Text-to-Speech API for Museum Audio Guides

By VoxVoyage editorial team · Updated 2026-11-18

VoxVoyage provides a straightforward Text-to-Speech API designed specifically for tourism and museum creators. This page explains how our technology turns your written scripts into natural-sounding audio guides without requiring coding experience. We focus on practical tools that help you digitize content quickly and affordably.

Here, you will find details on our voice licensing, data privacy practices, and technical limitations. Whether you are building a digital tour or an on-site audioguide, this information helps you understand exactly what the VoxVoyage API offers and how it integrates into your workflow.

Text-to-Speech API for Museum Audio Guides

Frequently asked questions

Who runs the VoxVoyage site?

VoxVoyage is an independent storefront for a cloud text-to-speech API. It is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We operate as a standalone service provider for tourism and museum creators seeking natural-sounding audio guides.

Where do the voices come from?

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

Is my data safe?

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 purposes, ensuring your script content remains private and secure.

Do you store my tour scripts?

No. Input text is used only to produce the audio and is not stored after generation. Generated audio is returned in the response and not stored on our servers. Only request metadata, such as time, character count, and status, is kept for billing purposes.

How do I contact support?

Support is available by email only. We do not offer a phone number or live chat. Please reach out via the contact page for any assistance regarding your account, billing, or technical questions about using the API for your audio guide projects.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base URL. However, we are an independent provider with our own keys, pricing, and voice models, distinct from OpenAI’s services.

Do you offer refunds?

Failed requests are free; if synthesis fails, the charge is returned in full. For other cases, since there are no monthly plans or subscriptions, you simply pay for what you use. There are no complex refund policies, just straightforward billing based on characters processed.

What is the SLA for uptime?

We do not offer an SLA (Service Level Agreement) or an uptime guarantee. Requests are processed one after another, so under load, a request may wait in a queue. Typical speed is roughly real time, but performance can vary based on server load.

Do you have a mobile app?

No, we do not have a mobile app, a browser extension, or a WordPress plugin. You interact with our service via the web API using standard HTTP requests or the official OpenAI SDKs. Our interface is designed for developers and no-code users to integrate audio into their workflows.

Can I use the API for commercial projects?

Yes, you can use the API for commercial projects. There are no restrictions on usage type. You pay based on characters processed, with no minimum spend or seats. This makes it suitable for tourism, museums, and audioguide services of any scale or commercial intent.

Is there a privacy policy?

Our data handling is straightforward: input text is used only to produce audio and is not used for training. Generated audio is not stored. We keep request metadata for billing.

Do you offer enterprise plans?

No, we do not offer enterprise contracts, custom SLAs, or dedicated infrastructure. We provide a simple pay-as-you-go model with no monthly plans, seats, or minimum spend. This structure is designed to be accessible for individual creators, small museums, and tourism operators without complex negotiations.

How are voices licensed?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), sourced from LibriVox public-domain audiobook readings. This ensures high-quality, legally cleared voice presets. Each generated file also includes an inaudible watermark to identify it as synthetic speech, maintaining transparency for your end users.

Our Mission for Tourism

Sound wave illustration for: Our Mission for Tourism

VoxVoyage exists to help tourism and museum creators turn written scripts into natural-sounding audio guides using a simple API. We focus on the practical workflow: paste your text, receive an audio file, and deploy it to your visitors.

Our goal is to support museums with digital tools that respect both content creators and visitors. By removing technical barriers, we ensure that audio content remains accessible, accurate, and easy to manage without expensive production teams.

Simplify audio guide creation

Simplify audio guide creation

We streamline the process of converting museum plaques, tour scripts, or exhibition notes into clear audio. You send text via our API and receive an MP3 or WAV file ready for playback systems.

This direct approach eliminates the need for complex studio setups or specialized audio engineers, allowing staff to update guides quickly as exhibits change.

  • Convert text to speech in seconds
  • Receive downloadable audio files instantly
  • Update guide content without re-recording

Support museums with digital tools

Support museums with digital tools

Our API integrates directly into existing museum software or web platforms. You retain control over which voices play which scripts, ensuring brand consistency across all locations.

The system handles character limits and language detection automatically, reducing manual effort for curators managing multilingual content.

  • Works with standard web platforms
  • No custom hardware required
  • Easy integration with existing websites

Make AI accessible to non-coders

Make AI accessible to non-coders

You do not need to write code to use our service. You can use the API directly or paste text on the /get-api-key/ page to download audio files.

Even without technical experience, museum staff can generate high-quality narration for tours, using simple presets like Aria or Felix for clear, engaging audio.

  • No coding experience required
  • Copy-paste workflow
  • Instant audio generation

Voice Licensing Details

Sound wave illustration for: Voice Licensing Details

VoxVoyage delivers natural-sounding audio guides by leveraging high-quality voice presets derived from licensed source material. We ensure transparency regarding the origin of the synthetic voices powering your museum tours, guaranteeing that your content is built on legitimate, cleared audio assets.

Our voice library is rooted in the LibriTTS-R dataset, which provides a diverse range of tones suitable for various exhibition contexts. This foundation allows us to offer eight distinct voice presets—from warm narrators to neutral news readers—without the need for expensive custom recordings.

