Video: Text-to-Video

vidu-q2-pro-text-to-video (balanced)

Generate videos from text using Vidu Q2 Pro (cinematic detail tier, up to 1080p, ~10s max, multi-reference support for character/scene consistency). Input: text prompt. Output: video. Use for: cinematic detail, scenes with consistent characters across shots via multi-reference.

post/api/v1/vidu-q2-pro-text-to-video

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/vidu-q2-pro-text-to-video
  • 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 required
resolution'720p' | '1080p'
aspect_ratio'16:9' | '9:16' | '1:1'
duration2 | 3 | 4 | 5 | 6 | 7 | 8
bgmboolean
movement_amplitude'auto' | 'small' | 'medium' | 'large'
webhook_urlstring uri nullable

Response

Successful Response

unknown required

Changes

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