{"info":{"title":"ModelRunner OpenAPI schema for pixverse/lipsync","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":["video_url","audio_url"],"properties":{"audio_url":{"type":"string","title":"Audio URL","format":"uri","x-order":1,"description":"URL of the speech track the speaker should appear to say. Required. The delivered video carries this track as its soundtrack, so a silent source clip comes back playable. A source clip longer than this track is trimmed to it; there is no setting for the reverse case, where the track outruns the clip. PixVerse documents support for multiple languages and for audio types beyond dialogue — including singing and advertisement reads — and a 60-second maximum on both inputs."},"video_url":{"type":"string","title":"Video URL","format":"uri","x-order":0,"description":"URL of the source video to re-sync. The result keeps this clip's frame size and frame rate exactly: no rescale and no frame-rate normalisation. Source video running past the end of the audio is trimmed to the speech; there is no setting for the reverse case, where the audio outruns the clip."}}},"Output":{"type":"string","title":"Output","format":"uri","description":"URL of the generated MP4: the source footage with the speaker's mouth re-animated to the supplied audio, at the input's frame size and frame rate, carrying that audio as its soundtrack."}}}}