Meet the Editorial Team Behind Our Independent TTS API

By SereniSpeech editorial team · Updated 2026-11-19

SereniSpeech is an independent editorial voice for indie developers building meditation and fitness apps. We help you evaluate text-to-speech engines by comparing calm, clear narration options against direct API alternatives like Speechify. This page explains who we are, how we license our voices, and the exact technical facts behind our API.

Readers get transparent details on the LibriTTS-R license, and our data policy. You will find honest limitations, such as the absence of SLAs or enterprise contracts, and clear contact information. Our goal is to provide specific, hype-free insights so you can choose the right voice and price for your users.

Meet the Editorial Team Behind Our Independent TTS API

Frequently asked questions

Who runs this site?

SereniSpeech is an independent editorial team helping indie developers evaluate TTS engines for meditation and fitness apps. We compare services like Speechify against direct API alternatives so you can choose the right voice and price for your users.

Are the voices licensed?

Yes. Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This ensures we have the proper rights to offer these specific voice characteristics through our API.

Do you use my text 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. We keep request metadata like time, characters, and status solely for billing.

Where is my audio stored?

Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) for billing purposes. We do not retain the actual audio files after delivery to your application.

Do you have an SLA?

No. We do not offer an SLA, uptime guarantee, or enterprise contract. Our service is designed for indie developers who need straightforward access without complex service level agreements or on-premise installation options.

How do I contact you?

Support is by email only. We do not have a phone number or live chat. You can reach us via the contact page or by email for any questions regarding your account or API usage.

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 shape matches OpenAI’s for convenience, but we are an independent storefront for our own TTS engine.

Do you offer enterprise support?

No. We do not offer enterprise contracts, SLAs, or dedicated support tiers. Our service is built for indie developers and small teams who need reliable, direct API access without the overhead of enterprise agreements.

Is there a phone number?

No. We do not have a phone number. All support is handled via email. This allows us to keep our service direct and focused on providing a reliable API for your meditation and fitness applications.

Do you have live chat?

No. We do not offer live chat. Support is available via email only. This approach ensures that your queries are handled thoroughly without the pressure of real-time conversations, fitting our editorial and direct service model.

Are the voices real people?

The voices are based on licensed recordings from LibriTTS-R. Specifically, they come from LibriVox public-domain audiobook readings under the LibriTTS-R license. Each generated file carries an inaudible watermark marking it as synthetic speech.

What is CC BY 4.0?

CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on recordings licensed under this standard, meaning we can use and adapt the source material while providing proper attribution to the original creators.

Do you store audio files?

No. Generated audio is returned in the response and not stored. We retain request metadata (time, characters, status) for billing purposes only. The actual audio files are not kept on our servers after delivery.

Can I request a feature?

You can contact us via email to request features. However, we do not promise specific features or custom voice cloning. Our roadmap is independent, and we focus on delivering a reliable, straightforward TTS API for developers.

Who We Are

Sound wave illustration for: Who We Are

SereniSpeech operates as an independent editorial storefront rather than a traditional software vendor. We focus on helping indie developers building meditation and fitness apps evaluate TTS engines for calm, clear narration. Our goal is to compare services like Speechify against direct API alternatives so you can choose the right voice and price for your users.

We prioritize editorial honesty over marketing hype. Our reviews are grounded in concrete numbers and real workflows, ensuring you know exactly what to expect when integrating our API into your wellness applications.

Editorial Team Focus

Editorial Team Focus

We operate as an independent editorial storefront rather than a traditional software vendor. Our team curates detailed comparisons and technical facts to help you make informed decisions about voice synthesis for your projects.

Indie Developer Perspective

Indie Developer Perspective

We understand the constraints of indie development. We focus on practical needs: clear pricing, straightforward API integration, and voices that fit the meditation and fitness niches without unnecessary enterprise complexity.

Independent Reviews

Independent Reviews

Our reviews are independent and not influenced by brand affiliations. We compare features like voice quality, character limits, and pricing models to give you a clear picture of your options.

Voice Licensing

Sound wave illustration for: Voice Licensing

Our eight voice presets are derived from licensed recordings in the LibriTTS-R dataset, offering indie developers a clear, calm foundation for meditation and fitness apps. This approach ensures consistent audio quality.

We provide transparent licensing details so you can integrate these voices confidently into your projects. Every generated file carries an inaudible watermark, marking the audio as synthetic speech while maintaining the natural flow of the original recordings.

LibriTTS-R License

LibriTTS-R License

The voices are based on licensed recordings from the LibriTTS-R dataset. This dataset provides a robust foundation for our TTS engine, ensuring that the audio output meets high standards for clarity and naturalness.

