About the Svajpa Editorial Team and Our Mission

By Svajpa Editorial Team · Updated 2026-11-19

Svajpa Editorial is an independent guide for indie developers building audio features for restaurants and dining platforms. We help you select the right synthetic voice from our catalog to enhance user engagement without the overhead of custom voice design. This page explains who we are, how we operate, and why we focus on the specific needs of the restaurant industry.

We provide editorial content that clarifies technical details, pricing, and voice options for developers integrating our text-to-speech API. Our team consists of editors and technical writers who understand the constraints of indie development. We aim to give you clear, honest information so you can make informed decisions about audio integration for your dining platform.

About the Svajpa Editorial Team and Our Mission

Frequently asked questions

Who runs Svajpa?

Svajpa Editorial is an independent storefront for the text-to-speech API. We provide an editorial guide for indie developers building audio features for restaurants and dining platforms, helping you select the right synthetic voice from our catalog to enhance user engagement without the overhead of custom voice design.

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 structure matches the OpenAI speech endpoint for convenience, but we are an independent provider using our own keys and infrastructure.

How are the voices licensed?

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

Do you use customer text for training?

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. We retain request metadata, such as time, characters, and status, strictly for billing purposes to ensure accurate charge calculation.

How long is my data kept?

Input text is used only to produce the audio and is not stored long-term. Generated audio is returned in the response and not stored. Request metadata, including time, characters, and status, is kept for billing purposes to verify usage and process charges accurately.

Can I contact you by phone?

No. We do not have a phone number or live chat. Support is provided by email only. This allows us to maintain a focused, asynchronous workflow suitable for indie developers who need clear, documented responses to their technical or billing questions without waiting on hold.

Is there a physical address?

We are a cloud-based API service. Our operations are entirely digital, from API endpoints to support. This structure keeps overhead low, allowing us to offer competitive pricing without the costs associated with maintaining a physical storefront or office.

Who are the editors?

Svajpa Editorial is an independent guide for indie developers building audio features for restaurants and dining platforms. We focus on practical integration advice, helping you choose from our eight presets to enhance user engagement. Our guidance is based on technical facts and real-world API workflows.

Do you offer enterprise support?

No. We do not offer SLAs, uptime guarantees, enterprise contracts, or dedicated support tiers. Our service is designed for indie developers and small teams. You receive standard email support, and our pricing model scales with your usage, with no minimum spend or monthly plans required.

Can I use the voices commercially?

Yes. Our voices are based on licensed recordings and public-domain readings, making them suitable for commercial use in your dining platforms. We do not offer custom voice cloning, but our eight presets cover various tones, from warm narrators to energetic promos, ideal for restaurant audio features.

Is the editorial team separate from the API?

Svajpa Editorial serves as the independent storefront and guide for the same text-to-speech API. While we provide editorial content to help you select voices, the underlying API infrastructure, including key management and speech synthesis, is handled directly through our cloud endpoints for seamless integration.

Do you have a privacy policy?

We retain request metadata (time, characters, status) for billing purposes. Input text is used only to produce audio and is not stored. Generated audio is returned in the response and not stored. We do not use customer text for training, ensuring your data remains private.

Can I request a specific voice?

You can choose from our eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. We do not offer custom voice cloning or uploading your own voice. Each voice is based on licensed recordings, and you can select the one that best fits your restaurant's tone.

How do you handle complaints?

Support is provided by email only. We do not have a phone number or live chat. You can reach us at the contact page to report issues with synthesis, billing, or API usage. We aim to resolve complaints efficiently through written correspondence, maintaining a clear record of all communications.

Our Mission

Sound wave illustration for: Our Mission

Svajpa Editorial helps indie developers integrate synthetic voices into restaurant apps without the overhead of custom voice design. We provide clear guidance on selecting voices that enhance user engagement for dining platforms, ensuring technical decisions align with practical audio needs.

Our focus remains on the specific requirements of the restaurant industry, from menu descriptions to reservation confirmations. We evaluate each voice preset for clarity and tone, helping you choose the right tool for your specific use case.

Supporting Indie Developers

Supporting Indie Developers

We simplify API integration by offering editorial insights rather than just technical documentation. Our goal is to help you select the right voice from our catalog, ensuring your audio features are both effective and easy to maintain.

By focusing on concrete workflows, we reduce the guesswork in audio implementation. You get specific recommendations based on real usage patterns in dining apps, rather than generic advice.

  • Clear voice selection guidance
  • Practical integration examples
  • Reduced development overhead

Focus on Restaurant Industry

Focus on Restaurant Industry

We understand the unique audio needs of restaurants and dining halls. Whether it’s a welcoming greeting or a detailed menu read-out, the right voice can significantly impact user experience.

Our editorial content is tailored to the nuances of the dining industry, ensuring that the synthetic voices we recommend fit naturally into your app’s interface.

Editorial Independence

Editorial Independence

As an independent storefront, Svajpa Editorial operates with full transparency. We do not claim to be the official provider for other brands, nor do we offer enterprise contracts or SLAs.

Our mission is to provide honest, specific advice that helps you build better audio features for your restaurant platform, without the noise of hype or superlatives.

Voice Licensing

Sound wave illustration for: Voice Licensing

Our synthetic voices are generated from licensed recordings in the LibriTTS-R dataset, providing a clear and neutral foundation for our TTS engine. This dataset serves as the raw material for all eight voice presets, ensuring consistent quality across 23 supported languages.

