About Our Team, Voice Licensing, and Data Policy

By Audioguide Voice editorial team · Updated 2026-11-18

This page explains the background of Audioguide Voice, the independent team behind this text-to-speech API. We are enthusiasts focused on tourism and museums, building tools for no-code users who need realistic voices for museum guides and travel videos. You will learn about our team’s mission, how our voices are licensed, and exactly how your data is handled.

Readers will discover that our voices are based on the LibriTTS-R dataset, which uses recordings from LibriVox. We clarify our data policy: input text is not used for training, and generated audio is not stored.

About Our Team, Voice Licensing, and Data Policy

Frequently asked questions

Who runs this website?

This site is an independent storefront for the Audioguide Voice API. Accounts are created per site, meaning your account here is specific to playabc77.com. We operate independently and are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We provide the API infrastructure for museum guides and travel content creators.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R, which uses public-domain audiobook readings from LibriVox. These recordings are licensed under CC BY 4.0. We process these source materials to create the synthetic voices available in our API, ensuring high-quality audio for your tourism and museum projects.

Is my text used for training?

No. Your input text is used only to produce the audio file for your request. It is not used for training our models or improving the voice synthesis engine. We respect your content ownership and ensure your specific texts remain private to your generation process.

Are the voices real humans?

The voices are synthetic. They are generated by an AI model trained on licensed human recordings. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. While based on real human voices, the output is computer-generated, not a direct recording of a person.

Do you store the generated audio?

No. Generated audio is returned in the response and not stored by our servers. We keep request metadata, such as time, character count, and status, strictly for billing purposes. Your actual audio files are delivered to you and do not remain on our infrastructure after delivery.

What is the CC BY 4.0 license?

CC BY 4.0 is a Creative Commons Attribution license. Our voice data is derived from LibriVox readings, which are licensed under CC BY 4.0. It allows commercial use and modification, provided appropriate credit is given to the original source material and creators.

Do you have an office?

We do not have a physical office or a listed physical address. We operate as a remote team supporting the API globally. Communication and support are handled entirely through email. There is no phone number or live chat available for customer inquiries or technical support.

Can I use the voices commercially?

Yes. You can use the generated audio for commercial purposes, such as museum audioguides, travel videos, or e-learning. Since the source recordings are from LibriVox public-domain readings and licensed under CC BY 4.0, you can integrate the synthetic audio into your commercial projects without additional royalty fees.

Is the API owned by OpenAI?

No. We are an independent storefront and are not affiliated with OpenAI. Our API endpoint is https://api.playabc77.com/v1. While our request format matches the OpenAI speech endpoint for compatibility, we use our own keys and infrastructure. We are a separate entity providing TTS services.

How do I contact support?

Support is available by email only. We do not offer phone support, live chat, or a physical address for in-person visits. You can reach us via the contact page or the email address provided in your account dashboard. We aim to respond to all inquiries promptly.

Do you use cookies?

The provided product facts do not specify cookie usage. We focus on the API service and billing. For details on cookies, please refer to the site’s privacy policy or contact us via email. Our primary data retention concerns request metadata for billing, not browser tracking.

What is the data retention period?

Request metadata, including time, character count, and status, is kept for billing purposes. Generated audio is not stored. Input text is used only for generation and not retained for training. We retain billing data long enough to process charges and handle disputes, but specific retention durations are not detailed.

Are the voices synthetic?

Yes. All voices are synthetic. Every audio file generated by our API contains an inaudible watermark indicating it is synthetic speech. The voices are created from licensed recordings but are generated by our text-to-speech engine, not recorded directly by humans for each output.

Do you have a physical address?

No. We do not have a physical office or a listed physical address. Our support is entirely remote and handled via email. There is no phone number or live chat. We operate as a digital-first API provider, serving customers globally without a central physical location.

Who We Are

Sound wave illustration for: Who We Are

Audioguide Voice is an independent storefront for a text-to-speech API. We are not a large tech conglomerate; we are enthusiasts who believe that audio guides and travel videos deserve clear, accessible narration without the complexity of enterprise software.

Our work focuses on tourism and museums, creating tools that help curators and creators produce engaging audio content quickly. We value honesty over hype, ensuring our API serves the specific needs of storytellers who want realistic voices for any language without unnecessary features or hidden costs.

Independent Editorial Team

Independent Editorial Team

We are a small, focused group of editors and developers who understand the nuances of museum narratives and travel storytelling. Unlike large platforms that prioritize scale over specificity, we prioritize clarity and reliability for audio content creators.

  • No corporate hierarchy; just a dedicated team.

Focus on Tourism and Museums

Focus on Tourism and Museums

We designed our platform for museum guides and travel videos. Whether you are creating an audio tour for a historical site or a voiceover for a YouTube travel vlog, our API provides the realistic voices and multi-language support you need.

We understand that tourists and visitors expect clear, engaging audio that enhances their experience without distracting from the visual content. Our API is designed for easy integration, suitable for both coding and no-code workflows.

  • Optimized for museum audio guides.
  • Ideal for travel video voiceovers.
  • Supports diverse cultural narratives.

