Video: Avatars

omnihuman-1-5 (balanced)

Generate talking head video from portrait image and audio using OmniHuman 1.5. Input: portrait image, audio. Output: talking head video. Use for: virtual presenter, avatar video, lipsync animation.

post/api/v1/omnihuman-1-5

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/omnihuman-1-5
  • Auth: one of:
    • API key in header x-api-key
    • OAuth 2 (client credentials, token URL https://api.muapi.ai/oauth/token)

Query parameters

webhookstring
team_idinteger nullable

Headers

x-api-keystring
x-embed-codestring nullable
x-agent-embed-codestring nullable
x-whitelabel-studiostring nullable
authorizationstring nullable

Request body

promptstring nullable
image_urlstring uri required
audio_urlstring uri required
mask_urlstring[] nullable
output_resolution'720' | '1080'
pe_fast_modeboolean
seedinteger
webhook_urlstring uri nullable

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 2 revisions of this API.