Dora AI Video

Check a video or image generation. Returns status (pending|done|failed) and result_url when done. Wait at least 30 seconds between polls — generations take 1-5 minutes typically.

check_job

Generate a video. Defaults: seedance_2_mini, 9:16 vertical, 8s, 480p, with audio. Only ask what the user wants to create; generate straight away with these defaults, and change one only when the user asks. For character consistency across shots (e.g. a recurring person), pass extra face/body anchor photos in reference_image_urls — Seedance 2 / 2-fast use up to 7 references. MOTION CONTROL: model kling_2_6_motion transfers the motion of a driving video onto the person in your image — pass the person photo in image_url AND the driving clip URL in motion_video_url (both required); set duration to the driving clip length (billed ~11 coins/s, min 3s). Returns job_id; poll check_job until status=done.

generate_video

Generate an image. Default model: nano_banana_2 (good quality, ~10 coins, supports reference photo). Use z_image (1 coin) only if the user wants the cheapest possible result. Use nano_banana_pro (18-24) only when the user explicitly asks for face preservation or maximum quality. Default resolution 1K — never use 2K/4K unless the user explicitly asks. Default aspect ratio 1:1; generate straight away and change it only when the user asks. For multi-character or character-plus-outfit shots, pass extra anchor images in reference_image_urls — Nano Banana 2 / Pro accept up to 7 inputs. Returns job_id; poll check_job until status=done.

generate_image

List Dora generation models, cheapest-first, with per-call coin cost. Call this when the user asks what models are available, when cost matters, or when you want to verify a model name. Defaults: nano_banana_2 for images, seedance_2_mini for videos — only step up if the user explicitly asks for higher quality, face preservation, or audio.

list_models