OmniHuman v1.5 overview
OmniHuman v1.5 by ByteDance
OmniHuman 1.5 API creates lifelike avatars by synchronizing lip movements, facial expressions, and behavior with audio.
OmniHuman v1.5 specs
- Model ID
bytedance/omnihuman/v1.5- Developer
- ByteDance
- Input
- Text, Image
- Output
- Video
- Endpoint
POST https://api.aimlapi.com/v2/video/generations
OmniHuman v1.5 API Overview
OmniHuman v1.5 is an advanced AI model designed to transform static human portraits and audio tracks into hyper-realistic talking videos. By combining multimodal deep learning in vision, speech, and motion synthesis, it delivers lifelike facial expressions, natural lip synchronization, and emotion-aware gestures that match the input voice with remarkable precision.
Technical Specifications
- Model Type: Multimodal Generative AI
- Input Modalities: Image, Audio
- Language Support: 50+ languages with dialect variants
Performance Benchmarks
- Improved Fluidity and Expressions: Enhanced facial expressions and overall motion fluidity.
- Better Contextual Understanding: The model can generate videos over one minute with more dynamic and contextually aware movements, including natural pauses in speech and rich musical expressions.
- Reduced Unnaturalness: The new reasoning module specifically targets and significantly reduces instances of unnatural motion that could occur in previous versions.
Key Features
- Generates seamless, natural video of a human subject from a still photo and speech/audio input.
- Accurately mimics facial expressions and emotional states to enhance realism.
- Supports a wide range of languages and voice accents without degrading video quality.
- Optimized for interactive avatars, virtual assistants, and character-driven multimedia.
- Lightweight architecture designed for efficient performance on consumer and professional hardware.
- Adjustable parameters to control facial movement intensity and emotional expressiveness.
Comparison with Other Models
vs Synthesia: OmniHuman produces more realistic facial expressions and emotional alignment with audio, while Synthesia focuses on faster video generation with simpler lip-sync. OmniHuman supports a broader range of emotions and subtle movements, making it better for high-fidelity avatar interactions.
vs Hour One: OmniHuman excels at fine-grained emotional and facial synchronization, while Hour One prioritizes rapid avatar creation for business use cases. OmniHuman produces more natural transitions and supports richer audio diversity across languages.
vs DeepBrain AI: DeepBrain AI specializes in news-anchor style video synthesis with limited emotional range. OmniHuman surpasses it by enabling dynamic emotional expressions and interactive avatar movements synchronized tightly with diverse audio content.
Use cases
- Interactive avatars for customer service, gaming, and VR environments.
- Dubbing and localization with matched facial expressions in films and animations.
- Educational multimedia with emotionally engaging character representations.
- Social media content creation and personalized video messaging.
- Digital humans for marketing, advertising, and brand storytelling.
OmniHuman v1.5 API pricing
| Usage | Price | Unit |
|---|---|---|
| Video generation | $0.16 | per second |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
OmniHuman v1.5 vs other video models: prices
AI/ML API rates for 5 models, per second.
| Model | Per second |
|---|---|
 OmniHuman v1.5 | $0.16 |
| Seedance 2.0 Fast | $0.0572 |
| Seedance 2.0 | $0.0711 |
 Kling 4.0 Image to Video | $0.157 |
| Seedance 2 | $0.394 |
How to use the OmniHuman v1.5 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v2/video/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "bytedance/omnihuman/v1.5",
"image_url": "https://example.com/input.jpg",
"audio_url": "https://example.com/input.mp3"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "bytedance/omnihuman/v1.5",
"image_url": "https://example.com/input.jpg",
"audio_url": "https://example.com/input.mp3"
}
response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "bytedance/omnihuman/v1.5",
"image_url": "https://example.com/input.jpg",
"audio_url": "https://example.com/input.mp3"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.
Models similar to OmniHuman v1.5
Related articles
OmniHuman v1.5 FAQ
What inputs and outputs does OmniHuman v1.5 support?
OmniHuman v1.5 takes image, text, video as input and returns video.
How much does OmniHuman v1.5 cost?
OmniHuman v1.5 costs $0.16 per second on AI/ML API, billed as you go with no subscription.
How is OmniHuman v1.5 billed?
OmniHuman v1.5 costs $0.16 per second on AI/ML API, billed as you go with no subscription.
Can OmniHuman v1.5 take an existing image as input?
Yes, OmniHuman v1.5 accepts image input as well as a text prompt.
Who created OmniHuman v1.5?
OmniHuman v1.5 was built by ByteDance.
How do I call OmniHuman v1.5 on AI/ML API?
Send a request to v2/video/generations with bytedance/omnihuman/v1.5 as the model id.
Is OmniHuman v1.5 available through a single API key?
Yes. OmniHuman v1.5 is served through AI/ML API, so the same key and endpoint format used for other models applies.
How does OmniHuman v1.5 improve on earlier versions?
It generates videos of human figures with more natural motion and more accurate facial detail than prior versions.
What is the OmniHuman v1.5 model ID?
Use bytedance/omnihuman/v1.5 as the model parameter. Requests go to https://api.aimlapi.com/v2/video/generations with your AI/ML API key.