{"info":{"title":"ModelRunner OpenAPI schema for omnihuman/v1.5","version":"0.1.0"},"paths":{"/health-check":{"get":{"summary":"Healthcheck","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Healthcheck Health Check Get"}}},"description":"Successful Response"}},"operationId":"healthcheck_health_check_get"}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["image_url","audio_url"],"properties":{"prompt":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Prompt","x-order":2,"description":"Optional text prompt guiding the motion, gestures, and performance. Leave empty to let the audio drive the animation."},"mask_url":{"anyOf":[{"type":"string","format":"uri"},{"type":"null"}],"title":"Mask URL","x-order":3,"description":"Optional mask image. When the photo has more than one person, only the person inside the white region of the mask will be animated to speak."},"audio_url":{"type":"string","title":"Audio URL","format":"uri","x-order":1,"description":"URL of the audio track the person should speak or sing. Keep audio under 30s at 1080p, under 60s at 720p."},"image_url":{"type":"string","title":"Image URL","format":"uri","x-order":0,"description":"URL of the source photo of the person to animate."},"resolution":{"allOf":[{"$ref":"#/components/schemas/resolution"}],"title":"Resolution","default":"1080p","x-order":5,"description":"Output resolution. 1080p limits input audio to 30s; 720p allows up to 60s."},"turbo_mode":{"type":"boolean","title":"Turbo Mode","default":false,"x-order":4,"description":"Generate faster with a slight quality trade-off. No price impact."}}},"Output":{"type":"string","title":"Output","format":"uri","description":"Generated talking-head video file URL."},"resolution":{"enum":["720p","1080p"],"type":"string","title":"resolution","description":"An enumeration."}}}}