Video: Text-to-Video

happy-horse-1-text-to-video-1080p (best)

Generate 1080p videos from text using HappyHorse 1.0 (Alibaba's open-source 15B-param unified Transformer; #1 on Artificial Analysis Video Arena at release). Native joint audio+video generation in a single forward pass — video frames and synchronized dialogue/ambient sound/Foley produced together, not dubbed. Multilingual lip-sync across 7 languages (EN, ZH, JA, KO, DE, FR, Cantonese). ~38s typical generation. Input: text prompt. Output: 1080p video with synced audio. Use for: cinematic generation with native sound, multilingual talking-head video, narrative shots where dialogue must lip-sync, premium video quality.

post/api/v1/happy-horse-1-text-to-video-1080p

Request

  • Base URL: https://api.muapi.ai
  • URL: https://api.muapi.ai/api/v1/happy-horse-1-text-to-video-1080p
  • 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

Text prompt describing the video.

webhook_urlstring uri nullable
aspect_ratio'16:9' | '9:16' | '1:1' | '4:3' | '3:4'
durationinteger

Video duration in seconds (3–15).

resolution'720p' | '1080p'

Output resolution. Price scales with resolution — see the model's pricing table.

Response

Successful Response

unknown required

Changes

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