Frequently asked questions
Who runs the TTS API site?
VoiceClass operates this independent storefront for the same text-to-speech API. We focus on clarity and affordability for teachers and product teams. Accounts are created per site, and we do not claim affiliation with OpenAI or other major brands. Our goal is to provide a simple, developer-friendly TTS API for accessible audio content.
What is the editorial team?
We do not have a traditional editorial team. Our content is driven by product facts and direct user needs. We prioritize honest, specific information about our API capabilities, pricing, and data policies. Our focus is on helping teachers and product teams integrate audio solutions without hype or unnecessary technical jargon.
How are voices licensed?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the raw audio data used to create the voice presets. Each generated file also carries an inaudible watermark to identify it as synthetic speech, ensuring transparency in usage.
What is CC BY 4.0?
CC BY 4.0 is a Creative Commons Attribution license. It allows our voices to use specific audio recordings while requiring proper attribution. This license ensures that the source material from LibriTTS-R is used legally and transparently. It supports the open nature of our voice library while respecting the original creators' rights.
What is LibriVox?
LibriVox is a project providing public-domain audiobook readings. We use recordings from the LibriTTS-R dataset, which includes readings from LibriVox, to create our voice presets. This ensures our voices are based on licensed recordings. LibriVox volunteers read texts freely available in the public domain, providing high-quality input for our synthesis engine.
How is my data used?
Input text is used solely to produce the requested audio file. We do not use your text for training our models or improving the API. Request metadata, including time, characters, and status, is kept strictly for billing purposes. Your data is processed to deliver the audio response and then handled according to our retention policy.
Is my input text stored?
No, your input text is not stored after generation. It is used only to produce the audio file and is not retained for training or analysis. Once the audio is generated and returned in the response, the text content is not kept on our servers, ensuring your content remains private and transient.
Is the generated audio stored?
No, the generated audio is not stored on our servers. It is returned directly in the API response for you to download or use. We do not keep a copy of the audio file after the request is complete. This ensures that your generated content remains under your control and is not archived by us.
What metadata is kept?
We keep request metadata including the time of the request, character count, and status for billing purposes. This data helps us track usage and ensure accurate charges to your account. No other personal or content data is retained. The metadata is used solely to support your account management and billing transparency.
What are the API limits?
The rate limit is 60 requests per minute per key. Before your first top-up, this limit is 10 requests per minute. Each request can handle up to 4096 characters. If you exceed the limit, requests may queue. We process requests sequentially, so load can affect speed. Longer texts should be split into parts.
Is there streaming support?
We do not offer streaming, WebSocket, or real-time partial audio support. The API returns the complete audio file upon request completion. You receive the full MP3, WAV, OPUS, FLAC, or PCM file once synthesis is done. This ensures high-quality, complete audio files rather than partial streams, simplifying integration for standard workflows.
Can I clone voices?
No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design a new one. We provide eight preset voices based on licensed recordings. If you need a specific voice, you must choose from our existing library. We do not offer voice cloning services or custom uploads.
How do I contact support?
Support is available via email only. We do not have a phone number, live chat, or on-call team. You can reach us through the contact page on our site. We aim to respond to emails promptly. For technical issues, please include your API key and request details to help us assist you faster.
Is there phone support?
No, we do not offer phone support. All customer service is handled via email. This allows us to maintain a direct, written record of your issues and solutions. You can contact us through our website’s contact page. We prioritize email support to ensure clear communication and detailed troubleshooting for all our users.
Is there live chat?
No, we do not have live chat support. Our support team is available via email only. This ensures that your queries are documented and can be addressed thoroughly without the pressure of real-time interaction. You can reach us through the contact page on our site for any assistance or questions you may have.
What is the mission?
Our mission is to help teachers and product teams build accessible audio content with a simple, developer-friendly TTS API. We focus on clarity, affordability, and ease of integration for schools and classrooms. We provide a reliable, transparent API that empowers educators and developers to create engaging audio experiences without complex infrastructure or high costs.
Who We Are
VoiceClass is built by a small editorial team that understands the daily reality of classroom audio needs. We focus on clarity and affordability, ensuring teachers and product teams can integrate accessible content without complex infrastructure.
Our mission is to provide honest, developer-friendly tools that respect educators' time. We avoid hype, offering a straightforward API that just works for generating clear speech files.
The Editorial Team
We are developers and educators who have built VoiceClass to solve a specific problem: creating accessible audio content without enterprise complexity. Our team values transparency and practical utility over marketing noise.
Our Mission
We aim to help teachers and product teams build accessible audio content with a simple, developer-friendly TTS API. Our platform focuses on clarity, affordability, and ease of integration for schools and classrooms.
Focus on Simplicity
We strip away unnecessary features to deliver exactly what you need: reliable text-to-speech generation. By keeping our interface and pricing straightforward, we ensure you can start generating audio files quickly.
Voice Licensing
VoiceClass relies on the LibriTTS-R dataset, ensuring that our synthetic voices are built from licensed recordings rather than proprietary black-box models. This foundation allows us to offer high-quality, clear speech while respecting the original creators' rights.
All voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are derived from public-domain audiobook readings. We do not alter the fundamental licensing terms, providing transparency about the source material that generates your audio.
LibriTTS-R License
The voices in our API are based on the LibriTTS-R dataset, which is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This means the original recordings are freely available for use, provided proper attribution is given to the source.
- Dataset: LibriTTS-R
- License: CC BY 4.0
- Citation required for public distribution
CC BY 4.0 Explained
Under CC BY 4.0, you are free to use, modify, and distribute the audio, even commercially. The only requirement is that you credit the original authors and the LibriVox project. This simplifies compliance for schools and product teams who need clear legal ground.
- Commercial use allowed
- Modification permitted
- Attribution required
LibriVox Source
Our voices originate from LibriVox, a platform hosting public-domain audiobooks read by volunteers. These recordings are in the public domain because their copyrights have expired. We process these readings to create the distinct voice presets available in our API, ensuring a natural and warm sound.
- Source: LibriVox public-domain audiobooks
- Volunteer narrators
- Expired copyright status
Data Policy
We use your input text solely to generate the requested audio file. Your text is not used for training our models or improving the voices. The generated audio is returned directly in the response and is not stored on our servers after delivery.
Input Text Usage
Your text is processed only to produce the specific audio file you requested. It is never used to train our models or improve voice presets.
Audio Storage Policy
Generated audio files are returned in the API response and are not stored on our servers. We do not keep copies of your spoken content after the request is complete.
Billing Metadata
We retain request metadata, including timestamp, character count, and status, solely for billing and usage tracking purposes. This data helps us accurately charge your account and manage rate limits.
Honest Limits
VoiceClass prioritizes reliable, batch-oriented synthesis for educational content and classroom materials. We focus on delivering stable audio files rather than real-time streaming, ensuring consistent quality for lesson plans and e-learning modules.
No Streaming Support
We do not offer WebSocket or streaming endpoints. Audio is generated, packaged, and returned as a complete file (mp3, wav, opus, flac, or pcm). This approach simplifies integration for static content like textbook readings or quiz audio, avoiding the complexity of managing partial audio chunks.
No Custom Voice Cloning
VoiceClass uses eight fixed presets derived from licensed LibriTTS-R recordings. We do not offer custom voice cloning, so you cannot upload your own voice or design a new one. This keeps costs predictable and ensures every generated file carries an inaudible synthetic watermark, clearly marking it as AI-generated.
- Eight preset voices (aria, nova, luna, sage, felix, milo, atlas, orion)
- No uploading personal voice samples
- No emotion tags or phoneme dictionaries
Rate Limits Explanation
Your API key allows 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up. Requests are processed sequentially, so under load, synthesis may queue slightly. This ensures fair resource distribution for all schools and product teams using the platform.
- 60 requests/minute per key after top-up
- 10 requests/minute for new accounts
- Sequential processing may cause minor delays

Contact Information
We prefer clear, asynchronous communication to ensure your questions are answered thoroughly without the noise of live queues. Our team reviews every message carefully, allowing us to provide detailed, accurate responses tailored to your specific integration needs.
By avoiding phone trees and live chat widgets, we keep our operational costs low and pass those savings directly to educators and product teams who value predictable pricing and straightforward support.
Email Support Only
All support requests are handled exclusively via email. This allows us to maintain a clear record of your technical issues and billing questions, ensuring nothing gets lost in a fast-moving chat window.
- Professional, documented responses
- No wait times for live agents
- Full context retention for complex issues
No Phone or Live Chat
We do not offer a phone number or real-time live chat. If you need immediate verbal confirmation, you may need to rely on our documentation or community resources. This approach ensures that every interaction is thoughtful and complete.
How to Reach Us
Send your inquiries to the email address listed on our contact page. Please include your API key prefix and a brief description of the issue. We aim to respond within one business day. For urgent billing matters, please specify 'Billing' in the subject line.
Our Commitment
We believe that accessible audio tools should be straightforward and affordable for schools. Our platform strips away unnecessary complexity, focusing on what matters: clear speech and easy integration for your classroom or educational product.
Transparency in Pricing
We charge a flat $10 per 1 million characters, with no hidden fees or monthly subscriptions. Failed requests are free, and your balance never expires. We accept USDT on the TRON network for top-ups.
- Flat rate: $0.01 per 1,000 characters
- No minimum spend or seats
- Failed requests are free
- Balance does not expire
Simplicity in Integration
Our API follows the same request shape as OpenAI’s speech endpoint. You can use standard OpenAI SDKs by simply changing the base URL to https://api.6wins.info/v1. This means your existing developer workflows require minimal adjustment to start generating audio.
Support for Educators
We designed VoiceClass with teachers and educational product teams in mind. Our voices are optimized for clarity, ensuring that instructional content is easy to understand. We prioritize simplicity so you can spend less time debugging code and more time creating engaging audio lessons.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This efficiency supports high-volume reading assignments without breaking the department budget.
23 languages
Any voice speaks any of these languages.
