STT (Speech to Text) - Phaseo Docs

Method: $client->generateTranscription(...) or $client->createTranscription(...)

Example

<?php

require 'vendor/autoload.php';

use Phaseo\Sdk\Phaseo;

$client = new Phaseo(getenv('PHASEO_API_KEY'));
$response = $client->generateTranscription([
    'model' => 'openai/gpt-4o-transcribe',
    'audio_url' => 'https://example.com/audio.mp3', // or 'audio_b64' for base64 data
    'language' => 'en'
]);
echo $response['text'] ?? '';

Key parameters

model (required): Transcription-capable model id.
audio_url or audio_b64 (required): Audio data (URL or base64).
language: Hint language code (e.g., en).
prompt: Optional context to improve accuracy.
temperature (0–2): Sampling randomness.
response_format: json, text, srt, verbose_json, etc.

Returns

AudioTranscriptionResponse

Last modified on July 26, 2026