Text-to-Speech API for Real Estate Agencies

By VoxProp editorial team · Updated 2026-11-19

This page explains who runs VoxProp and how we operate the text-to-speech API you see on x06.info. We are an independent provider built for real estate agencies creating virtual tours and property videos. We are not affiliated with OpenAI, ElevenLabs, or any other brand mentioned in our documentation.

We use licensed recordings from LibriVox and follow the CC BY 4.0 license for our voice engine. Here you will find details on our data policy, support channels, and technical limits. Support is by email only. Use this information to understand exactly what is included in your VoxProp API key and how we handle your listing descriptions.

Text-to-Speech API for Real Estate Agencies

Frequently asked questions

Who runs VoxProp?

VoxProp is an independent storefront for a cloud text-to-speech API. We operate as a standalone service for real estate agencies, providing a simple API and online tool to convert listing descriptions into audio files without hiring voice actors.

Are the voices original recordings?

The eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file carries an inaudible watermark marking it as synthetic speech, ensuring clear attribution of the source material.

Do you store my property data?

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.

Can I use the voices in commercials?

The underlying recordings are from LibriVox public-domain audiobook readings, licensed under CC BY 4.0. You can use the generated audio files for your property marketing and commercials.

Do you have a privacy policy?

We maintain a privacy policy on our website. Input text is not used for training, and generated audio is not stored. Request metadata is kept for billing. For details, please refer to the legal section on our site.

How do I contact support?

Support is available by email only. We do not offer a phone number or live chat. You can reach us via the contact page to discuss any issues regarding your account, billing, or API usage.

Is there a phone number for urgent issues?

No, we do not have a phone number. Support is provided via email only. There is no SLA or uptime guarantee, so response times may vary. Please use the contact form for all inquiries.

Do you offer refunds?

Failed requests are free, and the charge is returned in full if synthesis fails. For other cases, please contact us via email. We do not offer automatic refunds for successful generations, but we handle disputes case-by-case.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, so their SDKs work by changing the base URL. We are an independent provider using a different engine and voice library.

Can I sue for data breaches?

We do not offer an enterprise contract. While we use text only for synthesis and do not store audio, standard legal terms apply. Refer to our terms of service for dispute resolution details.

Do you use cookies?

Where are your servers located?

We do not specify data-center choices. Our service is a cloud API, and we do not provide certifications like SOC 2 or HIPAA. Server locations are determined by our infrastructure provider for optimal performance.

Do you have a team of editors?

We do not have a team of editors or voice designers. You select from eight preset voices (e.g., Aria, Nova, Felix). There is no custom voice cloning or emotion tagging. You control the output via the API parameters.

Can I license the voices separately?

We do not offer separate licensing for the voices. You pay for the API usage based on characters processed. The voices are part of our synthesis service, and generated audio files are yours to use upon successful payment.

Who we are

Sound wave illustration for: Who we are

VoxProp is an independent cloud text-to-speech API provider built specifically for real estate agencies and media producers. We offer a simple, reliable way to convert listing descriptions into clear, professional audio files without the overhead of hiring voice actors. Our service is designed to streamline the production of voiceovers for virtual tours and property videos.

Independent API provider

Independent API provider

We operate as a standalone API service, not a wrapper or reseller. You receive direct access to our synthesis engine via standard HTTP requests, ensuring predictable performance and transparent billing based on characters processed.

Focused on real estate and media

Focused on real estate and media

Our infrastructure and voice presets are optimized for the specific needs of real estate marketing. We prioritize clarity and natural pacing for property descriptions, ensuring the audio complements visual tours without distracting from the content.

No affiliation with OpenAI or others

No affiliation with OpenAI or others

Although our API endpoint shape matches the OpenAI speech endpoint for easy SDK integration, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We use the same engine and infrastructure as the standard API.

Our voices

Sound wave illustration for: Our voices

VoxProp’s voice library is built on high-quality, pre-licensed audio. We use the LibriTTS-R dataset, which provides a diverse range of natural-sounding voices suitable for real estate narration. This ensures your property descriptions sound professional without the cost of hiring individual voice actors.

Our voices are derived from recordings made by volunteers on LibriVox, a platform for public-domain audiobooks. This foundation gives us a robust, ethically sourced audio engine that scales with your agency’s needs.

Based on LibriTTS-R license

Based on LibriTTS-R license

The LibriTTS-R dataset offers eight distinct voice presets, including warm narrators like Aria and calm instructional voices like Sage. These voices are optimized for clarity, making them ideal for reading property listings and virtual tour scripts.

Each voice is designed to handle various tones, from energetic promo reads to neutral news-style updates, ensuring your brand voice remains consistent across all digital properties.

Recordings from LibriVox

LibriVox volunteers provide the source recordings for our engine. These contributors read from public-domain books, creating a rich audio base that avoids the licensing complexities of proprietary voice models.

By leveraging these community-driven recordings, we maintain a library that is both diverse and cost-effective for real estate agencies.

CC BY 4.0 and public domain

The underlying data is licensed under CC BY 4.0. This clear licensing structure means you can generate audio for commercial use without additional royalties.

All generated files include an inaudible watermark to identify them as synthetic speech, maintaining transparency for your end clients.

This open approach allows us to keep pricing simple and predictable, with no hidden fees for voice usage.

