Cloud Text-to-Speech API with 8 Licensed Voices

By VoxClass editorial team · Updated 2026-11-18

VoxClass is an independent cloud text-to-speech API designed for educators and methodologists who need to convert textbooks, lesson plans, and learning materials into audio. We provide a simple, affordable solution that helps teachers save time and make content accessible without requiring complex software or streaming infrastructure.

Our service relies on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings, ensuring clear, honest content without hype. We focus on concrete workflows for schools, offering fixed voice presets, email support, and transparent pricing. Read on to understand how we handle your data, our technical limitations, and why our API is tailored for educational needs.

Cloud Text-to-Speech API with 8 Licensed Voices

Frequently asked questions

Who runs this site?

VoxClass is an independent storefront for a text-to-speech API. We provide a simple, affordable API tailored for educators and methodologists. This site is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.

How are voices licensed?

Our eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated audio file carries an inaudible watermark that marks it as synthetic speech, ensuring transparency about the origin and nature of the voice synthesis.

Is my data safe?

Input text is used only to produce the audio and is not used for training. Request metadata, including time, characters, and status, is kept for billing purposes. Generated audio is returned in the response and is not stored on our servers after delivery.

Do you store audio files?

No. Generated audio is returned directly in the API response and is not stored on our servers. Only request metadata (time, characters, status) is retained for billing purposes. You receive the file immediately, and we do not keep a copy of your generated content.

How do I contact support?

Support is available by email only. We do not offer phone support or live chat. You can reach our team via the contact page or by emailing us directly regarding your account, billing, or technical questions about the API integration.

Is there a phone number?

No, there is no phone number for VoxClass. All customer support is handled via email. We do not maintain a direct line for voice calls, so please use the email contact method for any inquiries regarding your account or service usage.

Are there any certifications?

We do not hold SOC 2, HIPAA, or GDPR certificates, nor do we offer an SLA or uptime guarantee. We are an independent service without enterprise contracts or on-premise installation options. Our focus is on providing a straightforward, affordable API for educational content conversion.

Is this an official OpenAI site?

No, this is not an official OpenAI site. We are an independent storefront. Our API endpoint shape matches the OpenAI speech endpoint, so OpenAI SDKs work by changing the base URL, but we are not affiliated with OpenAI or any other major brand.

What is the editorial policy?

We are honest and specific, avoiding hype. We do not claim to be the best, fastest, or most realistic. Comparisons are based on published facts with dates. We never present this site as official for another brand and only mention competitors in comparison contexts.

Do you offer refunds?

Failed requests are free, and the charge is returned in full if synthesis fails. There are no monthly plans or subscriptions, so refunds for unused credit are not typically applicable. Your balance does not expire, and you only pay for successful character generation.

Is the site secure?

We use standard secure connections for API requests and account management. Authentication is handled via a Bearer token.

Can I trust the voices?

Yes. Our voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain readings. Every file includes an inaudible watermark marking it as synthetic. We do not imitate real people, celebrities, or politicians, ensuring clear and trustworthy synthetic speech for your educational materials.

Where are servers located?

We do not offer data-center choices or specify exact server locations. Our service is cloud-based, and we do not provide an on-premise install option. The API endpoint is hosted at https://api.play4447.com/v1, and we do not guarantee specific geographic data residency.

Do you have a privacy policy?

We do not explicitly list a separate privacy policy document, but our data practices are defined by our facts: input text is not used for training, and audio is not stored. Only request metadata is kept for billing. Contact us via email for specific data queries.

Our Editorial Team

Sound wave illustration for: Our Editorial Team

VoxClass is built by educators and technical reviewers who understand the specific needs of classrooms and methodologists. Our team validates that voice presets like Luna and Sage effectively support storytelling and instructional content, ensuring the API meets the practical demands of teaching materials.

Expert reviewers and educators

Expert reviewers and educators

Our reviewers are active in the education sector, validating that voices like Luna and Sage effectively support storytelling and instructional content. They test the API against real-world textbook and lesson plan workflows to ensure reliability for teachers and methodologists.

Focus on clear, honest content

Focus on clear, honest content

We prioritize specific, verifiable information over marketing fluff. Every claim on this page is backed by the technical facts of the VoxClass API, from voice licensing to character limits, helping educators make informed decisions about audio accessibility tools.

No hype or superlatives

No hype or superlatives

We do not claim to be the 'best' or 'fastest' TTS service. Our content avoids superlatives, focusing instead on what the API actually does: converting up to 4096 characters of text into audio files using eight licensed voices at a fixed price.

Voice Licensing and Sources

Sound wave illustration for: Voice Licensing and Sources

Our voices are generated from licensed recordings of LibriTTS-R, a high-quality dataset derived from LibriVox. These sources ensure that our synthetic speech is built on authentic, human performances rather than purely algorithmic synthesis.

LibriTTS-R licensed recordings

LibriTTS-R licensed recordings

The core of our voice models comes from the LibriTTS-R dataset, which provides clear, high-fidelity audio samples.

