# Personaplex · Realtime API

> Realtime-tagged Personaplex endpoint: audio in, persona-driven spoken reply out, with voice presets or cloning

Accepts user speech via `audio_url` and returns a spoken response, its duration, the seed and a text transcript. The persona comes from `prompt`, while the voice comes from a preset `voice` ID or from `voice_audio_url` for cloning, where 10 or more seconds of clear speech is recommended. Temperature and top-k controls exist for both audio and text sampling.

- Model id: `personaplex/realtime`
- Made by: NVIDIA
- Category: Audio
- Output: audio
- Charged by usage (up to $1.80 per run, typical $0.025; the rest of the hold is refunded): $0.001 / second of processing time (cheapest run $0.025 (25 API credits))
- Run: `POST https://api.doitong.com/v1/run/personaplex/realtime`
- Quote: `POST https://api.doitong.com/v1/quote/personaplex/realtime`
- Docs page: https://doitong.com/developers/models/personaplex/realtime

## Pricing

Price: **$0.001 / second of processing time**. Charged by actual usage at $0.001 / second of processing time: up to $1.80 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.025.

The full example input below holds up to $1.80 = 1800 API credits (up to 1800 s of processing time × $0.001) when it starts; a typical run costs $0.025 (25 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.com/v1/quote/personaplex/realtime` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | no | `You are a wise and friendly teacher. Answer questions or provide advice in a clear and engaging way.` |  | Text prompt defining the AI's persona and the context of the conversation. |
| `voice` |  | enum (string) | no | `NATF2` | `NATF0`, `NATF1`, `NATF2`, `NATF3`, `NATM0`, `NATM1`, `NATM2`, `NATM3`, `VARF0`, `VARF1`, `VARF2`, `VARF3`, `VARF4`, `VARM0`, `VARM1`, `VARM2`, `VARM3`, `VARM4` | AI response voice ID, overridden by voice_audio_url when supplied. Its codes distinguish natural (NAT) from variety (VAR) and female (F) from male (M). |
| `voice_audio_url` |  | string (audio URL) \| null | no |  |  | Voice-cloning sample URL; clear speech lasting at least 10 seconds is recommended. The sample is cloned on the fly, replacing the preset 'voice' for the AI's response. |
| `temperature_audio` |  | number | no | `0.8` | 0 – 2 | Temperature used when sampling audio; increasing it yields more varied results. |
| `temperature_text` |  | number | no | `0.7` | 0 – 2 | Temperature used when sampling text; increasing it yields more varied results. |
| `top_k_audio` |  | integer | no | `250` | 1 – 2,048 | Top-K setting used to sample audio tokens. |
| `top_k_text` |  | integer | no | `25` | 1 – 1,000 | Top-K setting used to sample text tokens. |
| `seed` |  | integer \| null | no |  |  | Seed controlling randomness for reproducible results. |
| `audio_url` | `audio` | string (audio URL) | yes |  |  | URL of the audio input containing the user's speech. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Screening can be relaxed by setting false, provided the caller is authorized. |

File parameters (`voice_audio_url`, `audio`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
}
```

## 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/personaplex/realtime?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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/personaplex/realtime?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }),
});
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 = {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/personaplex/realtime", 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": "personaplex/realtime",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
      },
      "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": "personaplex/realtime",
  "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": 1800,
    "usd": "1.80",
    "charged": 1800,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "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
    },
    "text": " Thank you for calling SwiftPlex Appliances. This is Farhod, how can I help you today? I understand your concern. The replacement part is out of stock, so we can't ship it right away. We can use an alternative part that will arrive in 3 days. Would you like to proceed with that?",
    "duration": 5,
    "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.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} | AI-generated response audio in WAV format at 24 kHz. |
| `text` | string | Text transcription of the response from the AI. |
| `duration` | number | Length of the generated audio, measured in seconds. |
| `seed` | integer | Seed value applied during generation. |

## Related models

- [Personaplex](https://doitong.com/developers/models/personaplex.md) (`personaplex`): $0.001 / second of input audio
- [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
- [Elevenlabs Sound Effects V2](https://doitong.com/developers/models/elevenlabs/sound-effects/v2.md) (`elevenlabs/sound-effects/v2`): $0.002 / second
- [ElevenLabs Voice Changer](https://doitong.com/developers/models/elevenlabs/voice-changer.md) (`elevenlabs/voice-changer`): $0.30 / minute of input audio
- [FFmpeg API \[Merge Audios\]](https://doitong.com/developers/models/ffmpeg-api/merge-audios.md) (`ffmpeg-api/merge-audios`): $0.00017 / second of processing time

## Links

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