Text to Speech
One API Call
Simplified

Create voice apps, audiobooks and accessible content with our text to speech API. 600+ natural voices in 142 languages for developers and businesses.

Recognized for Excellence

See what our users are saying about Verbatik

API PRICING

Simple, Transparent Pricing

Industry-Leading Value

Get the best value in the industry with our straightforward pricing. Perfect for businesses of all sizes, our API offers premium text-to-speech conversion at just $0.000025 per character. Scale your voice content without breaking the bank.

  • 50,000 Characters per $1
  • High-Quality TTS Voices
  • Fast TTS Speed
  • Commercial Rights
  • Simple API Integration
  • 600 Voices 142 Languages

Pay As You Go API

50,000 chars/$1

or $20 for 1M characters

For Developers

Why Developers Choose Verbatik's TTS API

Superior AI Voice API

Access 600+ natural-sounding voices powered by advanced voice AI technology

Lightning-Fast Processing

Convert millions of characters in seconds with our optimized text to voice API

142 Languages & Dialects

Reach global audiences with our comprehensive text to audio API

Simple Integration

Implement our voice AI API in just a few lines of code with clear documentation

Enterprise Scalability

Our text to speech AI API handles everything from small projects to enterprise needs

Commercial Usage Rights

Full rights to use generated audio in your commercial products

How to Get Started with Our API

Step 1

Top Up with Credits

Choose the right amount that fits your needs. You can get 10.000 Free Characters for AI voice generator API if you book a meeting with us.

Start Now

Step 2

Generate API key

Access your dashboard to create your unique secret key for secure voice.ai API authentication.

Generate Text to Speech

Step 3

Synthesize speech

Integrate the text to audio API with just a few lines of code and transform your text into natural speech.

Get Started Now

Text-to-Speech API Documentation

Complete guide to integrating TTS API with 568 voices across multiple providers

API v1.0

VerbatikText-to-Speech API Overview

High-quality neural text-to-speech with multiple voices

The Verbatik Text-to-Speech API provides high-quality neural voice synthesis Convert text to natural-sounding speech with 568 voices across 142 languages.

Key Features

  • 568 neural voices
  • 142 supported languages
  • SSML support for advanced control
  • Multiple provider support

Technical Specs

  • MP3 output format
  • 24kHz sample rate
  • Character-based billing
  • S3 storage integration

Voice Library

568
High-Quality Neural Voices
142
Languages Supported
24kHz
Sample Rate

API Endpoints

POST /api/v1/tts

Synthesize Speech

Convert text to speech using neural voices. Supports both plain text and SSML input with optional audio storage.

Request Headers

HeaderRequiredDescription
AuthorizationYesBearer token for authentication
Content-TypeYestext/plain or application/ssml+xml
X-Voice-IDOptionalVoice to use (default: Matthew)
X-Store-AudioOptionalStore audio in S3 and return URL (true/false)
Example Request (Plain Text)
curl -X POST "https://api.verbatik.com/api/v1/tts" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: text/plain" \
  -H "X-Voice-ID: Sarah" \
  -H "X-Store-Audio: true" \
  -d "Hello, this is a test of our text-to-speech API."
Example Request (SSML)
curl -X POST "https://api.verbatik.com/api/v1/tts" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/ssml+xml" \
  -H "X-Voice-ID: Emma" \
  -H "X-Store-Audio: true" \
  -d '<speak version="1.0">
    Hello, <break time="500ms"/> this is a <emphasis level="strong">test</emphasis> 
    of our text-to-speech API with <prosody rate="slow">SSML support</prosody>.
</speak>'
Example Response (Stored Audio)
{
  "success": true,
  "audio_url": "https://s3.eu-west-2.amazonaws.com/speak.verbatik.com/audio/123/uuid-filename.mp3"
}
GET /api/v1/voices

Get Available Voices

Retrieve the list of all available voices with their details including name, gender, and language.

Example Request
curl -X GET "https://api.verbatik.com/api/v1/voices" \
  -H "Authorization: Bearer YOUR_API_TOKEN"
Example Response
[
  {
    "name": "Sarah",
    "gender": "Female",
    "language_code": "en-US"
  },
  {
    "name": "Matthew",
    "gender": "Male", 
    "language_code": "en-US"
  },
  {
    "name": "Emma",
    "gender": "Female",
    "language_code": "en-US"
  }
]

Integration Examples

Ready-to-use code examples for popular programming languages and frameworks.

