✦

omnihuman-1-5

Commercial use

OmniHuman 1.5 is ByteDance's lip sync model, available here through a single relay API. It re-syncs a subject's lips to new audio or a new language. Provide a source image plus a prompt to steer the result. Requests run server-side against 97AI.PRO with your credit balance, so you get ByteDance quality without managing a separate ByteDance account or key.

💰Pricing: lip sync 28.35 credits / s (≈$0.1418)

24H STATUS MONITORSuccess: 100%

No requests in the last 24h · Operational

Input

MODEL: omnihuman-1-5

image_urlrequired

Portrait image URL; any aspect ratio (people, pets, anime, etc.)

mask_urloptional

Optional mask image URLs (max 5) for subject detection

audio_urlrequired

Audio URL; duration must be less than 60 seconds

promptoptional

Optional text prompt (max 1000 chars); multi-language

output_resolutionoptional

Output video resolution in pixels

pe_fast_modeoptional

Sacrifices some quality to speed up generation

seedoptional

Random seed; same positive integer gives consistent results

Output

output type: video

Result will appear here.