# CSM-1B API

> Mô hình chuyển văn bản thành giọng nói hội thoại, nhận một cảnh gồm các câu thoại cùng ngữ cảnh âm thanh tùy chọn

Tạo lời nói từ `scene` bắt buộc, là mảng các đối tượng chứa văn bản cần đọc. Mảng `context` tùy chọn cung cấp các lượt hội thoại trước đó để định hình cách thể hiện. Kết quả là một đầu ra âm thanh duy nhất. Được thiết kế cho lời thoại dạng hội thoại.

- Model id: `csm-1b`
- Made by: Sesame
- Category: Text to Speech
- Output: audio
- Estimated price per run: $0.03 / run (cheapest run $0.03 (30 API credits))
- Run: `POST https://api.doitong.com/v1/run/csm-1b`
- Quote: `POST https://api.doitong.com/v1/quote/csm-1b`
- Docs page: https://doitong.com/vi/developers/models/csm-1b

## Pricing

Price: **$0.03 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.03 = 30 API credits (1 request × 30 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/csm-1b` 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 |
|---|---|---|---|---|---|---|
| `scene` |  | array of object {speaker_id, text} | yes |  |  | Văn bản nguồn để tạo sinh âm thanh. |
| `scene[].speaker_id` |  | integer | yes |  |  |  |
| `scene[].text` |  | string | yes |  |  |  |
| `context` |  | array of object {prompt, speaker_id, audio_url} | no |  |  | Ngữ cảnh nguồn để tạo sinh âm thanh. |
| `context[].prompt` |  | string | yes |  |  |  |
| `context[].speaker_id` |  | integer | yes |  |  |  |
| `context[].audio_url` |  | string (audio URL) | yes |  |  |  |

## Example input

Required parameters only:

```json
{
  "scene": [
    {
      "speaker_id": 0,
      "text": "Hey how are you doing."
    },
    {
      "speaker_id": 1,
      "text": "Pretty good, pretty good."
    },
    {
      "speaker_id": 0,
      "text": "I'm great, so happy to be speaking to you."
    }
  ]
}
```

A fuller example:

```json
{
  "scene": [
    {
      "speaker_id": 0,
      "text": "Hey how are you doing."
    },
    {
      "speaker_id": 1,
      "text": "Pretty good, pretty good."
    },
    {
      "speaker_id": 0,
      "text": "I'm great, so happy to be speaking to you."
    }
  ]
}
```

## 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/csm-1b?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "scene": [
      {
        "speaker_id": 0,
        "text": "Hey how are you doing."
      },
      {
        "speaker_id": 1,
        "text": "Pretty good, pretty good."
      },
      {
        "speaker_id": 0,
        "text": "I'\''m great, so happy to be speaking to you."
      }
    ]
  }'

# 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/csm-1b?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "scene": [
      {
        "speaker_id": 0,
        "text": "Hey how are you doing."
      },
      {
        "speaker_id": 1,
        "text": "Pretty good, pretty good."
      },
      {
        "speaker_id": 0,
        "text": "I'm great, so happy to be speaking to you."
      }
    ]
  }),
});
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 = {
    "scene": [
        {
            "speaker_id": 0,
            "text": "Hey how are you doing.",
        },
        {
            "speaker_id": 1,
            "text": "Pretty good, pretty good.",
        },
        {
            "speaker_id": 0,
            "text": "I'm great, so happy to be speaking to you.",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/csm-1b", 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": "csm-1b",
      "input": {
        "scene": [
          {
            "speaker_id": 0,
            "text": "Hey how are you doing."
          },
          {
            "speaker_id": 1,
            "text": "Pretty good, pretty good."
          },
          {
            "speaker_id": 0,
            "text": "I'm great, so happy to be speaking to you."
          }
        ]
      },
      "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": "csm-1b",
  "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": 30,
    "usd": "0.03",
    "charged": 30,
    "refunded": 0
  },
  "input": {
    "scene": [
      {
        "speaker_id": 0,
        "text": "Hey how are you doing."
      },
      {
        "speaker_id": 1,
        "text": "Pretty good, pretty good."
      },
      {
        "speaker_id": 0,
        "text": "I'm great, so happy to be speaking to you."
      }
    ]
  },
  "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
    }
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} \| string | Âm thanh do mô hình tạo ra. |

## 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
- [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
- [Chatterbox · Speech to Speech](https://doitong.com/developers/models/chatterbox/speech-to-speech.md) (`chatterbox/speech-to-speech`): $0.015 / minute of input audio
- [Chatterbox · Text to Speech](https://doitong.com/developers/models/chatterbox/text-to-speech.md) (`chatterbox/text-to-speech`): $0.025 / 1000 characters
- [Chatterbox · Text to Speech · Multilingual](https://doitong.com/developers/models/chatterbox/text-to-speech/multilingual.md) (`chatterbox/text-to-speech/multilingual`): $0.025 / 1000 characters
- [Chatterboxhd · Speech to Speech](https://doitong.com/developers/models/resemble-ai/chatterboxhd/speech-to-speech.md) (`resemble-ai/chatterboxhd/speech-to-speech`): $0.02 / minute of input audio

## Links

- HTML page: https://doitong.com/developers/models/csm-1b
- 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=csm-1b
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/csm-1b