JavaScript/Node.js Example

async function synthesizeSpeech(text, voice, apiToken, storeAudio = true) {
    try {
        const response = await fetch('https://api.verbatik.com/api/v1/tts', {
            method: 'POST',
            headers: {
                'Authorization': `Bearer ${apiToken}`,
                'Content-Type': 'text/plain',
                'X-Voice-ID': voice,
                'X-Store-Audio': storeAudio.toString()
            },
            body: text
        });

        if (!response.ok) {
            throw new Error(`HTTP error! status: ${response.status}`);
        }

        if (storeAudio) {
            const result = await response.json();
            console.log('Audio URL:', result.audio_url);
            return result;
        } else {
            // Direct audio stream
            const audioBlob = await response.blob();
            const audioUrl = URL.createObjectURL(audioBlob);
            return { audio_url: audioUrl };
        }

    } catch (error) {
        console.error('TTS synthesis failed:', error);
        throw error;
    }
}

// Usage example
synthesizeSpeech(
    'Hello, this is a test of our text-to-speech API.',
    'Sarah',
    'YOUR_API_TOKEN'
).then(result => {
    console.log('Success:', result);
}).catch(error => {
    console.error('Error:', error);
});

Available Voices

Browse our collection of 568 neural voices across 142 languages from multiple providers.

568
Total Voices
Neural Quality
142
Languages
Global Coverage
24kHz
Sample Rate
High Fidelity

Voice Browser

Use the Voice Library to browse, filter, and test all available voices with audio previews.

af-ZA 2 voices
Sample: Adri, Willem
am-ET 2 voices
Sample: Mekdes, Ameha
ar-AE 2 voices
Sample: Fatima, Hamdan
ar-BH 2 voices
Sample: Laila, Ali
ar-DZ 2 voices
Sample: Amina, Ismael
ar-EG 2 voices
Sample: Salma, Shakir

Troubleshooting & Error Handling

HTTP Error Codes

CodeError TypeDescriptionSolution
400Bad RequestInvalid SSML or request formatCheck SSML syntax and headers
401UnauthorizedMissing or invalid API tokenVerify Authorization header
402Payment RequiredInsufficient character balanceTop up account or reduce text length
422Unprocessable EntityValidation errorsCheck request parameters
429Too Many RequestsRate limit exceededWait before making more requests
500Internal Server ErrorService unavailableTry again later or contact support

Common Issues & Solutions

"Invalid SSML format"

  • Ensure SSML starts with <speak> and ends with </speak>
  • Check for properly closed tags
  • Validate XML syntax
  • Use proper Content-Type header for SSML

"Voice not found"

  • Use the /api/v1/voices endpoint to get valid voice names
  • Check voice name spelling and case sensitivity
  • Ensure the voice supports the target language
  • Try with a default voice like "Matthew" or "Sarah"

"Audio quality issues"

  • Use neural voices for best quality
  • Check text for special characters or formatting
  • Use SSML for pronunciation control
  • Try different voices for comparison

SSML Quick Reference

Common SSML Tags

<break time="500ms"/> - Add pause
<emphasis level="strong"> - Emphasize text
<prosody rate="slow"> - Control speed
<prosody pitch="high"> - Control pitch

Example Usage

<speak version="1.0">
  Hello <break time="1s"/>
  <emphasis level="strong">world</emphasis>
</speak>

Need Help?

Our support team is here to help you integrate the TTS API successfully.

Voice Cloning API Documentation

Advanced AI-powered multilingual voice cloning technology

API v1.0

Voice Cloning API Overview

Advanced AI-powered multilingual voice cloning technology

The Voice Cloning API provides state-of-the-art text-to-speech voice cloning capabilities powered by advanced AI technology. Clone any voice using a sample audio file and generate speech in multiple languages with remarkable accuracy and naturalness.

Key Features

  • 14 supported languages
  • High-quality voice cloning
  • Multiple audio formats
  • Voice enhancement options

Technical Specs

  • Max text: 3,000 characters
  • Max audio: 50MB
  • 2x character billing rate
  • S3 storage integration

API Endpoints

POST /api/v1/voice-cloning

Clone Voice

Clone a voice using provided text and speaker audio. Supports both file uploads and URL-based audio inputs.