CC BY 4.0 Details

LibriTTS-R is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows us to use the recordings for commercial purposes, including generating audio for your apps, provided we attribute the source appropriately.

Public Domain Sources

The underlying audio recordings originate from LibriVox, featuring public-domain audiobook readings. This means the original content is free of copyright restrictions, allowing us to offer a diverse range of voices without additional licensing fees.

Data Policy

Sound wave illustration for: Data Policy

SereniSpeech processes input text exclusively to generate the requested audio file. We do not use your meditation scripts or fitness instructions to train our models or improve the TTS engine. Once the audio is delivered, the raw input text is not retained for any other purpose.

Generated audio is returned directly in the API response and is not stored on our servers. Your data remains transient, ensuring that your specific voiceover content stays private and is not repurposed for other customers or internal development.

Billing Metadata

To ensure accurate billing, we retain minimal request metadata, including the timestamp, character count, and request status. This information is used solely to calculate charges based on the $0.01 per 1,000 characters rate and to verify that credits were applied correctly.

This metadata is kept until the account is closed or deleted by the user. It does not contain the actual text content of your voiceovers, only the volume metrics needed for invoicing and rate limit management.

  • Timestamp of request
  • Character count processed
  • Request status (success/failed)
  • Associated API key ID

Honest Limitations

Sound wave illustration for: Honest Limitations

We operate without an SLA or uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue. We do not promise specific availability percentages or financial credits for downtime.

We offer no enterprise contracts or minimum spend requirements. There are no seats to manage or volume discounts to negotiate. You pay exactly for what you use, with no hidden tiers or long-term commitments.

No SLA or Uptime Guarantee

Our service is best-effort. We do not guarantee specific availability percentages or response times. Requests are processed in queue order, so high volume may delay synthesis.

  • No uptime credits
  • No guaranteed latency
  • Best-effort processing

No Enterprise Contracts

We are an independent API. We do not sign custom SLAs, provide dedicated support lines, or offer on-premise installations. Our model is transparent: pay per character, no minimums.

  • No custom contracts
  • No dedicated support
  • No on-premise option

Email Support Only

We do not offer live chat or phone support. All inquiries go to our support email. We aim to respond promptly, but volume varies.

There is no phone number listed on this site. For urgent billing issues, email is the fastest channel.

  • Email only
  • No live chat
  • No phone support
Honest Limitations

Contact and Feedback

Sound wave illustration for: Contact and Feedback

For questions about your API key, billing, or specific voice configurations, our editorial team is available via email. We prefer written communication to ensure every technical query is answered with precision and documented for future reference.

Email Contact

Send your inquiries directly to our support address. Whether you need help interpreting the /v1/voices endpoint or have a question about character limits, we are here to assist indie developers building meditation and fitness apps.

No Live Chat

We do not offer live chat or phone support. This keeps our overhead low and allows us to focus on maintaining the API infrastructure rather than managing real-time conversation queues.

Response Times

We aim to reply within one business day. Since our team is small and editorial-focused, complex technical questions may take slightly longer as we verify the specific behavior of the TTS-1 engine.

Affiliations and Transparency

Sound wave illustration for: Affiliations and Transparency

SereniSpeech operates as an independent storefront for the same text-to-speech API, distinct from major tech brands. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other service mentioned in our comparisons. Our API endpoint and keys are specific to this network, ensuring clear attribution for the underlying engine.

Not Affiliated with OpenAI

While our API mimics the OpenAI request shape for ease of use, we are a separate entity. The engine powering our voices is the same as OpenAI's tts-1 and tts-1-hd models. We do not use OpenAI branding or infrastructure, and our pricing structure ($0.01 per 1,000 characters) differs from theirs.

Independent Storefront

This site is one of several independent storefronts selling the same API. Each site manages its own accounts and keys. You are purchasing directly from SereniSpeech, not through a reseller agreement with a larger platform. Our base URL is https://api.vv2667.info/v1, distinct from other providers' domains.

No Brand Imitation

We do not imitate the voices of real people, celebrities, or politicians. Our eight voice presets are based on licensed recordings from LibriTTS-R and LibriVox. When we compare services like Speechify, we do so based on published facts, not by suggesting our voices are identical to other brands' offerings.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Developers can predict expenses based on character count, making financial planning straightforward for both small and growing apps.

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. Creative Commons Attribution 4.0
  3. IETF RFC 7845: Ogg Opus
  4. LibriVox public-domain audiobooks
  5. W3C WAI: making audio and video accessible
  6. MDN: Web Speech API
  7. LibriTTS-R corpus (OpenSLR 141)
  8. OpenAI API reference: create speech
  9. curl documentation
  10. openai-node on GitHub
  11. TRON developer hub: TRC-20
  12. Python documentation

More on this site