Lumivox API: Editorial Team, Licensing, and Data Policy

By Lumivox editorial team · Updated 2026-11-18

Lumivox is an independent storefront for a cloud text-to-speech API, built by a small editorial team of publishers who understand the specific needs of self-publishers and content creators. This page outlines our editorial background, the licensing of our voice assets, and our straightforward data policy. We focus on practical tools for converting kindergarten books into audio files without the noise of corporate hype.

You will find clear details on how our voices are sourced from public domain recordings, how your input text is handled, and why we keep our support simple. Whether you are a self-publisher or a content creator, this page explains the facts behind our service, including our limitations and independence from major tech brands.

Lumivox API: Editorial Team, Licensing, and Data Policy

Frequently asked questions

Who runs this website?

Lumivox operates this independent storefront for the TTS API. We focus on helping self-publishers convert kindergarten books into audio. Accounts are specific to this site, and we handle billing and key management directly without third-party intermediaries or enterprise contracts.

Are the voices owned by Lumivox?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and from LibriVox public-domain audiobook readings. We do not own the original recordings but have licensed them for synthesis. The generated audio files carry an inaudible watermark marking them as synthetic speech.

Do you use customer text for training?

No. Input text is used only to produce the audio file and is not used for training models. Generated audio is returned in the response and not stored. Only request metadata like time, characters, and status are kept for billing purposes.

How is my data handled?

Input text is processed solely to generate the audio and is not stored or used for training. Generated audio is returned in the response and not stored. We retain request metadata, such as timestamp, character count, and status, strictly for billing and usage records.

Do you have an SLA?

We do not offer an SLA, uptime guarantee, or enterprise contract. 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 may take a few seconds to generate.

Are you affiliated with OpenAI?

No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint mimics the OpenAI speech endpoint shape, allowing you to use the official OpenAI SDK by simply changing the base_url to our domain.

How do I contact support?

Support is available by email only. We do not have a phone number, live chat, or on-premise install option. For issues with your API key, billing, or text synthesis, please reach out via the contact form or email address provided on our contact page.

Is the team technical or editorial?

We are a practical team focused on helping content creators convert kindergarten books into readable audio. We handle the technical API infrastructure, including automatic text splitting and joining for long books, so you can focus on the story rather than the engineering details.

Who We Are

Sound wave illustration for: Who We Are

Lumivox is built by a team of editors and publishers who understand the specific challenges of converting kindergarten books into audio. We recognized that self-publishers need reliable tools to bring their stories to life without managing complex infrastructure.

Our focus is on practical utility. We provide a straightforward API that handles the heavy lifting of splitting and joining long texts, allowing creators to concentrate on the narrative rather than the technical details of generation.

Editorial team of publishers

Editorial team of publishers

We are not a generic tech startup; we are publishers who build tools for publishers. Our background in editorial workflows informs how we design the API, ensuring it fits naturally into the production of children's audio content.

  • Team with editorial and publishing experience
  • Built for self-publishers and content creators
  • Understanding of long-text workflows

Focus on practical tools

Focus on practical tools

We prioritize functionality over flair. The API automatically splits texts into parts of up to 4,096 characters and joins the resulting audio files, so you can submit entire book chapters without manual chunking.

No hype, just facts

No hype, just facts

We do not claim to be the best or fastest. We provide a reliable endpoint that converts text to speech at roughly real-time speeds, with clear pricing and transparent limitations.

Voice Licensing

Sound wave illustration for: Voice Licensing

Lumivox voices are built from licensed recordings sourced directly from the LibriVox archive. Each voice preset corresponds to one of eight voice styles derived from licensed recordings.

Based on LibriTTS-R

Based on LibriTTS-R

The underlying voice models are derived from the LibriTTS-R dataset. This dataset provides the source recordings for our eight voice presets.

CC BY 4.0 licensed

The source recordings are licensed under Creative Commons Attribution 4.0 International. This license allows us to process and serve these voices through our API while respecting the original creators' rights.

From LibriVox public domain

LibriVox volunteers have donated their readings of public domain books, forming the core of our voice library. We use these recordings to create the distinct voices of Aria, Nova, Luna, and our other options.

