Meet the Team Behind the AudioGuides API and Voice Licensing Details

By AudioGuides API editorial team · Updated 2026-11-19

This page outlines the engineering structure behind AudioGuides API and clarifies the licensing model for our voice presets. We explain how our product team manages the infrastructure and how you can reach our support team via email. This information is intended for product teams building audio experiences for museums, tourism, and audioguides who need to understand the operational details of our service.

We also detail the source of our voices, the specific data policies regarding your input text, and the technical limits that govern your API usage. You will find exact information on rate limits, character constraints, and the cloud infrastructure that delivers consistent audio quality. This context helps you integrate our API confidently into your tourism or museum exhibit workflows without surprises.

Meet the Team Behind the AudioGuides API and Voice Licensing Details

Frequently asked questions

Who runs this website?

This is an independent storefront for the AudioGuides API. The team builds and maintains the infrastructure to serve text-to-speech requests. We operate as a distinct entity providing cloud-based audio synthesis for tourism and museum applications, separate from larger technology brands.

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 shape matches the OpenAI speech endpoint for compatibility, but we use our own engine and billing system.

What is the source of the voices?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. We use these source recordings as the basis for our voice presets, ensuring consistent quality and distinct character profiles for your audioguide content.

Is my text used for training?

No. Input text is used only to produce the specific audio file requested. It is not used for training our models or improving future synthesis. Your content remains private to the generation process and is not repurposed for model development.

How long is data kept?

Request metadata, including time, character count, and status, is kept for billing purposes. Generated audio is returned in the response and not stored on our servers after delivery. We retain only the minimal data necessary to verify your usage and charges.

Do you have an SLA?

No. We do not offer a Service Level Agreement (SLA) or an uptime guarantee. Our infrastructure is designed for reliability, but we do not contractually promise specific availability percentages. Requests are processed sequentially, so load may affect processing time.

How do I contact support?

Support is available by email only. We do not offer live chat or phone support. You can reach our team via the contact page or by emailing the support address provided in your account dashboard for technical or billing inquiries.

Is there a phone number?

No. We do not have a phone number for customer support. All communication is handled via email. This allows us to maintain detailed records of your inquiries and provide written responses that you can reference later for technical details.

Do you have a privacy policy?

Yes, we respect your privacy. Input text is used solely for audio generation and not for training. We do not sell your data. Refer to our full privacy policy for details on how we handle request metadata and billing information.

Are the voices copyrighted?

The voice models are derived from LibriTTS-R (CC BY 4.0) and LibriVox public-domain recordings. While the source material is public domain, the generated audio files carry an inaudible watermark marking them as synthetic speech. You retain rights to the generated audio.

Can I use the audio commercially?

Yes. You can use the generated audio commercially for audioguides, museum exhibits, and tourism content, subject to the API usage charges.

Do you store generated audio?

No. Generated audio is returned in the API response and is not stored on our servers after delivery. We only retain request metadata (time, characters, status) for billing purposes. You are responsible for storing the audio files you receive.

What is the API uptime?

We do not guarantee a specific uptime percentage. There is no SLA or uptime guarantee. Requests are processed one after another, so under heavy load, a request may wait in a queue before synthesis begins.

Where are the servers located?

We do not specify the exact data-center locations or provide on-premise install options. Our cloud infrastructure is managed centrally to ensure consistent performance across all 23 supported languages. Specific geographic server locations are not disclosed in our public documentation.

Editorial Team

Sound wave illustration for: Editorial Team

AudioGuides API is built by engineers who understand the constraints of museum and tourism audio systems. We prioritize consistent volume, precise multilingual pronunciation, and reliable API responses over marketing claims. Our team focuses on delivering a stable infrastructure for product teams building audio experiences for exhibits and guides.

Engineering Focus

Engineering Focus

We engineer for reliability, not hype. The team ensures the TTS endpoint handles character limits and rate constraints predictably. We maintain the infrastructure so you can integrate speech synthesis into your applications without worrying about backend complexity.

  • API-first design
  • Consistent audio output
  • Predictable latency

Product Team

Product Team

The product team defines the roadmap based on developer feedback from the tourism and museum sectors. We focus on features that matter for audioguides, such as handling multiple languages and ensuring compatibility with existing workflows.

Support Contact

Support Contact

Support is handled via email only. We do not offer phone support or live chat. You can reach us at [email protected] for technical questions or billing issues. Response times vary based on volume.