Request Parameters

ParameterTypeRequiredDescription
textstringYesText to synthesize (max 3000 characters)
languagestringYesTarget language code (see supported languages)
speaker_audiofileYes*Audio file for voice cloning (max 50MB)
speaker_audio_urlstringYes*URL to audio file for voice cloning
cleanup_voicebooleanNoApply denoising to speaker audio (default: true)

*Either speaker_audio or speaker_audio_url is required.

Example Request (cURL)
curl -X POST "https://api.verbatik.com/api/v1/voice-cloning" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: multipart/form-data" \
  -F "text=Hello, this is a test of voice cloning technology." \
  -F "language=en" \
  -F "speaker_audio=@/path/to/speaker.wav" \
  -F "cleanup_voice=true"
Example Response
{
  "success": true,
  "audio_url": "https://s3.eu-west-2.amazonaws.com/speak.verbatik.com/voice-cloning/uuid-filename.wav",
  "characters_used": 94,
  "remaining_balance": 9906,
  "language": "en"
}
GET /api/v1/voice-cloning/languages

Get Supported Languages

Retrieve the list of supported languages for voice cloning.

Example Request
curl -X GET "https://api.verbatik.com/api/v1/voice-cloning/languages" \
  -H "Authorization: Bearer YOUR_API_TOKEN"
Example Response
{
  "success": true,
  "languages": {
    "en": "English 🇺🇸",
    "fr": "French 🇫🇷",
    "de": "German 🇩🇪",
    "es": "Spanish 🇪🇸",
    "it": "Italian 🇮🇹",
    "pt": "Portuguese 🇵🇹",
    "cs": "Czech 🇨🇿",
    "pl": "Polish 🇵🇱",
    "ru": "Russian 🇷🇺",
    "nl": "Dutch 🇳🇱",
    "tr": "Turkish 🇹🇷",
    "ar": "Arabic 🇦🇪",
    "zh-cn": "Mandarin Chinese 🇨🇳",
    "hi": "Hindi 🇮🇳"
  }
}
GET /api/v1/voice-cloning/info

Get Service Information

Get detailed information about the voice cloning service capabilities and limitations.

Example Request
curl -X GET "https://api.verbatik.com/api/v1/voice-cloning/info" \
  -H "Authorization: Bearer YOUR_API_TOKEN"
Example Response
{
  "success": true,
  "service": "Verbatik Voice Cloning",
  "description": "Advanced AI-powered multilingual voice cloning technology",
  "supported_formats": ["wav", "mp3", "m4a", "ogg", "flv"],
  "max_text_length": 3000,
  "max_audio_size": "50MB",
  "character_rate": "2x (voice cloning uses double character rate)",
  "min_audio_duration": "6 seconds recommended",
  "languages": { ... }
}

Integration Examples

Ready-to-use code examples for popular programming languages and frameworks.

JavaScript/Node.js Example

const FormData = require('form-data');
const fs = require('fs');
const fetch = require('node-fetch');

async function cloneVoice(text, audioFile, language, apiToken) {
    const formData = new FormData();
    formData.append('text', text);
    formData.append('language', language);
    formData.append('speaker_audio', fs.createReadStream(audioFile));
    formData.append('cleanup_voice', 'true');

    try {
        const response = await fetch('https://api.verbatik.com/api/v1/voice-cloning', {
            method: 'POST',
            headers: {
                'Authorization': `Bearer ${apiToken}`,
                ...formData.getHeaders()
            },
            body: formData
        });

        if (!response.ok) {
            throw new Error(`HTTP error! status: ${response.status}`);
        }

        const result = await response.json();
        console.log('Voice cloning successful:', result);
        return result;

    } catch (error) {
        console.error('Voice cloning failed:', error);
        throw error;
    }
}

// Usage example
cloneVoice(
    'Hello, this is a test of voice cloning technology.',
    '/path/to/speaker.wav',
    'en',
    'YOUR_API_TOKEN'
).then(result => {
    console.log('Audio URL:', result.audio_url);
}).catch(error => {
    console.error('Error:', error);
});

Supported Languages

The Voice Cloning API supports 14 languages for high-quality voice synthesis.