Enthusiast Tone

We are passionate about making audio content accessible to everyone. We believe that technology should serve the storyteller, not the other way around. Our enthusiasm drives us to keep our API simple, transparent, and effective.

When you use Audioguide Voice, you are working with a team that cares about the quality of your audio as much as you do. We are here to help you create engaging content that resonates with your audience.

  • Passionate about clear narration.
  • Focused on user experience.
  • Committed to transparency and honesty.

Voice Licensing

Sound wave illustration for: Voice Licensing

We build our audio engine on the LibriTTS-R dataset, which features high-quality recordings from the LibriVox project. These are recordings from the LibriVox project, licensed under CC BY 4.0.

LibriTTS-R Dataset

Our eight voice presets—like Aria, Felix, and Atlas—are derived directly from this dataset. We use these recordings to create eight voice presets.

CC BY 4.0 License

The underlying dataset is released under the Creative Commons Attribution 4.0 International license. This allows us to adapt and utilize the recordings for commercial TTS synthesis while respecting the original creators' rights through proper attribution standards.

LibriVox Public Domain

The source material consists of public-domain audiobooks read by volunteers worldwide. Because the source recordings are licensed under CC BY 4.0, we can use them for commercial synthesis.

Voice Licensing

Data Policy

Sound wave illustration for: Data Policy

We treat your content with care. The text you send to generate audio is used strictly for synthesis and is not used to train our models or improve the voice engine.

Input Text Not Trained

Your scripts remain yours. We do not ingest your input text into any training dataset, ensuring your creative work stays private and exclusive to your project.

No Stored Audio

Generated audio files are returned directly in the API response and are not permanently stored on our servers. Once you receive the file, we do not keep a copy of the audio generation.

Billing Metadata Kept

We retain request metadata—such as timestamp, character count, and status—solely for accurate billing and troubleshooting. This minimal data helps us process your charges correctly without storing the actual content you created.

Technology

Sound wave illustration for: Technology

Audioguide Voice runs as a cloud-based text-to-speech API. You send text via HTTP requests and receive audio files directly. The system processes requests sequentially, so longer texts are split into parts and joined. Typical generation speed is roughly real-time for long texts, though short phrases may take a few seconds depending on queue load.

Cloud-Based API

Our infrastructure is fully cloud-hosted, requiring no local servers or complex deployments. You interact with the service through standard HTTP endpoints, making it easy to integrate into websites, mobile apps, or travel guide systems without managing hardware.

OpenAI Compatible

The API follows the same request shape as the OpenAI speech endpoint. This means you can use the official OpenAI SDKs by simply changing the base_url to https://api.playabc77.com/v1. Standard tools and libraries work out of the box with your API key.

No Proprietary SDK

We do not build or maintain a dedicated proprietary SDK. Instead, we rely on established, widely-used libraries like the OpenAI Python or JavaScript SDKs. This ensures compatibility and reduces dependency on a single vendor's tooling updates.

Technology

Limitations

Sound wave illustration for: Limitations

We built Audioguide Voice as a simple, reliable tool for museums and travel content. It is not a real-time streaming service or a complex speech synthesis engine. We keep the feature set focused so you can generate audio files quickly without managing complex protocols.

No Streaming

You send a text request and receive a complete audio file (mp3, wav, etc.). There is no WebSocket or chunked streaming for real-time playback. This design ensures consistent quality and makes it easy to download and embed audio into your museum guide apps or travel videos.

No SSML

The API accepts plain text. We do not support SSML tags for fine-grained control over pauses, emphasis, or pronunciation. The voices naturally adapt to the text’s rhythm, which works well for standard narration in 23 languages without needing extra markup code.

No Voice Cloning

We offer eight preset voices based on licensed recordings, but we do not offer custom voice cloning. You cannot upload a sample to create a unique voice for your brand. This keeps our service simple and avoids the legal complexities of voice rights management.

Limitations

Contact Us

Sound wave illustration for: Contact Us

We are a small, independent team focused on making museum and travel audio accessible. For support inquiries, please use the email form below. We aim to respond promptly to all messages regarding your account or usage.

Email Support Only

All support requests go through our email address. This is our only channel for direct communication. You can reach us at [email protected] for billing questions, technical issues, or general feedback.

No Phone Number

We do not have a dedicated phone line. Since we are a lean team, managing calls would slow down our response times. Email allows us to provide detailed, written answers that you can reference later.

No Live Chat

There is no live chat widget on this site. Our asynchronous email support is more efficient for non-urgent matters. This approach keeps our operations simple and cost-effective, allowing us to focus on the API itself.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Your audioguide turns every museum visit into a memorable, easy-to-create experience for all visitors.

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 paper (arXiv 2305.18802)
  3. LibriTTS-R corpus (OpenSLR 141)
  4. curl documentation
  5. Tether (USDT)
  6. FFmpeg documentation
  7. OpenAI API reference: create speech
  8. IETF RFC 7845: Ogg Opus
  9. ISO 639 language codes
  10. Python documentation
  11. openai-node on GitHub
  12. W3C WAI: making audio and video accessible

More on this site