What is Verbatik?
Verbatik is a powerful text-to-speech (TTS) API service that converts text into natural-sounding speech using advanced neural voice technology. Our service supports multiple languages, voices, and customization options to create high-quality audio content for various applications.
How does Verbatik work?
You simply send your text to our API, and we return an audio file or a URL to the generated audio.
What can I use Verbatik for?
Verbatik can be used for a wide range of applications, including:
Creating voiceovers for videos and presentations
Developing accessible applications for visually impaired users
Building interactive voice response (IVR) systems
Adding voice capabilities to mobile apps and websites
Creating audiobooks and podcasts
Enhancing e-learning platforms with audio content
Developing voice assistants and chatbots
Which platforms and technologies does Verbatik support?
Verbatik is platform-agnostic. Our RESTful API can be integrated with any programming language or platform that can make HTTP requests, including JavaScript, Python, PHP, Ruby, Java, C#, and more.
Account & Billing
How do I create a Verbatik account?
You can create a Verbatik account by visiting our website and clicking on the "Sign Up" button. You'll need to provide your email address and create a password, or you can sign up using your Google account.
Is there a free trial?
Yes, all new accounts receive a free allocation of character credits to test our service. This allows you to try Verbatik before committing to a paid plan.
How does billing work?
Verbatik uses a character-based billing system. Each character in your text counts toward your usage. We offer various pricing tiers based on your expected usage volume, with discounts for higher volumes.
What happens if I run out of character credits?
If you run out of character credits, your API requests will return a 402 Payment Required error. You can purchase additional credits from your dashboard at any time.
How do I purchase more character credits?
You can purchase additional character credits from your dashboard by clicking on the "Top Up Credits" button. We accept major credit cards and process payments securely through Stripe.
Can I get a custom pricing plan for high-volume usage?
Yes, we offer custom pricing plans for high-volume users. Please contact our sales team at [email protected] to discuss your specific needs.
How can I view my usage and billing history?
You can view your usage and billing history in your dashboard under the "Usage" and "Billing" sections. This includes detailed information about your API requests, character usage, and payment history.
API Usage
How do I get started with the API?
Create a Verbatik account
Generate an API token from your dashboard
Integrate the API into your application using our documentation
Start converting text to speech
How do I authenticate API requests?
All API requests require authentication using an API token. Include your API token in the Authorization header of all requests:
text
Authorization: Bearer vbt_your_api_token
What is the base URL for API requests?
The base URL for all API endpoints is:
text
Apply to documentatio...
What are the main API endpoints?
Verbatik offers two main endpoints:
/tts - Convert text to speech
/voices - List all available voices
How do I convert text to speech?
Send a POST request to the /tts endpoint with your text in the request body and appropriate headers:
text
Apply to documentatio...
POST /api/v1/tts
Authorization: Bearer vbt_your_api_token
X-Voice-ID: Matthew
Content-Type: text/plain
Hello, welcome to Verbatik!
Can I use SSML to customize the speech output?
Yes, Verbatik supports Speech Synthesis Markup Language (SSML) for advanced control over speech synthesis. You can use SSML tags to adjust pronunciation, add pauses, emphasize words, and more.
How do I get a list of available voices?
Send a GET request to the /voices endpoint:
text
Apply to documentatio...
GET /api/v1/voices
Authorization: Bearer vbt_your_api_token
What is the difference between direct audio response and URL response?
Verbatik offers two ways to receive the generated audio:
Direct Audio Response: The API returns the audio file directly in the response. This is useful for immediate playback.
URL Response: The API stores the audio file and returns a URL. This is useful when you need a persistent link to the audio.
How do I specify which voice to use?
You can specify the voice using the X-Voice-ID header in your API request. For example:
text
Apply to documentatio...
X-Voice-ID: Matthew
What languages does Verbatik support?
Verbatik supports multiple languages, including but not limited to:
English (US, UK, AU)
Spanish
French
German
Italian
Japanese
Chinese
And many more
Is there a rate limit for API requests?
Yes, API requests are subject to rate limiting to ensure fair usage. The default rate limit is 60 requests per minute, but this can be customized in your account settings.
What happens if I exceed the rate limit?
If you exceed your rate limit, the API will return a 429 Too Many Requests error.
What file format is the audio returned in?
The audio is returned in MP3 or WAV format, which is widely supported across all platforms and devices.
Technical Questions
How do I handle errors from the API?