EN
English 🇺🇸
en
FR
French 🇫🇷
fr
DE
German 🇩🇪
de
ES
Spanish 🇪🇸
es
IT
Italian 🇮🇹
it
PT
Portuguese 🇵🇹
pt
CS
Czech 🇨🇿
cs
PL
Polish 🇵🇱
pl
RU
Russian 🇷🇺
ru
NL
Dutch 🇳🇱
nl
TR
Turkish 🇹🇷
tr
AR
Arabic 🇦🇪
ar
ZH-CN
Mandarin Chinese 🇨🇳
zh-cn
HI
Hindi 🇮🇳
hi

Troubleshooting & Error Handling

HTTP Error Codes

CodeError TypeDescriptionSolution
400Bad RequestInvalid request parametersCheck parameter format and values
401UnauthorizedMissing or invalid authenticationVerify API token in Authorization header
402Payment RequiredInsufficient character balanceTop up your account or reduce text length
413Payload Too LargeAudio file exceeds size limitReduce file size to under 50MB
422Unprocessable EntityValidation errorsCheck the errors field in response
429Too Many RequestsRate limit exceededWait before making more requests
500Internal Server ErrorService unavailableTry again later or contact support

Common Issues & Solutions

"Invalid speaker audio file"

  • Check file format (must be wav, mp3, m4a, ogg, or flv)
  • Ensure file size is under 50MB
  • Verify file is not corrupted
  • Make sure the file contains actual audio data

"Voice cloning timed out"

  • The service has a 5-minute timeout
  • Try with shorter text or smaller audio files
  • Check if the audio file is too large or complex
  • Retry the request after a few minutes

"Insufficient character balance"

  • Voice cloning uses 2x character rate
  • Check user's available character balance
  • Consider upgrading user's plan
  • Reduce text length to fit within available credits

"Unsupported language"

  • Use the /voice-cloning/languages endpoint to get supported languages
  • Ensure language code is lowercase (e.g., 'en', not 'EN')
  • Check for typos in the language code
  • Refer to the supported languages section above

Security Best Practices

API Token Security

Store API tokens securely and never expose them in client-side code

HTTPS Only

Always use HTTPS for API requests to ensure data encryption

Need Help?

Our support team is here to help you integrate the Voice Cloning API successfully.

Integrate with Your Favorite Tools

Connect Verbatik's powerful Text to Speech API with thousands of apps through Zapier's automation platform.

Instant conversion of text into speech

Effortlessly transform text to natural-sounding speech with our innovative instant conversion tool

Over 600+ Speech Voices

Choose from 600+ realistic AI voices for diverse text-to-speech conversions

Supports 142 languages and accents

Providing broad linguistic diversity with support for 142 languages and accents

Allows customization of the voices

Customization of AI voices including rate, pitch, volume, and pronunciations

Download options in MP3 and WAV audio file formats

Offering audio downloads in high-quality MP3 and WAV formats for versatile usage

Commercial and broadcast rights

Commercial and broadcast rights available for wide-reaching audio distribution

How Verbatik can Help You

AI Voices in Every Language and Accent in the World

Transform Your Articles into Engaging Audio

Testimonials

Hear from our customers

Ricky G.

Ricky G.

Content Creator

I liked that verbatik has some of the most realistic voices on the market. There is a large amount and many ways to customize all of the AI voices.

Juan Carlos V.

Juan Carlos V.

Media Production

I've found Verbatik to be a game-changer in the realm of text-to-speech. The platform is user-friendly, and the voice outputs are impressively lifelike. Whether I'm working on a presentation, video, or just experimenting, Verbatik has consistently delivered high-quality audio that adds value to my projects.

Boris S.

Boris S.

Private Tutor

I discovered VERBATIK when I was looking for a way to create voiceovers for multiple dialogues and monologues for personal use and it provided a good quality service for low price.

Zoe D.

Zoe D.

Student

Verbatik is relatively easy to use and understand and gives the quick text-to-speech results I wanted. The audio was used to narrate an educational video and was easy to export!

Verified Reviewer

Verified Reviewer

Broadcast Media

The broad range of AI voices and the ability to personalize the voice experience is very valuable to me as a content creator. I look forward to using it on a regular basis and exploring more tools that can optimise my content production process.

Aswin V.

Aswin V.

Technical Associate

Verbatik software is a user-friendly software that easily converts text into speech. The accuracy of the transcription is really amazing. There are different customization options. available. we can change the speaker. it supports different languages.

FAQ

Answers to all your questions

Experience AI-Powered Voice

Create Your Account Today

Unlock the power of lifelike text-to-speech technology. Sign up now and transform your content with natural-sounding voices.