  • High-fidelity source audio
  • Natural intonation patterns

CC BY 4.0 license

We utilize recordings under the Creative Commons Attribution 4.0 International license. This transparent licensing model ensures that the source material is legally clear and accessible, providing educators with confidence in the provenance of the audio they generate.

LibriVox public domain sources

The underlying recordings originate from LibriVox, a project dedicated to public domain audiobooks. By building on these established public domain readings, we maintain a library of voices that are historically grounded and free from proprietary restrictions on the source material.

Data Privacy Policy

Sound wave illustration for: Data Privacy Policy

When you send text to our API, it is processed solely to generate the requested audio file. We do not retain the input text or the resulting audio after the response is delivered to your application.

Request metadata, including the timestamp, character count, and status, is stored exclusively for billing accuracy. This minimal data ensures you are charged correctly for the 4096-character limits and usage volumes without retaining the actual educational content you convert.

Text used only for generation

Input text is transmitted to the engine, converted into speech, and the audio is returned to your request. The original text is not stored after the audio file is generated and returned, ensuring your specific textbook excerpts or lesson materials are not kept on our servers.

No training on user data

We do not use your input text or generated audio to train our voice models or improve our base engine. Your educational content remains distinct from our training data, preserving the integrity and ownership of your specific teaching materials.

Metadata kept for billing

To ensure accurate billing for your 1 million character credits, we retain minimal request metadata. This includes the request time, character count, and status code. This data is used strictly to calculate your balance and verify that failed requests are refunded correctly.

Technical Limitations

Sound wave illustration for: Technical Limitations

VoxClass delivers audio files via standard HTTP responses, meaning you receive the complete file only after synthesis finishes. There is no real-time streaming or WebSocket support, so partial audio chunks are not available during generation. This design keeps the API simple and reliable for batch processing lesson materials.

No streaming or WebSocket

Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real-time for long texts, but short phrases take a few seconds. You must handle the final audio file delivery in your application logic.

No custom voice cloning

We do not offer voice cloning or uploading of your own voice samples. The service uses eight fixed presets based on licensed LibriTTS-R recordings. This ensures consistent quality without the complexity of managing custom voice models or additional training data.

  • Predefined voice profiles only
  • No uploading of voice samples
  • Consistent output quality

Fixed voice presets only

The API provides exactly eight voice presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. You cannot create new voices or adjust emotional tags. Each voice supports all 23 languages, allowing educators to select a tone for their specific teaching context.

  • Aria, Nova, Luna, Sage (Female)
  • Felix, Milo, Atlas, Orion (Male)
  • 8 total presets
Technical Limitations

Support and Contact

Sound wave illustration for: Support and Contact

We prioritize direct, clear communication for educators and methodologists who need reliable support without the noise of automated systems.

Email support only

All support requests are managed exclusively via email. This ensures every ticket is tracked, documented, and addressed by a human reviewer who understands the specific needs of educational content creation.

No phone or live chat

We do not offer phone numbers or live chat widgets. This allows us to maintain focus on technical accuracy and provide detailed, written responses that you can reference later during your development or lesson planning process.

Response within 24 hours

During peak academic periods or high API usage, response times may vary slightly, but we ensure no request remains unanswered indefinitely.

Our Commitment to Education

Sound wave illustration for: Our Commitment to Education

VoxClass is built for educators who need reliable audio for textbooks and lesson plans without complex software. Our API charges $0.01 per 1,000 characters, making it affordable for schools with limited budgets. You can start with a free $0.50 trial credit, valid for 7 days, to test integration before committing.

Affordable pricing for schools

We offer simple, transparent pricing with no monthly plans or minimum spend. Top-ups are processed via USDT on the TRON network, credited automatically within minutes. Failed requests are free, ensuring you only pay for successful audio generation.

  • $0.01 per 1,000 characters
  • $0.50 free trial credit for 7 days
  • No monthly plans or subscriptions
  • Failed requests are free

Easy integration for teachers

Teachers can convert learning materials into audio using a standard POST request to our API. The endpoint matches the OpenAI format, so existing tools often work with minimal code changes. You can generate MP3, WAV, FLAC, OPUS, or PCM files directly from your lesson plans.

  • Standard JSON API endpoint
  • Compatible with OpenAI SDKs
  • Generates MP3, WAV, FLAC, OPUS, PCM
  • No complex software required

Accessible content for all

Our service supports 23 languages, allowing educators to create audio content for diverse student populations. With 8 licensed voices, you can choose a tone that fits the material.

  • Supports 23 languages
  • 8 distinct voice presets
  • Clear, distinct narration styles
  • Ideal for diverse classrooms

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Empowering educators with adaptable frameworks to nurture critical thinking and foster genuine curiosity in every learner.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. ISO 639 language codes
  3. MDN: Web Speech API
  4. OpenAI API reference: create speech
  5. LibriTTS-R paper (arXiv 2305.18802)
  6. TRON developer hub: TRC-20
  7. openai-python on GitHub
  8. Node.js documentation
  9. Python documentation
  10. openai-node on GitHub
  11. Creative Commons Attribution 4.0
  12. FFmpeg documentation

More on this site