Gemini Omni Character API: AI Image Editing

Gemini Omni Character API Reference

Endpoint

POST https://api.muapi.ai/api/v1/gemini-omni-character

Submit 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.

Parameters

Name	Type	Required	Description
descriptions	string	Yes	Describe the character's appearance, identity, style, and personality.
images_list	array	Yes	Provide exactly 1 reference image of the character. Maximum 20 MB. Must be a publicly accessible URL.
character_name	string	No	Optional display name for the character.
audio_ids	array	No	Optional list of voice profile IDs from Gemini Omni Audio to associate with this character.

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-omni-character \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"descriptions":"<descriptions>","images_list":[]}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

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-character", headers=headers, json={"descriptions":"<descriptions>","images_list":[]})
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.