hello
#b
final geode
eager oracleBOT
Hi @final geode. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Hello! How can I assist you today?
If you’re looking for how OpenAI models typically respond to greetings, a common approach is to reply in a friendly and open manner, such as: “Hello! How can I assist you today?” This is reflected in both API response examples and reasoning summaries for chat completions, where the assistant engages the user and invites further conversation when greeted with “Hello!” or similar phrases Create chat completion response.reasoning_summary_part.done.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
Let me check the knowledge base for you again. One moment! :books:
To generate videos using Sora 2 via code, you need to use the OpenAI API’s video generation endpoints. Here’s a basic workflow and code example:
1. Set Up Your Environment
- Make sure you have an OpenAI API key.
- Install the OpenAI Python SDK (
pip install openai).
2. Create a Video with Sora 2
Here’s a Python example using the OpenAI SDK:
from openai import OpenAI
openai = OpenAI()
video = openai.videos.create(
model="sora-2",
prompt="A video of a cool cat on a motorcycle in the night",
)
print("Video generation started:", video)
You can also specify additional parameters like size (resolution) and seconds (clip length):
video = openai.videos.create(
model="sora-2",
prompt="Wide tracking shot of a teal coupe driving through a desert highway, heat ripples visible, hard sun overhead.",
size="1280x720",
seconds="8"
)
3. Poll for Completion and Download the Video
After starting the job, poll the status until it’s complete, then download the MP4:
import time
while video.status in ("in_progress", "queued"):
video = openai.videos.retrieve(video.id)
time.sleep(2)
if video.status == "completed":
content = openai.videos.download_content(video.id, variant="video")
content.write_to_file("video.mp4")
print("Wrote video.mp4")
else:
print("Video generation failed")
4. Restrictions & Tips
- Sora 2 only supports content suitable for audiences under 18.
- You cannot generate real people or use copyrighted characters/music.
- For best results, be specific in your prompt about shot type, subject, action, setting, and lighting Video generation with Sora Prompting guide.
For more details and advanced usage, see the official Sora 2 API documentation and the video generation guide.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
Let me check the knowledge base for you again. One moment! :books:
Access to Sora 2 code (meaning the ability to generate videos programmatically using Sora 2) is available through the OpenAI API, but only for users and organizations that meet certain requirements:
- API Access: You need to be an API user on usage tiers 1 through 5, and your organization must be verified. Without this, you cannot use the Sora 2 or Sora 2 Pro models via the API Model Access by Usage Tier and Verification Status.
- Verification: To get access, your API organization must go through a verification process. Instructions for this are provided in OpenAI’s documentation Model Access by Usage Tier and Verification Status.
- No Public Code Without Access: If you see people sharing Sora 2 code, it’s because they have API access and a verified organization. The code examples themselves are public in the documentation, but you need the right API credentials and access to actually use them.
If you want your own Sora 2 code:
- Sign up for OpenAI API and ensure your organization is verified.
- Once you have access, you can use the code examples from the official documentation to generate videos Video generation with Sora.
If you don’t have access yet, you won’t be able to use Sora 2 programmatically, even if you have the code samples.
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
Let me check the knowledge base for you again. One moment! :books:
Yes, after your API organization is verified and you have access to Sora 2, you will be able to use your own code to generate videos with Sora 2 via the OpenAI API. The code itself is not unique to each user—everyone uses the same API endpoints and code patterns provided in the official documentation. What makes it "your own" is that you use your API key and your prompts to create videos for your specific needs.
You can write and run code like the examples in the documentation, and as long as your organization is verified and you have the required access, the code will work for you Model Access by Usage Tier and Verification Status Video generation with Sora.