# Mirage Avatar X

> Run Mirage Avatar X by mirage online or via API. $0.175/sec, no setup.

**URL:** https://inference.sh/apps/mirage/avatar-x
**Last updated:** 2026-11-11

---

Generate an expressive talking-head video from a portrait image or video reference and an audio track using Mirage Avatar X, with natural lip sync, eye contact and micro-expressions.

- app: `mirage/avatar-x`
- maker: [mirage](https://inference.sh/apps/mirage.md)
- category: [video](https://inference.sh/apps/category/video.md)
- tasks: [lip sync](https://inference.sh/apps/tag/lip-sync.md), [talking avatar](https://inference.sh/apps/tag/talking-avatar.md)
- price: $0.175/sec
- runs via: api, javascript and python sdk, belt cli, mcp

## avatar-x API Guide

### About
generate an expressive talking-head video from a portrait image or video reference and an audio track using mirage avatar x, with natural lip sync, eye contact and micro-expressions.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @2sx9p262 pinned
result = client.run({
        "app": "mirage/avatar-x@2sx9p262",
        "input": {
            "audio": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @2sx9p262 pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "mirage/avatar-x@2sx9p262",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "mirage/avatar-x@2sx9p262",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "mirage/avatar-x@2sx9p262",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **image** (string): Portrait image (JPEG or PNG, 9:16 or 16:9). Use a clear, front-facing shot of a single person with mouth open. Ignored when video is provided.
- **video** (string): Video appearance reference (MP4 or MOV, 10–60s). Takes precedence over image when both are provided.
- **audio** (string) *required*: Speech audio that drives the performance (WAV or MP3, 1–180s). The output video length matches this clip. Expressive, natural-sounding audio gives the best result.

#### Output
- **video** (string): The generated talking-head video.
- **video_id** (string): Mirage video ID for this generation.

## other video apps

- [Pika H3 Flex (self-hosted)](https://inference.sh/apps/pika/pika-h3-flex-oss.md): GPU time, billed per millisecond
- [Pika H3 Flex Upscale](https://inference.sh/apps/pika/pika-h3-flex-upscale.md): $0.05-$0.14/sec (480p src), $0.03-$0.12/sec (768p src); 1080p/2K/4K targets
- [Pika H3 Flex Reference to Video](https://inference.sh/apps/pika/pika-h3-flex-reference.md): $0.06/sec 480p, $0.12/sec 768p, $0.15/sec 1080p, $0.16/sec 2k, $0.20/sec 4k (output+input video sec). Stems: $0.001/sec
- [Pika H3 Flex](https://inference.sh/apps/pika/pika-h3-flex.md): $0.02/sec 480p, $0.04/sec 768p, $0.07/sec 1080p, $0.08/sec 2K, $0.16/sec 4K; stems +$0.001/stem-sec
- [Gemini Omni 1.2 Flash](https://inference.sh/apps/google/gemini-omni-1-2-flash.md): $0.0232/sec 360p, $0.0695/sec 720p, $0.1043/sec 1080p, $0.2085/sec 4K, plus $1.50/M input and $9.00/M thinking tokens

## faq

### how much does Mirage Avatar X cost?

$0.175/sec. you pay per run from your inference shell credits. no subscription is required.

### how do I run Mirage Avatar X via api?

call mirage/avatar-x with the javascript or python sdk, the rest api, or `belt app run mirage/avatar-x` from a terminal. the api reference on this page lists every input.

### who makes Mirage Avatar X?

Mirage Avatar X is made by mirage and runs on inference shell. every mirage app is listed at https://inference.sh/apps/mirage.

### can my agent use Mirage Avatar X?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Mirage Avatar X?

other video apps on inference shell include Pika H3 Flex (self-hosted), Pika H3 Flex Upscale, Pika H3 Flex Reference to Video, Pika H3 Flex. they run through the same api, so switching is a one-line change.