Gemini Omni Profile API: other

Gemini Omni Profile API Reference

Endpoint

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

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
audio_id	string	Yes	Preset voice to use as the base for this profile.Options: achernar, achird, algenib, algieba, alnilam, aoede, autonoe, callirrhoe, charon, despina, enceladus, erinome, fenrir, gacrux, iapetus, kore, laomedeia, leda, orus, puck, pulcherrima, rasalgethi, sadachbia, sadaltager, schedar, sulafat, umbriel, vindemiatrix, zephyr, zubenelgenubi
name	string	Yes	Name for this voice profile. Maximum 210 characters.
voice_description	string	No	Describe the voice timbre, style, and emotion. Maximum 20,000 characters.
example_dialogue	string	No	A short sample sentence the voice would say. Maximum 120 characters.

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-omni-audio \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_id":"achernar","name":"<name>"}' | 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-audio", headers=headers, json={"audio_id":"achernar","name":"<name>"})
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.