Voice Licensing

Sound wave illustration for: Voice Licensing

Our voice presets are derived from the LibriTTS-R dataset, ensuring consistent audio quality for museum exhibits and tourism content.

LibriTTS-R Dataset

LibriTTS-R Dataset

The engine uses licensed recordings from the LibriTTS-R dataset, providing a stable foundation for multilingual narration.

CC BY 4.0 License

CC BY 4.0 License

All generated audio carries an inaudible watermark that marks it as synthetic speech. This allows commercial use in audioguide applications, subject to the API usage charges.

LibriVox Source

Voice samples originate from LibriVox public-domain audiobook readings. This source ensures natural prosody and clear pronunciation suitable for engineering integrations.

Data Policy

Sound wave illustration for: Data Policy

Our engine processes input text strictly to generate the requested audio file. We do not store the generated audio in our systems; it is returned directly in the API response for your immediate use or storage.

Input Text Usage

Input text is used solely for the purpose of synthesis. Once the audio is generated and delivered, the original text payload is not retained for long-term storage or secondary processing.

No Training Data

Your input text is not used to train our models. We do not collect or reuse the content you send to improve voice quality or create new models. Your data remains isolated to your specific generation requests.

Request Metadata

We retain request metadata, including timestamp, character count, and status, exclusively for billing and usage verification purposes. This data ensures accurate charging per character and helps diagnose technical issues without revealing the content of your audioguide text.

API Limits

Sound wave illustration for: API Limits

The API enforces strict rate limits to ensure stable generation for your audioguide deployments. Each API key is capped at 60 requests per minute, with a lower threshold of 10 requests per minute applied until the first top-up is processed.

Character constraints are enforced per request, allowing up to 4,096 characters. For longer narration scripts, split the input into multiple requests and join the resulting audio files to maintain consistent volume and pronunciation quality.

Rate Limiting

Requests are processed sequentially, meaning high-volume bursts may queue. Monitor your usage dashboard to adjust request timing and avoid throttling during peak exhibition hours.

  • 60 requests per minute per key
  • 10 requests per minute before first top-up

Character Limits

Each API call accepts a maximum of 4,096 characters. Spaces and punctuation count toward this limit. Split longer texts into chunks and concatenate the output audio files for seamless playback.

  • 4,096 characters per request
  • Spaces and punctuation count as characters

No SLA

We do not offer a Service Level Agreement, uptime guarantee, or enterprise contract. Requests are processed in order, and generation time varies based on system load. Typical speed is roughly real-time, but short phrases may take a few seconds.

  • No SLA
  • No uptime guarantee
  • No enterprise contract

Technology

Sound wave illustration for: Technology

AudioGuides API runs on cloud infrastructure designed for consistent audio synthesis. Requests are processed in sequence, ensuring predictable output without complex orchestration overhead.

Cloud Infrastructure

Our cloud setup prioritizes stability over raw speed. Under load, requests may queue, but every synthesis attempt is handled sequentially to maintain audio integrity.

OpenAI Compatibility

The API mirrors the OpenAI speech endpoint structure. You can use the official OpenAI SDKs by simply changing the base_url to https://api.3178.info/v1.

SDK Support

We do not maintain a proprietary SDK. Use the official OpenAI SDKs or plain HTTP requests. This ensures broad compatibility with your existing engineering stack.

Contact

Sound wave illustration for: Contact

We prioritize asynchronous communication for clear, documented support interactions. Our team responds to all inquiries via email during standard business hours, ensuring every technical question or billing detail is addressed thoroughly without the noise of live queues.

Email Support

Send your questions to [email protected]. Include your API key prefix and specific details about your audioguide integration or licensing query. We aim to resolve issues efficiently, keeping the engineering focus sharp and direct.

No Phone

We do not offer a phone number. Voice calls can introduce context loss and delay resolution. Email allows you to attach logs, code snippets, or reference IDs, enabling a more precise engineering response.

No Live Chat

There is no live chat widget on this site. This keeps our overhead low and ensures you receive dedicated attention rather than being routed through a generic support queue. Your issue gets full focus when you write in.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Selecting the right voice is critical for museum audioguides, where clarity and tone must match the exhibit's context.

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. Creative Commons Attribution 4.0
  5. FFmpeg documentation
  6. IETF RFC 7845: Ogg Opus
  7. MDN: Web Speech API
  8. Tether (USDT)
  9. TRON developer hub: TRC-20
  10. OpenAI API reference: create speech
  11. LibriTTS-R paper (arXiv 2305.18802)
  12. Python documentation

More on this site