Video
OmniHuman
by Bytedance
OmniHuman audio-to-video avatars with subject detection and human identification helpers.
Capabilities
- Audio to video
- Subject detection
- Avatars
Available models
Pass any of these IDs in the model field.
| Model ID | Detail | Price |
|---|---|---|
| omnihuman-audio-to-video | per clip | $0.20 / call |
| omnihuman-subject-detection | per image | $0.01 / call |
Pricing starts at
$0.200 / call
Pay only for what you use. Each response returns the exact amount settled against your balance — no subscriptions, no minimums.
Quickstart
OmniHuman · omnihuman-audio-to-video
cURL
curl -X POST https://capi.ai/api/v1/kling/text_to_video \
-H "Authorization: Bearer YOUR_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "omnihuman-audio-to-video",
"prompt": "A paper kite flying above a quiet coastal town at sunrise",
"duration_seconds": 5
}'More Video models
View allVideo
Kling
Kuaishou
Kling video generation for cinematic text-to-video, image-to-video, motion control, and avatar clips.
from $0.070 / secondView
Video
Veo 3.1
Google Veo 3.1 for native audio-video generation, extension, and upscaling with strong prompt adherence.
from $0.150 / secondView
Video
Seedance
Bytedance
Seedance 2.5 delivers precise choreography and camera control for text- and image-driven video.
from $0.090 / secondView