Discover the Technology Behind Our Text-to-Speech Platform

By VoxApp editorial team · Updated 2026-11-19

This page outlines the operational model, technical specifications, and data policies of the VoxApp API, designed specifically for independent mobile developers. We provide a text-to-speech API engineered for integration into Android applications, enabling developers to implement voice features without managing complex infrastructure.

As an independent storefront, VoxApp operates separately from major cloud providers. This page details our voice licensing sources, strict data usage policies, and technical limitations to ensure transparent integration. Readers will find precise information on our infrastructure, support channels, and the specific constraints of our API, helping you assess fit for your mobile project.

Discover the Technology Behind Our Text-to-Speech Platform

Frequently asked questions

Who runs the site?

VoxApp operates this independent storefront for the text-to-speech API. We are an independent provider, not affiliated with major tech brands.

Where are voices from?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Each generated audio file carries an inaudible watermark marking it as synthetic speech.

Is data sold?

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

How do I contact support?

Support is available by email only. We do not offer phone support or live chat.

Is there a phone number?

No, there is no phone number. Support is provided via email only.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL.

Do you use my data for training?

No, input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Request metadata is kept for billing.

Is the API open source?

No, the API is not open source. We provide a proprietary text-to-speech API endpoint. You can use the official OpenAI SDK or plain HTTP to interact with our service.

Who owns the voices?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.

Is there a physical office?

No, there is no physical office listed. We operate as an independent digital storefront. Support is handled via email.

Do you have an SLA?

No, there is no Service Level Agreement (SLA) or uptime guarantee. We do not offer enterprise contracts or on-premise installations.

Is GDPR certified?

No, we do not have a GDPR certificate. We do not offer certifications such as SOC 2 or HIPAA.

Who is the CEO?

VoxApp is an independent storefront for the text-to-speech API.

When was the company founded?

VoxApp operates as an independent storefront for the text-to-speech API.

Company Overview

Sound wave illustration for: Company Overview

We operate as an independent storefront for a text-to-speech API, engineered specifically for mobile application integration. Our platform allows indie developers to implement high-quality voice features without managing complex infrastructure, ensuring that input text is used solely for production and not for training models.

Editorial Team Structure

Editorial Team Structure

Our operations are managed by a small, dedicated team focused on API reliability and developer support. We maintain direct engineering oversight to ensure consistent performance without regional office fragmentation.

Independent Storefront Model

Independent Storefront Model

We function as an independent storefront within a network, providing direct access to the same underlying TTS engine. This model eliminates middlemen, allowing for transparent pricing and direct control over key issuance and rate limits.

Target Audience Focus

Target Audience Focus

Our primary audience consists of indie developers building Android applications. We provide a reliable, cost-effective solution that simplifies voice integration, enabling teams to focus on application logic rather than audio infrastructure management.

Voice Licensing

Sound wave illustration for: Voice Licensing

VoxApp’s voice synthesis engine relies on eight presets derived from licensed recordings. These voices are generated from the LibriTTS-R dataset, which provides a stable foundation for consistent audio quality across all supported languages and use cases.

LibriTTS-R Source

LibriTTS-R Source

The underlying audio models are built upon the LibriTTS-R dataset. This source material originates from LibriVox public-domain audiobook readings, ensuring that the synthetic voices maintain a natural, human-like cadence without relying on celebrity likenesses or expensive custom voice design.

CC BY 4.0 License

The LibriTTS-R dataset is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows VoxApp to legally process and synthesize these recordings into its API endpoints while maintaining clear attribution standards for the original data source.

Public Domain Readings

The source material originates from LibriVox public-domain audiobook readings. By utilizing these pre-existing recordings, VoxApp provides a cost-effective infrastructure that avoids the legal complexities of custom voice cloning or rights management for individual performers.

Data Policy

Sound wave illustration for: Data Policy

VoxApp processes input text exclusively for immediate audio synthesis. The raw text is transmitted to the TTS engine, converted into speech, and the resulting audio stream is returned to the client application. This text is not archived for other purposes.

Input Text Usage

Input text is used only to produce the audio and is not used for training. We do not retain the semantic content of your scripts for model improvement or dataset creation.

No Training Data

Generated audio files are not stored after delivery. We retain only request metadata—such as timestamp, character count, and status—for billing and operational purposes.

Audio Storage Policy

Generated audio is returned in the response and not stored. Once the synthesis is complete and the audio file is delivered to your application, the source audio is not kept on our servers for later retrieval or analysis.

Technical Limitations

Sound wave illustration for: Technical Limitations

VoxApp prioritizes stability and simplicity for Android integration by adhering to a straightforward request-response model. We do not offer streaming, custom voice cloning, or SSML support, ensuring predictable behavior for indie developers who need reliable audio delivery without complex infrastructure management.

No Streaming Support

The API returns a complete audio file upon request completion. Partial audio chunks are not streamed during generation, so clients must wait for the full synthesis to finish before playing the audio.

No Custom Cloning

We do not offer custom voice cloning or the ability to upload your own voice samples. The eight available voices are fixed presets.

No SSML Support

The endpoint accepts plain text input only. There is no support for Speech Synthesis Markup Language (SSML) tags.

Technical Limitations

Support Channels

Sound wave illustration for: Support Channels

VoxApp operates as an independent entity focused on providing a reliable text-to-speech API for mobile integration. Our structure is designed to support indie developers with clear, documented endpoints and straightforward pricing, ensuring that technical implementation remains the primary focus without unnecessary overhead.

We maintain a lean operational model to keep costs low and service predictable. By eliminating complex support tiers and third-party integrations, we ensure that every interaction with our platform is direct, transparent, and aligned with the specific needs of Android application development.

Email Only

Our primary support channel is email. Developers can reach our team at [email protected] for technical questions, billing inquiries, or integration issues.

No Phone Support

We do not offer phone support.

Response Expectations

Support requests are processed in the order they are received. Response times may vary.

Affiliations

Sound wave illustration for: Affiliations

VoxApp operates as an independent entity, managing its own keys, billing via USDT (TRC-20), and voice presets independently.

Our API endpoint structure and JSON request body mimic the OpenAI speech endpoint format to facilitate easy integration for developers already familiar with that ecosystem.

Not Affiliated with OpenAI

Our API endpoint structure and JSON request body mimic the OpenAI speech endpoint format.

Independent Entity

VoxApp manages its own keys, billing via USDT (TRC-20), and voice presets independently.

No Brand Imitation

We do not imitate the branding, logos, or marketing style of OpenAI, ElevenLabs, Google, or Amazon. When we reference these brands in documentation, it is strictly for technical comparison of endpoint formats or voice characteristics.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Understanding these distinctions helps developers select the right tool for their app’s audio needs without over-engineering the solution.

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. LibriTTS-R corpus (OpenSLR 141)
  3. ISO 639 language codes
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. TRON developer hub: TRC-20
  6. Python documentation
  7. openai-python on GitHub
  8. LibriVox public-domain audiobooks
  9. Node.js documentation
  10. openai-node on GitHub
  11. curl documentation
  12. Tether (USDT)

More on this site