LibriTTS-R Source

LibriTTS-R Source

The LibriTTS-R dataset consists of high-quality audio recordings originally intended for speech recognition research. We utilize these recordings to power our text-to-speech API. Every generated audio file carries an inaudible watermark that marks it as synthetic speech.

  • High-fidelity audio recordings
  • Optimized for TTS training
  • Multi-language support base

CC BY 4.0 License

The underlying voice data is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows us to legally adapt and redistribute the audio characteristics in our commercial API while giving proper credit to the original dataset contributors, maintaining transparency in our sourcing.

  • CC BY 4.0 compliant
  • Attribution required for dataset
  • Commercial use allowed

Public Domain Readings

Many of the source recordings originate from LibriVox, featuring public domain audiobook readings. These recordings, performed by volunteers reading classic literature, provide a rich and diverse vocal base. This heritage ensures that our voices sound natural and experienced, rather than purely synthetic or robotic.

  • LibriVox sourced recordings
  • Public domain source material
  • Natural human cadence

Data Privacy

Sound wave illustration for: Data Privacy

Svajpa Editorial helps indie developers integrate synthetic voice into restaurant platforms, focusing on practical audio features without the overhead of custom voice design.

Text Usage Policy

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. We do not store the generated audio content.

No Training Data

Your text is not used to train our models or improve the TTS engine. The voices are based on licensed LibriTTS-R recordings, but your specific inputs remain isolated.

Metadata Retention

We retain request metadata, including timestamp, character count, and status, strictly for billing and usage verification. This data ensures accurate charges for the $10 per million characters rate.

Team Structure

Sound wave illustration for: Team Structure

Svajpa Editorial is built by indie developers who understand the constraints of building audio features for restaurant platforms without enterprise overhead. Our small, focused team ensures that every voice recommendation is practical, tested, and directly applicable to dining scenarios like table orders or waitlist updates.

Editorial Roles

Our editors curate voice selections based on technical facts, ensuring that presets like Aria’s warm narration or Felix’s energetic promo style fit specific dining contexts. We prioritize clarity and engagement over artificial perfection, helping developers choose voices that enhance user experience without requiring custom design work.

  • Voice selection specialists
  • Industry-specific content editors
  • Technical writers for API docs

Technical Oversight

Technical leads manage the integration between the TTS API and editorial content, ensuring accurate representation of limits like the 4096-character input cap and 60 requests per minute rate limit. We verify that speed adjustments and format choices (mp3, wav, opus) align with developer needs for seamless audio delivery.

  • API integration specialists
  • Quality assurance testers
  • Documentation maintainers

Community Engagement

Support is provided by email only. Our community focus ensures that updates to voice presets and pricing models reflect actual developer usage patterns and feedback from the dining platform sector.

  • Developer feedback channels
  • Usage pattern analysis
  • Community-driven updates
Team Structure

Contact Information

Sound wave illustration for: Contact Information

We handle all communication for the Svajpa Editorial team via email, ensuring a clear written record of your inquiries. Whether you need assistance with voice selection for your restaurant platform or have questions about the API integration, our email channel is the primary point of contact.

Email Support

Send your questions to the support email listed on the contact page. We prefer email because it allows our technical and editorial staff to respond with detailed, accurate information without the pressure of a live conversation.

No Phone Line

There is no phone number for Svajpa Editorial or the API service. We do not offer live chat or voice support, keeping our operations lean and focused on asynchronous communication that indie developers find efficient.

Response Times

During high traffic periods or holidays, responses may take slightly longer, but we prioritize technical issues related to voice generation and billing.

Honest Limitations

Sound wave illustration for: Honest Limitations

We operate as a simple, independent storefront for the Svajpa TTS API, rather than a traditional enterprise SaaS provider. This means you get direct access to the technology without the overhead of complex support structures or guaranteed uptime metrics, as we do not offer an SLA. Our focus remains on providing reliable, affordable synthetic voice generation for indie developers in the restaurant industry.

No SLA

We do not offer a Service Level Agreement or uptime guarantee. While we strive for consistent performance, request processing may queue during high load, especially since requests are handled sequentially. There is no formal contract defining response times or availability percentages, so please factor this into your restaurant platform's audio features.

No Enterprise Contracts

There are no enterprise agreements, dedicated accounts, or custom billing arrangements. We support individual developers and small teams through a straightforward, pay-as-you-go model. You manage your own API key and balance, with no minimum spend or monthly subscriptions required. This keeps the service accessible and transparent for indie projects.

Independent Storefront

This site is an independent storefront for the same TTS API used across our network. We are not affiliated with OpenAI, ElevenLabs, or other major voice brands. Our editorial content focuses on helping developers choose the right voice for dining platforms, without the bias of a larger corporate ecosystem.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The voice is neutral yet deep, avoiding excessive emotion or brightness.

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. W3C WAI: making audio and video accessible
  3. OpenAI API reference: create speech
  4. Python documentation
  5. LibriTTS-R corpus (OpenSLR 141)
  6. Tether (USDT)
  7. MDN: Web Speech API
  8. Node.js documentation
  9. IETF RFC 7845: Ogg Opus
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. LibriVox public-domain audiobooks
  12. Creative Commons Attribution 4.0

More on this site