API Documentation
Integrate natural text-to-speech into your applications with our simple REST API
Base URL
https://voicenom.com/api/v1Quick Start
Create Account
Sign up free and get 1,000 units instantly
Get API Key
Generate your key in Dashboard → API Keys
Make Request
Send text, receive audio. It's that simple!
Authentication
All API requests require authentication. Include your API key in theX-API-Keyheader with every request.
Keep your API key secure! Never expose it in client-side code or public repositories.
API Endpoints
/v1/synthesizeConvert text to natural-sounding speech audio
Request Body (JSON)
| Parameter | Type | Required | Description |
|---|---|---|---|
| text | string | Yes | Text to convert (max 10,000 characters) |
| voice | string | No | Voice ID (default: en-US-AriaNeural) |
| rate | string | No | Speaking rate: "-50%" to "+100%" (default: "+0%") |
| pitch | string | No | Voice pitch: "-50Hz" to "+50Hz" (default: "+0Hz") |
| volume | string | No | Volume: "-50%" to "+50%" (default: "+0%") |
Response
Returns an MP3 audio file with Content-Type: audio/mpeg
/voicesGet list of all available voices (no authentication required)
Returns a JSON object with voices organized by gender and region.
This endpoint is public and doesn't require an API key.
/pricingGet current pricing tiers (no authentication required)
Returns an array of pricing tier objects with name, units, and price information.
Code Examples
curl -X POST "https://voicenom.com/api/v1/synthesize" \
-H "X-API-Key: vn_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"text": "Hello! Welcome to VoiceNom.",
"voice": "en-US-AriaNeural",
"rate": "+0%",
"pitch": "+0Hz"
}' \
--output speech.mp3Popular Voices
| Voice ID | Name | Language | Gender | Style |
|---|---|---|---|---|
| en-US-AriaNeural | Aria | English (US) | Female | Most Natural |
| en-US-GuyNeural | Guy | English (US) | Male | Professional |
| en-US-JennyNeural | Jenny | English (US) | Female | Conversational |
| en-US-AvaMultilingualNeural | Ava | English (US) | Female | Multilingual |
| en-US-AndrewMultilingualNeural | Andrew | English (US) | Male | Multilingual |
| en-GB-SoniaNeural | Sonia | English (UK) | Female | Elegant |
| en-GB-RyanNeural | Ryan | English (UK) | Male | Professional |
| en-AU-NatashaNeural | Natasha | English (AU) | Female | Warm |
| es-ES-ElviraNeural | Elvira | Spanish | Female | Natural |
| fr-FR-DeniseNeural | Denise | French | Female | Natural |
| de-DE-KatjaNeural | Katja | German | Female | Natural |
| ja-JP-NanamiNeural | Nanami | Japanese | Female | Natural |
50+ voices available. Use /voices endpoint for the complete list.
Voice CloningPaid Feature
Create custom voice clones from audio samples. This premium feature is available for users who have made at least one purchase.
Endpoints
- POST
/voice-clones - GET
/voice-clones - POST
/voice-clones/:id/samples - POST
/voice-clones/:id/train - POST
/synthesize-clone
Requirements
- At least one unit purchase required
- Upload 1-10 audio samples (MP3/WAV)
- Maximum 5 voice clones per account
- Clone synthesis costs 20% more units
Pricing & Usage
How Billing Works
VoiceNom uses a simple unit-based billing system. 1 unit = 1 character (excluding whitespace).
- Units are deducted per request
- Units never expire
- No monthly subscriptions
Current Pricing
Rate Limits
API requests are rate-limited to ensure fair usage and service stability.
Rate limit headers are included in every response:X-RateLimit-Limit,X-RateLimit-Remaining,X-RateLimit-Reset
Need higher limits? Contact support@voicenom.com for enterprise plans.
Need Help?
Our team is here to help you integrate VoiceNom into your application.