OmniHuman 1.5 es el modelo de avatar de IA y humano digital de ByteDance que transforma una sola imagen y audio en videos realistas donde el personaje habla, con sincronización labial natural, expresiones faciales y movimientos auténticos.

Model Type:
Pricing: 27 credits per second (~$0.135). High-tier top-ups (+10% bonus) bring effective pricing down to ~$0.122 per second.
Input

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP Maximum file size: 10MB

Portrait image URL, supports any aspect ratio with subjects including people/pets/anime, etc.

Text
0 / ∞
No items yet. Click Add to start.

To have a specific subject in the image speak, use 'Subject Detection' to get the corresponding mask image and pass it as input.

Click to upload or drag and drop

Supported formats: MPEG, WAV, X-WAV, AAC, OGG, MP4 Maximum file size: 10MB

Audio URL. Duration must be < 60 seconds (recommended ≤15 seconds; exceeding this will cause degradation).

Prompt text, limited to Chinese/English/Japanese/Korean/Spanish/Indonesian, recommended ≤300 characters.

0/300

Output video resolution, default 1080.

Fast mode, sacrifices some quality to speed up generation.

Random seed. Default is -1 (random). When using the same positive integer and keeping all other parameters identical, the result will be highly consistent (with very high probability).

Output
output typevideo

README

Complete guide to using omnihuman-1-5

API de OmniHuman 1.5 de ByteDance para la generación de videos de avatares de IA y humanos digitales

Original image