Based on LibriTTS-R recordings

Based on LibriTTS-R recordings

The VoxVoyage voices are synthesized using models trained on the LibriTTS-R dataset. This dataset contains spoken English, providing the acoustic foundation for our eight voice presets. By using this robust dataset, we ensure consistent audio quality and natural prosody across all generated audio guides.

  • Trained on high-quality, clean speech data
  • Supports 23 languages with consistent quality
  • Generates synthetic speech with inaudible watermarks

CC BY 4.0 license from LibriVox

The source recordings in the LibriTTS-R dataset are licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This license permits commercial use, which is essential for museums and tourism operators who generate audio for public consumption. The CC BY 4.0 license permits commercial use of the source recordings.

  • Permits commercial use for museums and tours
  • Requires attribution if specified by your contract
  • No additional fees for voice usage rights

Public domain audiobook readings

The LibriVox project provides public domain audiobook readings, which form the core of our voice data. These recordings are typically of classic literature and historical texts, offering a rich, expressive tone ideal for museum narratives. The source recordings are from LibriVox public-domain audiobook readings.

  • Rooted in public domain audiobook content
  • Ideal for historical and literary exhibits
  • No recurring voice royalty payments

Data Privacy Policy

Sound wave illustration for: Data Privacy Policy

When you submit a script to our API, the text is processed solely to generate the audio file for your museum audio guide. We do not repurpose your content for any other purpose beyond that specific synthesis request.

Text used only for generation

Your input text is transmitted to the engine and converted into audio immediately. The primary purpose is strictly limited to producing the speech output you requested for your exhibit or tour.

No training on your content

We do not use your submitted text or the resulting audio to train our models. Your unique scripts remain yours, and we do not build them into our core engine for other customers.

No storage of generated audio

Once the audio file is generated and returned in the response, it is not stored on our servers. Only request metadata—such as the time, character count, and status—is kept for billing purposes.

Technical Limitations

Sound wave illustration for: Technical Limitations

The API returns complete audio files only after synthesis finishes. There is no real-time partial audio stream, so you cannot hear words as they are generated. This means the full file must be ready before playback can begin, which is standard for on-demand audio guides but differs from live streaming solutions.

No streaming or WebSocket support

Audio is delivered as a single file once processing completes. If a request is queued due to load, you wait for the entire synthesis to finish before receiving the data. This ensures file integrity but prevents low-latency, word-by-word audio delivery.

No SSML or phoneme customization

You cannot use SSML tags to control pacing or pronunciation. The system guesses the language from the script; Latin text defaults to English, so you must explicitly set the language field for non-English Latin texts. For specific phoneme adjustments or custom lexicons, you must edit the source text before sending it to the API.

No voice cloning or emotion tags

Voices are fixed presets based on licensed recordings. There are no emotion tags to alter tone, nor can you upload a sample to clone a specific voice. Each voice has a consistent character, such as 'calm' or 'energetic,' which you select by name rather than through dynamic instruction.

Technical Limitations

Support and Contact

Sound wave illustration for: Support and Contact

We provide straightforward assistance for your museum audio guide projects via email. Our team is equipped to help with API integration questions, voice selection, or billing inquiries.

Email support only

All communication is handled through email. Please send your questions to [email protected]. This allows us to maintain detailed records of your specific technical or billing needs.

No phone or live chat

We do not offer phone lines or real-time live chat. This ensures you receive thoughtful, documented responses rather than rushed answers. It also keeps our operational costs low, which helps maintain our affordable pricing for museums.

Response within 24 hours

For urgent issues during museum opening hours, consider using the API’s clear error messages to diagnose common problems quickly.

Why We Chose This Model

Sound wave illustration for: Why We Chose This Model

We built VoxVoyage around a TTS API that prioritizes simplicity for tourism creators who need audio guides without hiring developers. By using standard HTTP requests, museums can generate natural-sounding narration for exhibitions, tours, or printed materials with minimal technical friction.

Simplicity for tourism use cases

Our model supports 23 languages and eight distinct voices, allowing curators to match tone to content—such as using 'luna' for storytelling or 'atlas' for news-style updates. Longer texts are split into parts of up to 4096 characters and joined into audio files.

  • Supports 23 languages including English, Spanish, German, and Japanese

Cost-effective for large volumes

Audio guides often require multiple language versions and repeated updates. At $10 per million characters, generating hours of narration remains affordable. Failed requests are free, ensuring you only pay for successful audio files delivered to your visitors.

  • Flat rate: $0.01 per 1,000 characters

Open SDK compatibility

We use the same request shape as the OpenAI speech endpoint, meaning you can use official OpenAI SDKs by simply changing the base URL. This eliminates the need for custom integration code or learning a proprietary protocol.

  • Compatible with standard OpenAI SDKs via base_url change

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This feedback loop ensures your final audio guide meets visitor expectations without unnecessary rework.

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. FFmpeg documentation
  3. openai-node on GitHub
  4. ISO 639 language codes
  5. TRON developer hub: TRC-20
  6. MDN: Web Speech API
  7. Creative Commons Attribution 4.0
  8. LibriVox public-domain audiobooks
  9. LibriTTS-R corpus (OpenSLR 141)
  10. OpenAI API reference: create speech
  11. IETF RFC 7845: Ogg Opus
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site