OmniHuman 1.5 API 定价
Pay-as-you-go access through PiAPI.
OmniHuman 1.5 API
$0.13/s
- Audio-driven avatar generation
- Full-body and talking-head videos
Features
Capabilities from the production model page.
OmniHuman 1.5 支持音频驱动的全身生成吗?
支持。OmniHuman 1.5 可以直接根据文本、图像和音频输入生成全身数字人视频,并同步口型与肢体动作。我们的 AI 数字人 API 适用于开发者和内容创作者。
我可以通过提示词控制场景或情绪吗?
可以。OmniHuman 1.5 API 支持通过提示词进行细致控制,你可以修改背景场景并指定情绪基调,同时保持身份一致性。
Multi-Character & Multi-Audio Scene Generation
OmniHuman 1.5 AI API animates multiple characters within a single scene, each driven by independent audio tracks and coordinated interactions.
Long-Horizon Avatar Generation
OmniHuman 1.5 AI maintains motion coherence, expressiveness, and temporal consistency in video sequences exceeding one minute.
Diverse Character Styles & Appearance
OmniHuman supports a wide range of character styles and visual identities while preserving realism and expressiveness.
Temporal Identity Preservation
With pseudo last frame identity preservation technique, OmniHuman 1.5 prevents appearance drift across frames.
先进训练架构
OmniHuman 1.5 采用多模态大语言模型进行统一全局规划,结合关键帧控制架构、交叉注意力机制、增强口型同步策略和优化数据处理流程,以获得更稳健的生成效果。
我可以通过提示词控制场景或情绪吗?
可以。OmniHuman 1.5 API 支持通过提示词进行细致控制,你可以修改背景场景并指定情绪基调,同时保持身份一致性。
基准测试领先
在 Kling AI 内部数据集 的 375 组图像-音频-提示样本上进行测试后,OmniHuman 1.5 的生成质量优于多款领先的数字人模型,例如 Omnihuman-1 和 HeyGen Avatar 。
Get started
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "omni-human",
"task_type": "omni-human-1.5",
"input": {
"prompt": "A presenter speaking naturally to camera",
"image_url": "YOUR_IMAGE_URL",
"audio_url": "YOUR_AUDIO_URL",
"fast_mode": false
}
}'
# → { "task_id": "9d5a…", "status": "pending" }curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'
# poll until status = completed
{
"data": {
"status": "completed",
"output": {
"video_url": "https://img.theapi.app/ephemeral/…"
}
}
}$ npm install -g piapi-cli $ piapi run omnihuman-1-5 \ prompt="A presenter speaking naturally to camera" \ image_url=YOUR_IMAGE_URL \ audio_url=YOUR_AUDIO_URL \ fast_mode=false ✓ Task completed! https://img.theapi.app/ephemeral/…
FAQ
什么是 OmniHuman 1.5?
Kling AI Avatar 是由 Bytedance推出的一项 AI 技术,可让你从想象中生成 AI 数字人。通过 OmniHuman-1,你现在就可以使用我们的 OmniHuman 1.5 API 创建 AI 数字人!
什么是 OmniHuman 1.5 API?
OmniHuman 1.5 API 提供先进的 AI 驱动数字人生成功能,支持高保真写实风格和风格化输出,适用于虚拟身份与创意制作流程。
How can I use OmniHuman?
PiAPI offers API endpoints for avatar generation. Documentation includes full API references, request examples, and usage guides.
How does OmniHuman compare to other AI video generation tools?
OmniHuman is an avatar generation model that specializes in AI avatar generation, as compared to other general-purpose video generation tools. Check out our blog comparison between OmniHuman 1.5 vs Kling AI Avatarto find out more!
OmniHuman 1.5 支持 NSFW 或受限内容吗?
Please refer to our NSFW policyfor more information and follow the guidelines.
OmniHuman 1.5 支持音频驱动的全身生成吗?
支持。OmniHuman 1.5 可以直接根据文本、图像和音频输入生成全身数字人视频,并同步口型与肢体动作。我们的 AI 数字人 API 适用于开发者和内容创作者。 Go to our OmniHuman AI video generatorto experiment with audio-driven virtual human AI avatar.
我可以通过提示词控制场景或情绪吗?
可以。OmniHuman 1.5 API 支持通过提示词进行细致控制,你可以修改背景场景并指定情绪基调,同时保持身份一致性。
More questions? See the API docs.
Our blog
OmniHuman 1.5 API