Data Policy

Sound wave illustration for: Data Policy

We process your input text solely to generate the requested audio file. Your manuscript content is not used for training our models or improving the voice engine, ensuring your stories remain private during synthesis.

Text not used for training

The text you submit is processed in real-time to produce the audio output. It is not retained for model training, so your creative work stays yours.

Audio not stored by us

Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once you download the file, it is no longer held by our systems.

Metadata kept for billing

We retain request metadata, including timestamp, character count, and status, strictly for billing and usage verification. This data ensures accurate charging to your account balance.

Support Contact

Sound wave illustration for: Support Contact

We handle all customer inquiries via email. This allows our editorial team to provide detailed, thoughtful responses tailored to your specific publishing needs without the distractions of real-time chat. You can reach us at [email protected] for any questions regarding your API key, billing, or technical integration.

We maintain a simple, direct line of communication. By avoiding complex call centers, we ensure that every message receives full attention from someone who understands the nuances of converting kindergarten books into audio.

Email support only

Our primary support channel is email. This ensures that your queries are documented and can be referenced easily if you need follow-up assistance with your API usage or billing cycles.

No phone or live chat

We do not offer phone support or live chat widgets. This approach allows our small editorial team to focus on delivering accurate technical and editorial answers without being interrupted by simultaneous calls.

Response within 24 hours

Since we are a small team of publishers, we prioritize quality over speed, ensuring that your technical or content questions are answered thoroughly.

During weekends or holidays, response times may vary slightly, but we strive to keep delays minimal for self-publishers working on tight release schedules.

Support Contact

Limitations

Sound wave illustration for: Limitations

Lumivox provides a practical utility for self-publishers, not a critical infrastructure service with rigid guarantees. Our API handles long texts by splitting and joining them automatically, but we do not promise specific uptime percentages. Requests are processed sequentially, so under load, a request may wait in a queue, affecting generation speed.

We do not hold external certifications such as SOC 2, HIPAA, or ISO 27001. These are not relevant to our model of providing a simple, direct API for audiobook conversion. We focus on delivering accurate audio files without the overhead of enterprise compliance layers.

No SLA or uptime guarantee

We do not offer a Service Level Agreement (SLA). There is no guaranteed uptime percentage, and we do not provide financial credits for service interruptions. Our system processes requests one after another; during high demand, synthesis may take longer than the typical real-time speed.

No certifications like SOC 2

Lumivox does not hold certifications such as SOC 2, HIPAA, or ISO 27001. Our data policy is straightforward: 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 by us.

  • Input text is not used for model training.
  • Generated audio is not stored by us.
  • Request metadata is kept for billing purposes only.

No enterprise contracts

We do not offer custom enterprise contracts, dedicated support lines, or on-premise installation options. Our service is designed for independent creators and self-publishers who need a straightforward, pay-as-you-go solution. There are no monthly plans, no seats, and no minimum spend requirements.

Independence

Sound wave illustration for: Independence

Lumivox is an independent service, not affiliated with OpenAI, ElevenLabs, or any other brand mentioned in comparisons. We are not the official provider of the OpenAI TTS engine, nor do we claim to be. Our identity is distinct from the companies whose technologies we may reference.

Not affiliated with OpenAI

We operate independently. While our API endpoint mirrors the OpenAI speech structure for ease of use, we are not owned by or connected to OpenAI. Brand names of others appear only in comparison or 'alternative' contexts to clarify our position.

Independent storefront

This site, getx99.com, is one of many independent storefronts for the same underlying text-to-speech API. Each site manages its own accounts and branding, but the core service remains consistent across the network.

Same API for all sites

Every site of the network is an independent storefront for the same text-to-speech API. You can use the same API key and base URL structure regardless of which storefront you register on, ensuring a uniform experience for self-publishers and content creators.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Male voices offer distinct tonal qualities for different narrative needs.

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. Node.js documentation
  3. LibriTTS-R corpus (OpenSLR 141)
  4. MDN: Web Speech API
  5. LibriVox public-domain audiobooks
  6. TRON developer hub: TRC-20
  7. ISO 639 language codes
  8. curl documentation
  9. W3C WAI: making audio and video accessible
  10. Creative Commons Attribution 4.0
  11. LibriTTS-R paper (arXiv 2305.18802)
  12. openai-node on GitHub

More on this site