gpt-4o-mini-tts

This documentation is valid for the following model:

• openai/gpt-4o-mini-tts

A text-to-speech model based on GPT-4o mini, supporting up to 2,000 input tokens.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

Code Example

Python

import requests

# Insert your AI/ML API key instead of <YOUR_AIMLAPI_KEY>:
api_key = "<YOUR_AIMLAPI_KEY>" 
base_url = "https://api.aimlapi.com/v1"

headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}

data = {
    "model": "openai/gpt-4o-mini-tts",
    "text": "GPT-4o-mini-tts is a small and fast model. Use it to convert text to natural sounding spoken text.",
    "voice": "coral",
}

response = requests.post(f"{base_url}/tts", headers=headers, json=data)
response.raise_for_status()

result = response.json()

print("Audio URL:", result["audio"]["url"])

JaveScript

import axios from "axios";

// Insert your AI/ML API key instead of <YOUR_AIMLAPI_KEY>:
const apiKey = "<YOUR_API_KEY>";
const baseURL = "https://api.aimlapi.com/v1";

const headers = {
  Authorization: `Bearer ${apiKey}`,
  "Content-Type": "application/json",
};

const data = {
  model: "openai/gpt-4o-mini-tts",
  text: "GPT-4o-mini-tts is a small and fast model. Use it to convert text to natural sounding spoken text.",
  voice: "coral",
};

const main = async () => {
  const response = await axios.post(`${baseURL}/tts`, data, { headers });
  console.log("Audio URL:", response.data.audio.url);
};

main().catch(console.error);

Response

Audio URL: https://cdn.aimlapi.com/generations/hedgehog/1760948488200-5a500947-2ec2-41b5-b77b-4b75c7913aad.mp3

Listen to the audio sample we generated:

API Schema

post

Authorizations

access-token

Body

application/json

modelundefined · enumRequiredPossible values:

textstring · min: 1 · max: 4096Required

The text content to be converted to speech.

voicestring · enumRequired

Name of the voice to be used

Possible values:

stylestringOptional

Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0.

response_formatstring · enumOptional

Format of the output content for non-streaming requests. Controls how the generated audio data is encoded in the response.

Default: mp3Possible values:

speednumber · min: 0.25 · max: 4Optional

Adjusts the speed of the voice. A value of 1.0 is the default speed, while values less than 1.0 slow down the speech, and values greater than 1.0 speed it up.

Default: 1

Responses

201Success

application/json

post

/v1/tts

HTTPcURLJavaScriptPython

POST /v1/tts HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 113

{
  "model": "openai/gpt-4o-mini-tts",
  "text": "text",
  "voice": "alloy",
  "style": "text",
  "response_format": "mp3",
  "speed": 1
}

201Success

{
  "metadata": {
    "transaction_key": "text",
    "request_id": "text",
    "sha256": "text",
    "created": "2025-10-20T12:12:52.407Z",
    "duration": 1,
    "channels": 1,
    "models": [
      "text"
    ],
    "model_info": {
      "ANY_ADDITIONAL_PROPERTY": {
        "name": "text",
        "version": "text",
        "arch": "text"
      }
    }
  }
}