{"info":{"title":"ModelRunner OpenAPI schema for wan/v2.7/image-to-video/audio-driven","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":["start_image_url","driving_audio_url"],"properties":{"seed":{"type":"integer","title":"Seed","maximum":2147483647,"minimum":0,"x-order":8,"description":"Random seed for reproducible results. Omit for a random seed each run."},"prompt":{"type":"string","title":"Prompt","x-order":2,"maxLength":5000,"description":"Optional description of the motion and camera movement. The scene is already fixed by the start image and the mouth movement and action timing come from the driving audio, so use the prompt for gesture, framing and camera. Chinese and English are supported."},"duration":{"type":"integer","title":"Duration","default":5,"maximum":15,"minimum":2,"x-order":5,"description":"Length of the generated video in seconds (2-15). This is the output length, and the only length that is billed - the driving audio clip's own length never changes it."},"resolution":{"allOf":[{"$ref":"#/components/schemas/ResolutionEnum"}],"title":"Resolution","default":"1080P","x-order":4,"description":"Output video resolution. 720P bills at $0.10 per second of finished video; 1080P (default) bills at $0.15 per second."},"end_image_url":{"type":"string","title":"End Image Url","format":"uri","x-order":3,"description":"Optional closing frame. Supply it to pin where the clip ends while the driving audio times everything in between; it cannot be used on its own, without a start frame. Same formats and size limits as the start frame, and it should share the start frame's aspect ratio."},"negative_prompt":{"type":"string","title":"Negative Prompt","x-order":6,"maxLength":500,"description":"Describe content to avoid in the generated video."},"start_image_url":{"type":"string","title":"Start Image Url","format":"uri","x-order":0,"description":"The opening frame the video animates from. For lip-sync, pick a frame where the subject's face and mouth are clearly visible and unobscured. JPEG, JPG, PNG (alpha channel not supported), BMP or WEBP; width and height each between 240 and 8000 px, aspect ratio between 1:8 and 8:1, up to 20 MB. The finished clip takes its frame shape from this image."},"driving_audio_url":{"type":"string","title":"Driving Audio Url","format":"uri","x-order":1,"description":"The audio clip that drives the performance: the model uses it as the source for lip-sync and action timing, and it is the sound heard in the finished clip. WAV or MP3, 2-30 seconds, up to 15 MB. Audio longer than the requested duration is truncated to the first duration seconds; audio shorter than the requested duration leaves the rest of the clip silent, so match the two for sound throughout."},"enable_prompt_expansion":{"type":"boolean","title":"Enable Prompt Expansion","default":true,"x-order":7,"description":"When enabled, an LLM rewrites and enriches your prompt before generation. Disable to follow your exact wording."}}},"Output":{"type":"string","title":"Output","format":"uri","description":"Generated video file URL."},"ResolutionEnum":{"enum":["720P","1080P"],"type":"string","title":"ResolutionEnum","description":"An enumeration."}}}}