PoYo Sora 2
Use this skill to submit and track Sora 2 video jobs on PoYo AI.
Quick workflow
- Choose the model:
sora-2for standard Sora 2 generationsora-2-privatefor the private standard-quality variant
- Build the request body.
- Submit a POST request to
https://api.poyo.ai/api/generate/submitwith Bearer auth. - Save the returned
task_id. - Poll unified task status until the job finishes, or rely on
callback_urlif the user has a webhook.
Request rules
- Require
Authorization: Bearer <POYO_API_KEY>. - Require top-level
model. - Require
input.prompt. - Use
input.image_urlsonly for image-to-video; PoYo docs say only one image is supported. - Use
input.durationwhen the user specifies clip length; valid values are10or15. - Use
input.aspect_ratiowhen needed; valid values are16:9or9:16. - Optional stylistic control is available through
input.styleandinput.storyboard.
Model selection
sora-2
Use for:
- standard text-to-video generation
- standard image-to-video generation
- default Sora 2 jobs on PoYo
sora-2-private
Use for:
- private standard-quality variant when the user explicitly asks for it
- cases where the user's account/workflow expects the private model id
Execution
- Read
references/api.mdfor payload fields, examples, and polling notes. - Use
scripts/submit_sora_2.shto submit a task from the shell when direct API execution is appropriate. - If the user needs a raw curl example, adapt one from
references/api.md. - After submission, report the
task_idclearly so follow-up polling is easy.
Output expectations
When helping with a Sora 2 task, include:
- chosen model
- whether the request is text-to-video or image-to-video
- final payload or summarized parameters
- returned
task_idif the request was actually submitted - next step: poll status or wait for webhook