# Avatar Omni Human 2.0 — Atlas Cloud API

> OmniHuman 2.0 is ByteDance's audio-driven avatar model: one image plus an audio track becomes a 720p video of the character(s) speaking or singing, with dynamic gestures, multi-person scenes, prompt-directed camera movement and clips up to 5 minutes.

This is the machine-readable API reference for **Avatar Omni Human 2.0** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `bytedance/avatar-omni-human-v2.0`
- **Built by**: ByteDance
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/bytedance/avatar-omni-human-v2.0
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.056 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "bytedance/avatar-omni-human-v2.0"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video bytedance/avatar-omni-human-v2.0 -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `bytedance/avatar-omni-human-v2.0`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  Model name.
  - Default: `"bytedance/avatar-omni-human-v2.0"`
  - Options: "bytedance/avatar-omni-human-v2.0"

- **`prompt`** (`string`, _optional_):
  Optional text to direct the scene, actions, gestures and camera movement. Supported languages: Chinese, English, Japanese, Korean, Spanish (Mexican), Indonesian.

- **`image`** (`string`, _required_):
  Reference image of the character(s) to animate, as a URL or Base64. Formats: JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF. Under 30 MB, width and height 300–6000 px, aspect ratio (width/height) 0.4–2.5.

- **`audio`** (`string`, _required_):
  Driving audio (speech or singing), as a URL or Base64. Formats: WAV, MP3. Under 15 MB, 4–300 seconds. The output video has the same length as the audio, and billing follows the audio length.

- **`watermark`** (`boolean`, _optional_):
  Add a watermark to the output video.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "bytedance/avatar-omni-human-v2.0",
  "image": "",
  "audio": ""
}
```


**Full Example**:

```json
{
  "model": "bytedance/avatar-omni-human-v2.0",
  "prompt": "",
  "image": "",
  "audio": "",
  "watermark": false
}
```


### Output Schema

The API returns the following output format:


- **`id`** (`string`, _optional_):
  Unique identifier for the prediction, the ID of the prediction to get.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated content (empty when status is not completed).

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.



**Example Response**:

```json
{
  "id": "",
  "urls": {},
  "model": "",
  "status": "",
  "outputs": [
    ""
  ],
  "created_at": ""
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/avatar-omni-human-v2.0",
  "prompt": "",
  "image": "",
  "audio": "",
  "watermark": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/bytedance/avatar-omni-human-v2.0)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Avatar Omni Human 2.0

**Avatar Omni Human 2.0** is ByteDance's audio-driven avatar video model. Give it one image and an audio track, and it animates the character(s) in the image to speak or sing that audio. Lip sync, expressions, gestures and camera movement follow the rhythm and meaning of the audio. An optional text prompt adds direction.

#### Why Choose This?

- **More dynamic motion than 1.5.** Full-body movement, gestures and camera moves, not just a talking head.
- **Multi-person scenes.** Animate an image with more than one character.
- **Long clips.** One request handles audio from 4 seconds up to 5 minutes.
- **Prompt control.** Use text to direct actions, objects in the scene and camera movement.
- **Lower cost.** Cheaper per second than Avatar Omni Human 1.5.

#### Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| model | Yes | `bytedance/avatar-omni-human-v2.0` |
| image | Yes | Reference image, as a URL or Base64. JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC or HEIF. Under 30 MB, width and height 300–6000 px, aspect ratio (width/height) 0.4–2.5. |
| audio | Yes | Driving audio, as a URL or Base64. WAV or MP3, under 15 MB, 4–300 seconds. The output video is the same length as the audio. |
| prompt | No | Text to direct the scene, actions, gestures and camera movement. Chinese, English, Japanese, Korean, Spanish (Mexican) or Indonesian. |
| watermark | No | Add a watermark to the output video. Default `false`. |

#### How to Use

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/bytedance/avatar-omni-human-v2.0 · Docs: https://www.atlascloud.ai/docs