Gemini 2.5 Pro TTS API: AI Audio Generation

Gemini 2.5 Pro TTS API Reference

Endpoint

POST https://api.muapi.ai/api/v1/gemini-2-5-pro-tts

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
scene	string	No	Optional scene description that sets the acoustic setting, e.g. "A quiet, warm room with a fireplace crackling softly."Default: ""
speakers	array	Yes	List of speaker voice configurations. Each dialogue turn references a speaker by its ID.
temperature	number	No	Sampling temperature (0-2). Higher values produce more varied delivery.Default: 1
dialogue_turns	array	Yes	Ordered list of dialogue lines. Each turn's speaker_id must match a speaker defined above. Text may include tone tags like [shouting] or [whispers].
sample_context	string	No	Optional overall tone/style, e.g. "Audiobook style narration. Tone is gentle and inviting."Default: ""

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-2-5-pro-tts \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"speakers":[],"dialogue_turns":[]}' | 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-2-5-pro-tts", headers=headers, json={"speakers":[],"dialogue_turns":[]})
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.