ElevenLabs TTS Turbo 2.5 API: AI Audio Generation

ElevenLabs TTS Turbo 2.5 API Reference

Endpoint

POST https://api.muapi.ai/api/v1/elevenlabs-tts-turbo-2-5

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
prompt	string	Yes	Text to convert to speech. Maximum 40,000 characters; billing is based on trimmed length.
voice_id	string	No	ElevenLabs voice ID. Select a popular voice or paste your own custom voice ID.Options: [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object]Default: "21m00Tcm4TlvDq8ikWAM"
stability	number	No	Determines voice consistency and randomness (0 to 1, default 0.5).Default: 0.5
similarity_boost	number	No	Determines how closely the output resembles the selected voice (0 to 1, default 0.75).Default: 0.75
speed	number	No	Speech rate adjustment (0.7 to 1.2, default 1.0).Default: 1
language_code	string	No	Target language for speech. Leave empty for automatic language detection.Options: en, fr, de, ja, vi, hu, noDefault: null

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/elevenlabs-tts-turbo-2-5 \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>"}' | 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}/elevenlabs-tts-turbo-2-5", headers=headers, json={"prompt":"<prompt>"})
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.