Skip to main content
Method: AudioApi#audioSpeechPost

​
Example

<?php

require 'vendor/autoload.php';

use AIStats\Sdk\Api\AudioApi;
use AIStats\Sdk\Configuration;
use AIStats\Sdk\Model\AudioSpeechRequest;

$apiKey = getenv('AI_STATS_API_KEY');
$config = Configuration::getDefaultConfiguration()
    ->setHost('https://api.ai-stats.phaseo.app/v1')
    ->setApiKey('GatewayAuth', 'Bearer ' . $apiKey);

$audioApi = new AudioApi(null, $config);

$request = new AudioSpeechRequest([
    'model' => 'openai/gpt-4o-mini-tts',
    'input' => 'Hello world',
    'voice' => 'alloy',
    'format' => 'mp3'
]);

$audioFile = $audioApi->audioSpeechPost($request);
// $audioFile is a \SplFileObject containing the audio data
file_put_contents('output.mp3', $audioFile->fread($audioFile->getSize()));

​
Key parameters

  • model (required): TTS-capable model id.
  • input (required): Text to synthesize.
  • voice: Voice preset (model-dependent, e.g., alloy).
  • format: mp3, wav, flac, etc.
  • speed: Playback speed multiplier (typically 0.25–4).

​
Returns

Audio binary (\SplFileObject)