digital-human
Bytedance OmniHuman turns a single portrait photo into avatar video with lifelike motion and expressions ($0.12/sec). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
您的請求將花費 $0.12 每次運行。
使用 $10 您可以運行此模型大約 83 次。
示例查看全部
README
ByteDance Avatar Omni Human
Transform any portrait into a realistic talking avatar with ByteDance's Avatar Omni Human. Simply upload a photo and an audio clip, and watch the subject come to life with perfectly synchronized lip movements, natural expressions, and lifelike head motion — ideal for virtual presenters, digital content, and personalized video messages.
Why It Looks Great
- Realistic lip sync: Advanced audio analysis ensures precise mouth movements matching every syllable.
- Natural expressions: Generates authentic facial expressions and subtle head movements.
- Simple workflow: Just two inputs — an image and audio — for complete avatar generation.
- High fidelity: Preserves the original portrait's likeness and quality.
- Versatile audio support: Works with speech, singing, and various audio types.
Parameters
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Portrait image of the person to animate (upload or public URL). |
| audio | Yes | Audio file for lip synchronization (upload or public URL). |
| enable_base64_output | No | API only: Returns base64 string instead of URL. |
How to Use
- Upload your image — drag and drop a clear portrait photo or paste a public URL.
- Upload your audio — add the speech or audio you want the avatar to perform.
- Run — click the button to generate.
- Download — preview and save your talking avatar video.
Pricing
Per-second billing based on audio duration.
| Metric | Cost |
|---|---|
| Per second | $0.12 |
Examples
| Audio Length | Calculation | Total Cost |
|---|---|---|
| 5s | 5 × $0.12 | $0.60 |
| 15s | 15 × $0.12 | $1.80 |
| 30s | 30 × $0.12 | $3.60 |
| 1m (60s) | 60 × $0.12 | $7.20 |
| 5m (300s) | 300 × $0.12 | $36.00 |
Best Use Cases
- Virtual Presenters — Create AI spokespeople for videos, presentations, and training content.
- Personalized Messages — Generate custom video messages from a single photo.
- Content Localization — Dub content into different languages with matching lip movements.
- Social Media Content — Produce engaging talking-head videos without filming.
- E-learning & Training — Create instructor-led content from static presenter images.
- Digital Avatars — Bring character portraits and illustrations to life with speech.
Pro Tips for Best Results
- Use clear, front-facing portrait photos with good lighting for best lip sync accuracy.
- Ensure the face is clearly visible and not obscured by hair, accessories, or shadows.
- High-quality audio with minimal background noise produces more accurate synchronization.
- Neutral or slightly open mouth expressions in the source image work best.
- The subject's face should be a reasonable size in the frame — not too small or cropped.
- Test with shorter audio clips first before processing longer content.
Notes
- If using URLs for image or audio, ensure they are publicly accessible.
- The enable_base64_output option is only available through the API.
- Processing time scales with audio duration.
- Best results come from portrait-style images with clear facial features.
- Works with various audio formats — speech, narration, singing, and more.