Discover the Creative Minds Powering VoxMuse Today

By ChickenSubway editorial team · Updated 2026-11-18

This page explains who VoxMuse is and how our text-to-speech API works for indie developers building audioguides and tourism experiences. You will find clear details about our voice sources, data handling, and support limits.

Readers will learn that our voices originate from the LibriTTS-R dataset, which uses recordings from LibriVox public-domain audiobook readings. We also outline our data policy, admission of limitations like no SLA or phone support, and our affiliation status with major brands. This information helps you integrate confidently into your workflow.

Discover the Creative Minds Powering VoxMuse Today

Frequently asked questions

Who runs this site?

VoxMuse is an independent storefront for a text-to-speech API. We focus on providing reliable character-based TTS for tourism and audioguide applications without complex enterprise contracts or subscriptions.

Are you OpenAI?

No. We are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech request shape, so their official SDKs work by changing the base_url. However, we are a separate entity with our own pricing, voices, and infrastructure.

Where do voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated audio file includes an inaudible watermark to identify it as synthetic speech.

Do you sell user data?

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 (time, characters, status) solely for billing.

How do I contact support?

Support is available via email only. We do not offer live chat or a phone number. You can reach us through the contact page or the email address provided in your account dashboard.

Is there a phone number?

No. We do not have a phone number. All support inquiries are handled via email to ensure detailed responses for technical issues. We do not offer live chat or real-time voice support.

Do you have an SLA?

No. We do not provide an SLA or uptime guarantee. Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real time for long texts.

Are the voices copyrighted?

The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. While the source material is public domain or CC licensed, the specific synthetic generation carries an inaudible watermark to mark it as synthetic speech.

Can I use voices commercially?

Yes. The underlying recordings are from CC BY 4.0 and public-domain sources. You pay for the generation service based on characters used. There are no restrictions on commercial use for audioguides, tourism, or other applications.

Do you store my text?

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. Only request metadata is kept for billing purposes.

Is this a large company?

No. VoxMuse is an independent storefront. We focus on indie developers and tourism applications. We do not have enterprise contracts, multiple data centers, or a large corporate structure.

Do you have a team?

Yes. We are a small team of indie developers. We handle development, support, and infrastructure directly. We do not have a large sales or support department, keeping our operations lean and cost-effective.

Can I request features?

Yes. You can contact us via email to suggest features or report issues. We do not have a public roadmap, but we consider user feedback to improve the API for tourism and audioguide use cases.

How do I verify licensing?

Our voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can verify these sources directly. The generated audio includes an inaudible watermark to identify it as synthetic speech created by our API.

Who We Are

Sound wave illustration for: Who We Are

VoxMuse is an independent storefront for a text-to-speech API. We do not operate as a large enterprise; we are a small, focused group that builds tools for other builders. Our primary goal is to provide a reliable, character-based TTS API without the overhead of complex subscriptions or enterprise contracts.

We design our product for indie developers creating audioguides and tourism experiences. By offering a straightforward pay-per-character model and standard OpenAI-compatible endpoints, we ensure you can integrate speech synthesis quickly into your existing workflows without needing specialized SDKs or deep technical overhead.

Independent editorial team

Independent editorial team

Our team operates independently, allowing us to make practical decisions based on developer feedback rather than corporate mandates. This structure keeps our focus sharp on the specific needs of small teams and solo creators who need dependable infrastructure.

  • No corporate bureaucracy
  • Direct developer feedback loop
  • Small, agile team

Focus on indie developers

Focus on indie developers

Our API is tailored for indie developers building audioguides, museum tours, and location-based experiences. We prioritize simplicity and transparency. You get a clear API key, predictable pricing, and standard integration methods that fit seamlessly into your current development stack.

  • Designed for indie projects
  • Audioguide optimization
  • Simple integration

Practical, honest tone

Practical, honest tone

We avoid hype and superlatives. We state exactly what our API does and what it does not do. Our documentation is written to be practical, giving you the specific details you need to integrate quickly without wading through marketing fluff.

  • No hype
  • Clear documentation
  • Transparent pricing

Voice Licensing

Sound wave illustration for: Voice Licensing

VoxMuse provides a reliable, character-based TTS API designed for indie developers building audioguides and tourism experiences. Our voices are based on recordings from the LibriTTS-R dataset, which uses recordings from LibriVox public-domain audiobook readings.

