#Sora ai 2
1 messages · Page 1 of 1 (latest)
Hi @regal quartz. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
To generate a video of an emoji eating jam using Sora 2, you can use the OpenAI Video API with the Sora 2 model. Here’s how you can do it:
Example API Request
You’ll need to send a POST request to the /videos endpoint with a descriptive prompt. Here’s a sample using curl:
curl -X POST "<https://api.openai.com/v1/videos"> \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F prompt="A cute emoji character happily eating jam with a spoon, bright colors, simple background." \
-F model="sora-2" \
-F size="1280x720" \
-F seconds="8"
- prompt: Describe the scene you want (e.g., "A cute emoji character happily eating jam with a spoon, bright colors, simple background.").
- model: Use
sora-2for fast, flexible generation. - size: Choose a supported resolution, such as
1280x720. - seconds: Set the duration (e.g., 8 seconds).
What Happens Next
- The API will return a job ID and status.
- Poll the status or use webhooks until the job is complete.
- Download the finished MP4 video using the provided endpoint.
Note: Sora 2 does not support generating videos with real people or copyrighted characters, but an emoji character is allowed. Make sure your prompt is clear and specific for best results. You can also start from an image if you want to use a specific emoji style as the first frame, but the image must not depict real people and must match the video resolution requirementsVideo generation with Sora Use image references.
If you need help with the code in Python or JavaScript, let me know!
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
@regal quartz Kapa.ai is still learning and improving, please let me know how I did by reacting below.
Mujhe so sora 2.0 chalana hai