The API returns standard HTTP status codes along with JSON error messages. Common error codes include:
401 Unauthorized: Invalid or missing API token
402 Payment Required: Insufficient character balance
429 Too Many Requests: Rate limit exceeded
400 Bad Request: Invalid request format
500 Internal Server Error: Server-side error
How can I optimize my character usage?
To optimize your character usage:
Keep your text concise and to the point
Use SSML for better control over speech synthesis
Monitor your usage in the dashboard
Is the API secure?
Yes, all API requests are encrypted using HTTPS. We also implement token-based authentication and follow security best practices to protect your data.
Can I use the API in a production environment?
Yes, Verbatik is designed for production use with high availability and reliability. Our infrastructure is built to handle high volumes of requests with minimal latency.
How do I implement proper error handling?
Always implement proper error handling in your application:
Check for sufficient character balance
Handle rate limiting with exponential backoff
Validate your input before sending to the API
Catch and handle HTTP errors appropriately
How do I secure my API token?
Keep your API token secure by:
Never exposing it in client-side code
Rotating your tokens periodically
Setting appropriate rate limits to prevent abuse
Can I use the API with serverless functions?
Yes, Verbatik works well with serverless functions like AWS Lambda, Google Cloud Functions, or Azure Functions. The API's stateless nature makes it ideal for serverless architectures.
Voice & Audio Quality
How natural do the voices sound?
Verbatik uses advanced neural text-to-speech technology that produces highly natural-sounding voices with appropriate intonation, rhythm, and emphasis.
Can I customize the voice characteristics?
Yes, you can use SSML to customize various aspects of the speech, including:
Speech rate
Pitch
Volume
Pronunciation
Pauses and breaks
Emphasis on specific words
What is the audio quality of the generated speech?
Verbatik generates high-quality MP3 audio files optimized for clarity and file size. The audio is suitable for professional applications including podcasts, videos, and interactive voice systems.
How long can the text be for a single API request?
There is a limit to how much text can be processed in a single request. For very long texts, we recommend breaking it into smaller chunks and making multiple API requests.
Integration & Development
Do you provide client libraries or SDKs?
While we don't currently offer official SDKs, our API is RESTful and easy to integrate with any programming language. We provide code examples in JavaScript, PHP, Python, and other languages in our documentation.
Can I integrate Verbatik with my existing applications?
Yes, Verbatik's RESTful API makes it easy to integrate with existing applications, regardless of the technology stack.
How do I test the API before implementing it?
You can test the API using tools like Postman or cURL before implementing it in your application. We also provide a free tier of character credits for testing purposes.
Do you have webhooks for asynchronous processing?
Currently, we don't offer webhooks, but we're considering adding this feature in the future for long-form audio generation.
Can I use Verbatik in mobile applications?
Yes, Verbatik can be used in mobile applications. However, we recommend making API calls from your server rather than directly from mobile clients to keep your API token secure.
Support & Resources
Where can I find documentation for the API?
Comprehensive API documentation is available at https://api.verbatik.com/api/documentation or in your dashboard.
How do I get support if I encounter issues?
If you encounter any issues or have questions about the API, please contact our support team at [email protected].
Do you offer technical consulting for integration?
Yes, we offer technical consulting services for complex integrations. Please contact our support team to discuss your specific needs.
Privacy & Data
How does Verbatik handle data privacy?
We take data privacy seriously. We do not store the content of your text submissions beyond what's necessary to generate the audio. All data is processed in compliance with relevant privacy regulations.
Is my data encrypted?
Yes, all data transmitted to and from our API is encrypted using HTTPS. We also implement encryption for stored data.
Do you comply with GDPR?
Yes, Verbatik is designed to be GDPR-compliant. We only collect and process the data necessary to provide our service.
How long do you store generated audio files?
If you use the URL response option, generated audio files are stored for 30 days by default. After that period, they may be automatically deleted. If you need longer retention, please contact our support team.
Can I request deletion of my data?
Yes, you can request deletion of your account and associated data at any time through your dashboard or by contacting our support team.
Future Development
What new features are you planning to add?
We're constantly improving Verbatik and plan to add features such as:
More voice options and languages
Advanced SSML capabilities
Batch processing for large texts
Voice cloning and customization
Integration with popular platforms and services
Can I request a new feature?
Yes, we welcome feature requests! Please send your suggestions to [email protected] or use the feedback form in your dashboard.
How often do you update the service?
We regularly update Verbatik with new features, improvements, and bug fixes. Major updates are announced via email and in your dashboard.
Will there be price changes in the future?
While we strive to keep our pricing stable, we may adjust our pricing structure in the future. Existing customers will always be notified well in advance of any pricing changes.