LibriTTS-R source

LibriTTS-R source

Our eight voice presets are derived from the LibriTTS-R dataset, which uses recordings from LibriVox public-domain audiobook readings. This foundation ensures consistent, natural-sounding output for your tourism applications.

CC BY 4.0 license

The source recordings are licensed under CC BY 4.0. This allows us to integrate these voices into our API while maintaining clear licensing terms for our users.

LibriVox public domain

LibriVox provides public-domain audiobook readings, forming the core of our voice library. We process these recordings to create our eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion.

Data Policy

Sound wave illustration for: Data Policy

We prioritize transparency in how your data is handled during the text-to-speech generation process. Our system is designed to be straightforward: you send text, we return audio, and that’s it. There are no hidden data practices or complex retention policies to navigate.

Input text not trained

Your input text is used exclusively to produce the audio file for your request. It is not stored long-term for the purpose of training our models or improving future voice outputs. Once the synthesis is complete, the text is not retained in our training datasets.

No stored audio files

Generated audio is returned directly in the API response and is not stored on our servers after delivery. You own the generated files immediately upon receipt. We do not keep copies of your audio clips for analysis or marketing purposes.

Metadata kept for billing

We retain request metadata—such as timestamp, character count, and status—to accurately track usage and process charges. This data is essential for billing transparency and ensuring you are only charged for successful synthesis attempts.

Limitations We Admit

Sound wave illustration for: Limitations We Admit

We do not provide an SLA or uptime guarantee. While we strive for reliability, request processing can queue under load, and generation times vary based on server traffic.

No phone support

Support is available via email only. There is no live chat widget, no phone number to call, and no direct line to engineers. We prioritize asynchronous communication to keep our team focused on API stability rather than real-time ticket management.

No custom voice cloning

We do not offer voice cloning, custom voice design, or the ability to upload your own voice samples. You are limited to the eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) provided in the API. Each voice is based on licensed recordings from LibriTTS-R.

Limitations We Admit

We believe in transparency about what our API does not do. This ensures you can plan your audioguide or tourism project without unexpected feature gaps or hidden constraints.

  • No SLA or uptime guarantee
  • Email support only; no phone or live chat
  • No custom voice cloning or upload capabilities
Limitations We Admit

Contact and Support

Sound wave illustration for: Contact and Support

We keep communication simple and asynchronous. All support requests go through a single email channel, allowing our team to handle inquiries thoroughly without the pressure of real-time availability.

We do not offer live chat or a dedicated phone line. This keeps our overhead low and aligns with our indie developer-focused, no-frills approach.

Email support only

Send your questions to our support address. We prefer email because it provides a clear record of your issue, including API keys or error logs, which speeds up diagnosis for TTS integration problems.

No live chat

There is no live chat widget on this site. If you need immediate attention during business hours, email is still your best option, but we do not guarantee instant replies.

Response time varies

As a small independent team, response times depend on the volume of requests. We aim to reply within 24–48 hours, but complex billing or API issues may take longer.

Affiliation Status

Sound wave illustration for: Affiliation Status

VoxMuse operates as an independent storefront for a text-to-speech API. While the endpoint structure mirrors the OpenAI speech endpoint, we are not OpenAI, nor do we use their infrastructure. The API base is api.getchickensubway.com/v1, and we use our own keys.

Not affiliated with OpenAI

The API uses a similar JSON shape, so OpenAI SDKs work by changing the base URL. However, our models, voices, and pricing are entirely separate. We are not a subsidiary or partner of OpenAI.

Not affiliated with ElevenLabs

Our voices are licensed from LibriTTS-R and LibriVox. We do not use ElevenLabs’ technology, voices, or infrastructure. Comparisons are based on technical facts, not brand association.

Independent storefront

This site is one of several independent storefronts for the same API. Each site manages its own accounts and billing. We are not part of a larger platform; we are a direct provider for indie developers.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. We build immersive audio stories for independent creators who want to bring museums to life through sound.

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. LibriVox public-domain audiobooks
  3. curl documentation
  4. openai-python on GitHub
  5. W3C WAI: making audio and video accessible
  6. openai-node on GitHub
  7. Tether (USDT)
  8. Python documentation
  9. Creative Commons Attribution 4.0
  10. Node.js documentation
  11. TRON developer hub: TRC-20
  12. MDN: Web Speech API

More on this site