Animate images to video with Gemini Omni Image to Video via the Muapi REST API. Pay per generation — no subscription needed.
POST https://api.muapi.ai/api/v1/gemini-omni-image-to-videoSubmit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.
| Name | Type | Required | Description |
|---|---|---|---|
| prompt | string | Yes | Text description of the desired motion and scene. Gemini Omni supports rich multimodal prompts including camera direction, dialogue, and ambient audio cues. |
| image_urls | array | Yes | Upload 1–7 reference images for the video. Maximum 20 MB each. |
| duration | int | No | Duration of the generated video in seconds.Options: 4, 6, 8, 10Default: 8 |
| resolution | string | No | Output video resolution. 720p and 1080p are the same price; 4K costs more.Options: 720p, 1080p, 4kDefault: "1080p" |
| aspect_ratio | string | No | Output video aspect ratio.Options: 16:9, 9:16Default: "16:9" |
| audio_ids | array | No | Up to 3 voice profile IDs returned by the Gemini Omni Audio endpoint. |
| seed | int | No | Random seed (0–2147483647). Fix for reproducibility; results may still vary due to model stochasticity.Default: 0 |
| character_ids | array | No | Up to 3 character IDs from Gemini Omni Character to feature in the video. |
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-omni-image-to-video \
-H "x-api-key: $MUAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"<prompt>","image_urls":[]}' | jq -r .request_id)
curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"import os, time, requests
API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}
r = requests.post(f"{API}/gemini-omni-image-to-video", headers=headers, json={"prompt":"<prompt>","image_urls":[]})
request_id = r.json()["request_id"]
while True:
res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
if res["status"] == "completed":
print(res["outputs"]); break
if res["status"] == "failed":
raise RuntimeError(res.get("error"))
time.sleep(3)Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.