs": [
    {
      "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
      "voice": "Aria"
    },
    {
      "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
      "voice": "Charlotte"
    }
  ]
}
```

## 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/elevenlabs/text-to-dialogue/eleven-v3?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      {
        "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
        "voice": "Aria"
      },
      {
        "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
        "voice": "Charlotte"
      }
    ]
  }'

# 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/elevenlabs/text-to-dialogue/eleven-v3?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "inputs": [
      {
        "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
        "voice": "Aria"
      },
      {
        "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
        "voice": "Charlotte"
      }
    ]
  }),
});
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 = {
    "inputs": [
        {
            "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
            "voice": "Aria",
        },
        {
            "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
            "voice": "Charlotte",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/elevenlabs/text-to-dialogue/eleven-v3", 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": "elevenlabs/text-to-dialogue/eleven-v3",
      "input": {
        "inputs": [
          {
            "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
            "voice": "Aria"
          },
          {
            "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
            "voice": "Charlotte"
          }
        ]
      },
      "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": "elevenlabs/text-to-dialogue/eleven-v3",
  "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": 100,
    "usd": "0.10",
    "charged": 100,
    "refunded": 0
  },
  "input": {
    "inputs": [
      {
        "text": "[applause] Thank you all for coming tonight! Today we have a very special guest with us.",
        "voice": "Aria"
      },
      {
        "text": "[gulps] ... [strong canadian accent] [excited] Hello everyone! Thank you all for having me tonight on this special day.",
        "voice": "Charlotte"
      }
    ]
  },
  "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
  },
  "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} | 생성된 오디오 파일입니다. |
| `seed` | integer | 재현 가능한 결과를 위해 무작위성을 제어하는 시드입니다. |

## Related models

- [Eleven v4 Text to Speech](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4.md) (`elevenlabs/tts/eleven-v4`): $0.08 / 1000 characters
- [MiniMax Speech 2.8 HD](https://doitong.com/developers/models/minimax/speech-2.8-hd.md) (`minimax/speech-2.8-hd`): $0.10 / 1000 characters
- [Eleven v4 Turbo](https://doitong.com/developers/models/elevenlabs/tts/eleven-v4-turbo.md) (`elevenlabs/tts/eleven-v4-turbo`): $0.04 / 1000 characters
- [Elevenlabs Tts Eleven V3](https://doitong.com/developers/models/elevenlabs/tts/eleven-v3.md) (`elevenlabs/tts/eleven-v3`): $0.10 / 1000 characters
- [ElevenLabs TTS Multilingual v2](https://doitong.com/developers/models/elevenlabs/tts/multilingual-v2.md) (`elevenlabs/tts/multilingual-v2`): $0.10 / 1000 characters
- [ElevenLabs TTS Turbo v2.5](https://doitong.com/developers/models/elevenlabs/tts/turbo-v2.5.md) (`elevenlabs/tts/turbo-v2.5`): $0.05 / 1000 characters
- [Async Text to Speech Pro V1.0](https://doitong.com/developers/models/async/tts-pro/v1.0.md) (`async/tts-pro/v1.0`): $0.01 / 1000 characters
- [Bytedance Seed Speech Text to Speech](https://doitong.com/developers/models/bytedance/seed-speech/tts/v2.md) (`bytedance/seed-speech/tts/v2`): $0.03 / 1000 characters

## Links

- HTML page: https://doitong.com/developers/models/elevenlabs/text-to-dialogue/eleven-v3
- 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=elevenlabs/text-to-dialogue/eleven-v3
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/elevenlabs/text-to-dialogue/eleven-v3