# Avatar X API

> Talking-avatar video from a script, using a stock avatar or your own reference video and voice

Turns a `script` of 50 to 1,500 characters into a speaking avatar video, with generated speech limited to 180 seconds. Choose a stock `avatar` such as Jasmine, Luke or Maya, including 16:9 variants. Alternatively supply both `video_reference_url` and `audio_reference_url` to use your own footage and voice reference, in which case the stock avatar is ignored.

- Model id: `mirage-api/avatar-x/text-to-video`
- Made by: Mirage
- Category: Lipsync & Avatars
- Output: video
- Estimated price per run: $54.00 / run (cheapest run $54.00 (54000 API credits))
- Run: `POST https://api.doitong.com/v1/run/mirage-api/avatar-x/text-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/mirage-api/avatar-x/text-to-video`
- Docs page: https://doitong.com/developers/models/mirage-api/avatar-x/text-to-video

## Pricing

Price: **$54.00 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $54.00 = 54000 API credits (1 request × 54000 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/mirage-api/avatar-x/text-to-video` 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 |
|---|---|---|---|---|---|---|
| `script` |  | string | yes |  | 50 – 1500 characters | Script constrained by both character count and generated duration: speech may not exceed 180 seconds, even when speaking pace pushes a shorter script past that limit. Supply 50 to 1,500 characters; the 50-character minimum generally yields about four seconds of speech. |
| `avatar` |  | enum (string) \| null | no | `Jasmine` | `None`, `Ayesha`, `Ayesha (16:9)`, `Farhan`, `Farhan (16:9)`, `Giulia`, `Giulia (16:9)`, `Jasmine`, `Jasmine (16:9)`, `Luke`, `Luke (16:9)`, `Maya`, `Maya (16:9)`, `Michael`, `Michael (16:9)`, `Neha`, `Neha (16:9)`, `Tariq`, `Tariq (16:9)`, `Valerie`, `Valerie (16:9)` | Stock appearance-and-voice selection, unnecessary when both video_reference_url and audio_reference_url are supplied because those references replace it completely. Use None to leave the avatar unset, or copy an exact Avatar value after previewing all options in the [avatar catalog](https://captions.ai/help/docs/api/actor-catalog). |
| `video_reference_url` |  | string \| null | no |  |  | Reference-video URL that replaces the selected avatar and requires audio_reference_url; any audio embedded in the video is disregarded. Media must last from 1 to 120 seconds, stay within 1 GiB, and have a display aspect ratio within 5% of 9:16 or 16:9; supported codec/container combinations are H.264, H.265/HEVC, or ProRes in .mp4, .mov, or .m4v, and VP8 or VP9 in .webm. Retrieval must be public over HTTPS without cookies or authorization headers. |
| `audio_reference_url` |  | string \| null | no |  |  | Voice-reference HTTPS URL that requires an accompanying video_reference_url and causes the chosen avatar to be disregarded; retrieval must work publicly without authorization headers or cookies. Processing uses only the first 60 seconds, but the file must last 10 to 180 seconds, remain within 64 MiB, and contain a single mono or stereo stream at 8 to 48 kHz. Accepted formats include FLAC, MP3, PCM WAV or AIFF, AAC or ALAC, and Opus or Vorbis. |

## Example input

Required parameters only:

```json
{
  "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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/mirage-api/avatar-x/text-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/mirage-api/avatar-x/text-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/mirage-api/avatar-x/text-to-video", 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": "mirage-api/avatar-x/text-to-video",
      "input": {
        "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "mirage-api/avatar-x/text-to-video",
  "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": 54000,
    "usd": "54.00",
    "charged": 54000,
    "refunded": 0
  },
  "input": {
    "script": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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} |  |

## Related models

- [Mirage Avatar X](https://doitong.com/developers/models/mirage-api/avatar-x/reference-to-video.md) (`mirage-api/avatar-x/reference-to-video`): $0.30 / second of input audio
- [Kling AI Avatar 2.0 Pro](https://doitong.com/developers/models/kling-video/ai-avatar/v2/pro.md) (`kling-video/ai-avatar/v2/pro`): $0.115 / second of input audio
- [Sync Lipsync 3](https://doitong.com/developers/models/sync-lipsync/v3.md) (`sync-lipsync/v3`): $8.00 / minute of output video
- [VEED Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0.md) (`veed/fabric-1.0`): from $0.08 / second of input audio
- [AI Avatar Multi](https://doitong.com/developers/models/ai-avatar/multi.md) (`ai-avatar/multi`): from $0.20 / second of output video
- [AI Avatar Multi Text](https://doitong.com/developers/models/ai-avatar/multi-text.md) (`ai-avatar/multi-text`): from $0.648 / run
- [AI Avatar Single Text](https://doitong.com/developers/models/ai-avatar/single-text.md) (`ai-avatar/single-text`): from $4.688 / run
- [Avatars Audio to Video](https://doitong.com/developers/models/argil/avatars/audio-to-video.md) (`argil/avatars/audio-to-video`): from $0.02 / second of input audio

## Links

- HTML page: https://doitong.com/developers/models/mirage-api/avatar-x/text-to-video
- 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=mirage-api/avatar-x/text-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/mirage-api/avatar-x/text-to-video