Data policy

Sound wave illustration for: Data policy

We process your listing descriptions solely to generate the audio file. Once the synthesis is complete, the input text is not retained for training or any other purpose. This ensures your property details remain private and are not used to improve our models.

Generated audio is returned directly in the API response and is not stored on our servers. We keep only request metadata—such as timestamp, character count, and status—for billing purposes. This minimal data allows us to verify charges and manage your account accurately without retaining your content.

Input text not used for training

Your property descriptions are used exclusively to produce the voiceover. We do not use your input text to train or improve our speech models, ensuring your specific listing data remains yours.

Audio returned in response, not stored

The generated audio file is delivered to you via the API response and is not stored on our servers. We do not keep copies of your voiceovers, ensuring your content is transient and secure.

Metadata kept for billing only

We retain only essential request metadata—time, character count, and status—to calculate charges and manage your account. This data is used strictly for billing and does not include the content of your listings.

Support and contact

Sound wave illustration for: Support and contact

We provide email support for all technical and billing inquiries. You can reach our team at [email protected]. We do not offer a live chat widget or a dedicated phone number, keeping our operations lean and focused on API reliability.

Email support only

Send your questions to [email protected]. Whether it is a question about voice selection for a property tour or a billing issue with your USDT top-up, our team handles all correspondence via email. This allows us to provide detailed, written responses that you can reference later.

No live chat or phone

We do not maintain a phone line or real-time chat support. By avoiding these channels, we reduce overhead costs and pass the savings on to you. If you need immediate assistance, you can also check the documentation or try the API directly.

Response within business hours

We aim to respond to all emails during standard business hours. While we do not guarantee a specific response time, we strive to address your inquiries promptly during these times. For urgent API issues, you can also verify your key status via the dashboard.

Support and contact

Technical limits

Sound wave illustration for: Technical limits

VoxProp operates as a cloud API service designed for flexibility rather than guaranteed availability. We do not offer a Service Level Agreement (SLA) or an uptime guarantee for our infrastructure. While we strive to keep the API running, request processing may experience delays during high load periods, as requests are handled in sequence.

We serve independent agencies and developers without enterprise-level commercial contracts. There are no minimum spend requirements, no dedicated account managers, and no custom SLAs. Our pricing remains transparent at $10 per million characters, billed via USTRC-20, with no monthly commitments or seats.

No SLA or uptime guarantee

VoxProp operates as a cloud API service designed for flexibility rather than guaranteed availability. We do not offer a Service Level Agreement (SLA) or an uptime guarantee for our infrastructure. While we strive to keep the API running, request processing may experience delays during high load periods, as requests are handled in sequence.

We serve independent agencies and developers without enterprise-level commercial contracts. There are no minimum spend requirements, no dedicated account managers, and no custom SLAs. Our pricing remains transparent at $10 per million characters, billed via US TRC-20, with no monthly commitments or seats.

  • No 99.9% uptime promise
  • No financial credits for downtime
  • Standard queue processing under load

No enterprise contracts

We do not provide traditional enterprise support structures. There are no dedicated account managers, no volume discounts, and no multi-year agreements. Each account is independent, and scaling is handled simply by purchasing more USDT credits.

Support is limited to email. We do not offer phone support or live chat. Responses are provided during business hours, but there is no guaranteed response time. This keeps our overhead low and our API pricing competitive for agencies of any size.

  • Email support only
  • No dedicated account managers
  • No volume discounts

No on-premise installation

VoxProp is a cloud-only service. You cannot install our engines on your own servers or private networks. All processing happens on our cloud infrastructure, requiring only an internet connection to send text and receive audio files via our API.

This architecture means you do not need to manage hardware, GPUs, or software licenses. You simply integrate our endpoint into your virtual tour software or listing platform. All model updates and optimizations are handled centrally by our team.

  • Cloud processing only
  • No local hardware required
  • No license key management

License and trademarks

Sound wave illustration for: License and trademarks

VoxProp is an independent text-to-speech API provider. We are not affiliated with, endorsed by, or connected to OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in our documentation. Our product is a standalone service.

Not affiliated with OpenAI

Our API is not an official OpenAI product. While we mimic the request structure of OpenAI’s speech endpoint for convenience, we operate independently. Our voice models and infrastructure are distinct from OpenAI’s offerings.

OpenAI SDK compatibility noted

We designed our API to be compatible with the official OpenAI SDKs. By changing the base_url to https://api.x06.info/v1, you can use the same SDK code with your VoxProp key. This simplifies integration for developers already familiar with OpenAI’s pattern.

All trademarks belong to their owners

OpenAI, the OpenAI logo, and the GPT series trademarks are the property of their respective owners. We mention them only to describe technical compatibility. Our brand, VoxProp, and its associated logos are the property of this independent storefront.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. He is perfect for reading property specifications, legal descriptions, or factual data where clarity and professionalism are prioritized over emotion.

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. MDN: Web Speech API
  3. curl documentation
  4. openai-python on GitHub
  5. LibriTTS-R corpus (OpenSLR 141)
  6. Tether (USDT)
  7. Python documentation
  8. W3C WAI: making audio and video accessible
  9. LibriTTS-R paper (arXiv 2305.18802)
  10. FFmpeg documentation
  11. TRON developer hub: TRC-20
  12. Node.js documentation

More on this site