/tts (Start TTS)

This is the main endpoint for creating new text-to-speech tasks.

When you send a request, the API validates your inputs and queues the generation task. Because this process is asynchronous, the endpoint immediately returns a generation_id upon success.

You must then use this ID to poll the Status Endpoint to retrieve your audio URL once it's ready.

---

Base URL

https://api.audixa.ai/v2

Request

POST /tts

---

Request Body

All parameters are sent as a JSON object in the request body.

Parameter	Type	Required	Description
text	string	Yes	The text you want to convert to speech. Must be at least 30 characters.
voice	string	Yes	The Voice ID to use for generation. See the Voice Library for all available IDs.
model	string	No	The model to use. Can be "base" or "advance". Defaults to "base".
speed	number	No	Playback speed. Can range from 0.5 to 2.0. Defaults to 1.0.

---

Advance Model Parameters

These parameters are only used if you set "model": "advance". They will be ignored by the Base model. See our Models Guide for details.

Parameter	Type	Default	Description
emotion	string	"neutral"	The emotion to apply. Valid options: "neutral", "happy", "sad", "angry", "surprised".
temperature	number	0.9	Controls randomness. Lower values are more deterministic. Range: 0.7 to 0.9.
top_p	number	0.9	Nucleus sampling. Range: 0.7 to 0.98.
do_sample	boolean	false	Set to true to enable sampling for more varied outputs.

---

Code Examples

cURL

curl -X POST "https://api.audixa.ai/v2/tts" \
     -H "x-api-key: YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
          "text": "Welcome to Audixa AI, your affordable and powerful text-to-speech solution.",
          "voice": "am_ethan",
          "model": "base",
          "speed": 1.1
        }'

Python

import requests

api_url = "https://api.audixa.ai/v2/tts"
api_key = "YOUR_API_KEY"

headers = {
    "x-api-key": api_key,
    "Content-Type": "application/json"
}

data = {
    "text": "Welcome to Audixa AI, your affordable and powerful text-to-speech solution.",
    "voice": "am_ethan", # Voice IDs are case-insensitive
    "model": "base",
    "speed": 1.1
}

response = requests.post(api_url, headers=headers, json=data)

if response.status_code == 201:
    result = response.json()
    print("Generation started:", result)
    # Save this ID: result['generation_id']
else:
    print(f"Error: {response.status_code}")
    print(response.json())

JavaScript (Node.js)

// This code must be run in a secure backend environment
// to protect your API key.

const fetch = require('node-fetch'); // or use native fetch in Node 18+

const API_URL = "https://api.audixa.ai/v2/tts";
const API_KEY = "YOUR_API_KEY";

const generateAudio = async () => {
  const payload = {
    text: "Welcome to Audixa AI, your affordable and powerful text-to-speech solution.",
    voice: "am_ethan",
    model: "base",
    speed: 1.1
  };

  try {
    const response = await fetch(API_URL, {
      method: "POST",
      headers: {
        "x-api-key": API_KEY,
        "Content-Type": "application/json"
      },
      body: JSON.stringify(payload)
    });

    const result = await response.json();

    if (response.status === 201) {
      console.log("Generation started:", result);
      // Save this ID: result.generation_id
    } else {
      console.error(`Error (${response.status}):`, result.detail);
    }
  } catch (error) {
    console.error("Request failed:", error);
  }
};

generateAudio();

---

Responses

✅ Success

A successful request will return a 201 Created status code along with the unique ID for your generation task.

Response: 201 Created

{
  "generation_id": "base_27b4695b-017f-4b6e-8121-03264624479c"
}

❌ Errors

This endpoint will return standard HTTP error codes:

Status Code	Error Code	Description
400 Bad Request	Invalid voice ID	The voice ID you sent does not exist.
400 Bad Request	Invalid Emotion	You sent an emotion not in the allowed list for the Advance model.
400 Bad Request	Text must be...	Your text input was too short.
401 Unauthorized	Invalid API Key	Your x-api-key is missing or incorrect.
402 Payment Required	Insufficient Balance	Your account does not have enough credits to perform this generation.
403 Forbidden	This voice is...	Your plan does not have access to this premium voice.

---

Next Steps

Once you have your generation_id, you must poll the Get Status Endpoint to check on the progress and retrieve your audio file.