🎥 Video Generation - Oxen.ai

Video Generation

Generate a video from a text prompt. Videos can take several minutes. To find models, filter the Models page by “Text to video”.

cURL
Python

Start the generation

GEN_ID=$(curl -s -X POST \
  https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
    "model": "bytedance-seedance-2-5-text-to-video",
    "prompt": "An ox walking in a field",
    "duration": 5
  }' | jq -r '.generations[0].generation_id')

Wait for it to finish

while true; do
  STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
  case $STATUS in succeeded|failed|cancelled) break;; esac
  sleep 15
done

curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
  "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.result_url'

import os
import requests
import time

HEADERS = {
    "Authorization": f"Bearer {os.getenv('OXEN_API_KEY')}",
    "Content-Type": "application/json",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "bytedance-seedance-2-5-text-to-video",
        "prompt": "An ox walking in a field",
        "duration": 5,
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    data = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    ).json()
    if data["status"] in {"succeeded", "failed", "cancelled"}:
        break
    time.sleep(15)

print(f"Generated video: {data['result_url']}")

Parameters

model: Model name, for example bytedance-seedance-2-5-text-to-video
prompt: What to generate
duration: Length in seconds (optional, defaults vary by model)

Models can take more parameters, listed in each model’s API reference. The queue reference covers the rest of the queue API. To skip polling, listen for completion events instead.