Video generation - AI Stats Docs

Methods:

client.create_video(...)
client.list_videos(...)
client.get_video(...)
client.retrieve_video_content(...)
client.get_video_download_url(...)
client.cancel_video(...)
client.delete_video(...)
client.list_video_models(...)
client.get_async_job_websocket_url(...)
client.video_websocket_url(...)
client.async_jobs.websocket_url(...)

Example

require_relative "../lib/index"

client = AIStatsSdk::AIStats.new(api_key: ENV.fetch("AI_STATS_API_KEY"))

job = client.create_video(
  model: "openai/sora-2",
  prompt: "A calm ocean at dusk"
)

jobs = client.list_videos(
  status: "queued,completed",
  limit: 2
)

websocket_url = client.video_websocket_url(job["id"], interval_ms: 1500)

The create response is an async job object. Poll status and then use content or signed download endpoints once the job is complete. Use client.video_websocket_url(...) when you want to subscribe to the documented /v1/async/video/{id}/ws lifecycle stream instead of polling only. Use client.async_jobs.websocket_url("video", job["id"], ...) when you want the generic async-jobs resource helper. Use client.get_async_job_websocket_url("video", job["id"], ...) when you want the same generic helper without going through the resource object. client.cancel_video(...) is exposed, but the public video cancel route currently returns a structured 501 not_implemented_yet error while provider-level cancellation is standardized.

​Example

Example