# Mureka 9.5 Podcast Generation API

> Tạo âm thanh podcast từ danh sách lượt hội thoại theo thứ tự, với giọng nói riêng cho từng lượt

Mảng `conversations` bắt buộc chứa từ 1 đến 10 lượt theo thứ tự, mỗi lượt gồm văn bản và lựa chọn giọng nói. Kết quả là tệp âm thanh, thời lượng tính bằng mili giây nếu có và `song_id` có thể tái sử dụng.

- Model id: `mureka/api/generate/podcast`
- Made by: Mureka
- Category: Audio
- Output: audio
- Estimated price per run: $0.019 / run (cheapest run $0.019 (19 API credits))
- Run: `POST https://api.doitong.com/v1/run/mureka/api/generate/podcast`
- Quote: `POST https://api.doitong.com/v1/quote/mureka/api/generate/podcast`
- Docs page: https://doitong.com/vi/developers/models/mureka/api/generate/podcast

## Pricing

Price: **$0.019 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.019 = 19 API credits (1 request × 19 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/mureka/api/generate/podcast` 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 |
|---|---|---|---|---|---|---|
| `conversations` |  | array of object {text, voice} | yes |  | 1 – 10 items | Các lượt hội thoại theo thứ tự để tạo sinh âm thanh podcast. |
| `conversations[].text` |  | string | yes |  | 1 – 400 characters | Văn bản lời nói cho lượt hội thoại hiện tại, giới hạn ở 400 ký tự. |
| `conversations[].voice` |  | enum (string) | yes |  | `Ethan`, `Victoria`, `Jake`, `Luna`, `Emma` | Giọng tích hợp được gán cho lượt hội thoại hiện tại. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Có thể nới lỏng việc kiểm duyệt bằng cách đặt thành false, nếu người gọi được cấp quyền. |

## Example input

Required parameters only:

```json
{
  "conversations": [
    {
      "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
      "voice": "Ethan"
    }
  ]
}
```

A fuller example:

```json
{
  "conversations": [
    {
      "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
      "voice": "Ethan"
    }
  ]
}
```

## 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/mureka/api/generate/podcast?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "conversations": [
      {
        "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "voice": "Ethan"
      }
    ]
  }'

# 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/mureka/api/generate/podcast?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "conversations": [
      {
        "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "voice": "Ethan"
      }
    ]
  }),
});
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 = {
    "conversations": [
        {
            "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
            "voice": "Ethan",
        },
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/mureka/api/generate/podcast", 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": "mureka/api/generate/podcast",
      "input": {
        "conversations": [
          {
            "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
            "voice": "Ethan"
          }
        ]
      },
      "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": "mureka/api/generate/podcast",
  "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": 19,
    "usd": "0.019",
    "charged": 19,
    "refunded": 0
  },
  "input": {
    "conversations": [
      {
        "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "voice": "Ethan"
      }
    ]
  },
  "output": {
    "song_id": "string",
    "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
    },
    "duration": 5,
    "lyrics_sections": [
      {
        "section_type": "intro",
        "start": 1,
        "end": 1,
        "lines": [
          {}
        ]
      }
    ]
  },
  "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 |
|---|---|---|
| `song_id` | string \| null | Mã định danh âm thanh có thể tái sử dụng cho các điểm cuối chấp nhận song_id. |
| `audio` | object {url, content_type, file_name, file_size} | Tệp âm thanh được tạo sinh. |
| `duration` | integer \| null | Độ dài âm thanh được tạo, tính bằng mili giây, nếu có. |
| `lyrics_sections` | array of object {section_type, start, end, lines} \| null | Các phần lời bài hát kèm thông tin thời gian của âm thanh được tạo, nếu có. |

## Related models

- [Mureka 9.5 Lyrics Video](https://doitong.com/developers/models/mureka/api/generate/lyrics-video.md) (`mureka/api/generate/lyrics-video`): $0.15 / video
- [Mureka 9.5 Instrumental Generation](https://doitong.com/developers/models/mureka/api/generate/instrumental.md) (`mureka/api/generate/instrumental`): from $0.045 / request
- [Mureka 9.5 Song Generation](https://doitong.com/developers/models/mureka/api/generate/song.md) (`mureka/api/generate/song`): from $0.45 / run
- [Mureka 9.5 Lyrics Generation](https://doitong.com/developers/models/mureka/api/generate/lyrics.md) (`mureka/api/generate/lyrics`): $0.0135 / request
- [MMAudio V2](https://doitong.com/developers/models/mmaudio-v2.md) (`mmaudio-v2`): $0.001 / second
- [DeepFilterNet 3](https://doitong.com/developers/models/deepfilternet3.md) (`deepfilternet3`): $0.001 / second of input audio
- [Demucs](https://doitong.com/developers/models/demucs.md) (`demucs`): $0.0007 / second of input audio
- [ElevenLabs Audio Isolation](https://doitong.com/developers/models/elevenlabs/audio-isolation.md) (`elevenlabs/audio-isolation`): $0.10 / minute of input file

## Links

- HTML page: https://doitong.com/developers/models/mureka/api/generate/podcast
- 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=mureka/api/generate/podcast
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/mureka/api/generate/podcast