Lumoz TTS
Flagship neural text-to-speech & instant voice cloning engine by Lumoz AI. Supports custom voice cloning from audio samples (reference_audio or lumoz_clone_voice), 10 v4 studio voices, inline emotion directing [whispers], and automatic 90+ language synthesis (including Bengali).
API endpoint
POST
https://lumozai.com/api/v4/run
Use this endpoint to run the model with your parameters. Authentication is required using your API key.
Sample code (PHP cURL)
PHP (cURL)
<?php
// API endpoint URL
$apiUrl = 'https://lumozai.com/api/v4/run';
// Your API key
$apiKey = 'YOUR_API_KEY';
// Model parameters
$params = [
'model_id' => 'lumoz-tts',
'text' => 'Welcome to Lumoz TTS. Experience studio-grade neural voice synthesis with natural emotional nuance, human cadence, and expressive delivery.',
'voice_id' => 'lumoz-aria',
'reference_audio' => '',
'stability' => 0.38,
'similarity_boost' => 0.8,
'style' => 0.2,
'speed' => 1,
'format' => 'mp3',
'turbo' => false,
];
// Initialize cURL session
$curl = curl_init();
// Set cURL options
curl_setopt_array($curl, [
CURLOPT_URL => $apiUrl,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_POSTFIELDS => $params,
CURLOPT_HTTPHEADER => [
'Accept: application/json',
'Authorization: Bearer ' . $apiKey
]
]);
// Execute the request
$response = curl_exec($curl);
$httpCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
// Check for errors
if (curl_errno($curl)) {
echo 'cURL Error: ' . curl_error($curl);
} else {
// Process the response
$result = json_decode($response, true);
if ($httpCode == 200 && isset($result['success']) && $result['success']) {
// Handle successful response
echo 'Model output: ';
print_r($result['data']['output']);
} else {
// Handle error response
echo 'Error: ' . ($result['message'] ?? 'Unknown error');
}
}
// Close cURL session
curl_close($curl);
Request parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model_id |
string | Required | The ID of the model to run (lumoz-tts) |
api_key |
string | Required | Your API key for authentication (sent via Bearer token in the Authorization header) |
text |
string | Required | The text or script to convert into high-fidelity speech (up to 5,000 characters). Supports bracketed performance directing tags (e.g. [whispers], [said excitedly]). |
voice_id |
string | Optional | Curated studio voice personality or custom voice ID. |
reference_audio |
string | Optional | Optional: Paste a clean 10–120s voice recording URL to instantly clone that voice and synthesize the script in 90+ languages (+$0.25 one-time clone fee). |
stability |
number | Optional | 0.38 is tuned for natural v4 human breathing and micro-inflections. Higher values produce steadier delivery. |
similarity_boost |
number | Optional | Enhances voice fidelity and likeness to the authentic studio or cloned voice profile. |
style |
number | Optional | Amplifies natural speaker character and conversational emotion (0.20 recommended for v4). |
speed |
number | Optional | Speech tempo multiplier. 1.0x is natural human pace. |
format |
string | Optional | Output audio format. |
turbo |
boolean | Optional | Switch to Lumoz TTS v4 Turbo for sub-second real-time conversational agents and voice bots (50% lower rate). |
Response format
JSON
{
"success": true,
"data": {
"output": "https://lumozai.com/storage/outputs/example.png"
}
}
Modell-Preise
Zahlen Sie nur für das, was Sie ausführen. Die Kosten werden direkt von Ihrem Guthaben abgezogen – ohne wiederkehrende Bindung.
Neural Voice Synthesis Rates
Billed dynamically per character synthesized • Up to 5,000 chars per request
Studio HD v4 (Flagship)
Standard
$0.36 / 1K chars
$0.036 per 100 chars • $0.015 min
Turbo Low-Latency v4
50% Off
$0.18 / 1K chars
$0.018 per 100 chars • $0.010 min
Kostenschätzer
Studio HD v4 ($0.36/1K chars)
100 K characters
Geschätzte Gesamtkosten
$360.00
Automatische Sofortrückerstattung bei Fehlern • Guthaben 1 Jahr gültig