About PropVoice: The Editorial Team Behind Our TTS API

By PropVoice editorial team · Updated 2026-11-18

PropVoice is an independent storefront for a text-to-speech API designed for no-code creators in real estate. We focus on turning property descriptions into natural audio for virtual tours, without the complexity of enterprise contracts or certifications.

We are not affiliated with major tech brands or OpenAI. This page explains the API details, data policies, and limitations so you can integrate audio into your no-code workflows with confidence. Read on to understand the licensing, data usage, and how to reach support.

About PropVoice: The Editorial Team Behind Our TTS API

Frequently asked questions

Who runs this site?

This is an independent storefront for the PropVoice text-to-speech API. Accounts are created per site, and we operate as a standalone provider for no-code creators building virtual property tours.

Are you affiliated with OpenAI?

No. We are not affiliated with OpenAI, despite our API shape matching their speech endpoint. We use the same request structure but operate independently with our own keys, pricing, and infrastructure.

Where do voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These originate from LibriVox public-domain audiobook readings, ensuring clear, natural-sounding audio for your real estate walkthroughs.

Is my data private?

Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata for billing purposes.

How do I contact support?

Support is available by email only. We do not offer a phone number, live chat, or instant messaging. Please reach out via the contact page for assistance with your account.

Do you have an SLA?

We do not offer a Service Level Agreement or uptime guarantee. Requests are processed sequentially, so under load, synthesis may wait in a queue. Typical speed is roughly real-time for long texts.

Are you HIPAA certified?

No. We do not hold certifications such as HIPAA, SOC 2, or GDPR certificates. Our service is designed for general real estate marketing and virtual tour audio, not regulated medical data.

Do you store audio files?

Generated audio is returned in the response and is not stored by us. Only request metadata (time, characters, status) is kept for billing and usage tracking purposes.

Is text used for training?

No. Your input text is used solely to generate the audio file for your request. It is not used for model training or to improve our voice engines over time.

Can I request a feature?

We do not have a public feature request board or voting system. Since we are an independent storefront, you can email us directly to share feedback or suggest improvements for the API.

Do you have a blog?

We do not maintain a public blog. Updates and information are provided through our documentation and direct communication. Visit our docs page for technical details and integration guides.

Are there refunds?

Failed requests are free, and the charge is returned in full if synthesis fails. For other cases, refunds are handled via email support. We do not have an automated refund portal.

Is USDT the only payment?

Yes. Top-ups are accepted via USDT on the TRON network (TRC-20) only. We do not accept credit cards, PayPal, or subscriptions. Minimum top-up is $5, credited automatically within minutes.

Do you offer enterprise plans?

No. We offer no monthly plans, no seats, and no enterprise contracts. Pricing is flat at $10 per million characters, with no minimum spend or volume tiers required.

Can I get an invoice?

No. We do not issue invoices with VAT. Payments are made via cryptocurrency, and your balance history is visible in your account dashboard for your records.

Is the API open source?

No. The API is proprietary. You can use the official OpenAI SDKs by changing the base URL, but the underlying engine and code are not open source.

Do you have a team page?

No. We do not have a public team page listing individual staff members. Support is handled via email, and the service is operated by the independent storefront team.

Where are you located?

We are a cloud-based API service with no specific physical data center choice for customers. We do not offer on-premise installations or specify a single geographic location for our operations.

Is the site secure?

We use standard secure connections for API requests. We do not claim specific security certifications like SOC 2. Your API key is the primary method for securing access to your account.

Do you use cookies?

We use cookies for site functionality and authentication. Specific details are not listed here, but standard web practices apply. You can manage preferences in your browser settings.

Who we are

Sound wave illustration for: Who we are

PropVoice is an independent storefront, not a subsidiary of a major tech company. We built a specialized text-to-speech API designed specifically for no-code creators who need to turn property descriptions into natural-sounding audio for virtual tours.

We operate independently of OpenAI, ElevenLabs, and other brands. Our focus is entirely on the practical needs of real estate professionals, ensuring the API integrates seamlessly into existing no-code workflows without requiring complex engineering.

We offer straightforward pricing and reliable audio generation that fits directly into website builders and tour platforms.

Independent editorial team

Independent editorial team

We are an independent storefront team. Unlike large corporations, we focus on delivering a reliable, straightforward API without unnecessary bloat.

We maintain the code and documentation directly.

  • Support via email
  • Transparent pricing with no hidden fees
  • Built by creators, for creators

No affiliation with major brands

No affiliation with major brands

We are not affiliated with OpenAI, Google, Amazon, or Microsoft. While our API endpoint mimics the OpenAI speech endpoint for ease of use, we are a separate entity.

This independence allows us to offer competitive pricing and specific features tailored to real estate needs, without the overhead of a large parent company.

Focused on real estate needs

Focused on real estate needs

Our voices are suitable for guiding users through virtual property tours. We support 23 languages, including English, Spanish, and French, catering to a global audience.

We provide simple, character-based pricing ($10 per million characters) and no monthly subscriptions, making it easy for agents to budget for their audio needs.

Voice licensing

Sound wave illustration for: Voice licensing

PropVoice’s eight voice presets are not generated from scratch but are derived from licensed recordings of the LibriTTS-R dataset. This foundation ensures consistent synthetic speech suitable for property descriptions and guided tours.

The underlying recordings originate from LibriVox, a platform providing public domain audiobook readings. By utilizing these established sources, we deliver reliable audio.

Based on LibriTTS-R

Based on LibriTTS-R

All eight voices—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are synthesized using the LibriTTS-R dataset. This dataset provides the acoustic variety for distinct tones, from warm narrators to energetic promotional voices.

The voices support all 23 languages, allowing your virtual tours to sound natural whether describing a kitchen in English or a garden in Spanish.

  • Eight distinct voice presets derived from a single, consistent dataset
  • Acoustic variety supports different tour styles, from calm walkthroughs to energetic promos

CC BY 4.0 licensed

CC BY 4.0 licensed

The audio data powering our engine is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). This license permits commercial use, allowing PropVoice to distribute the resulting TTS audio files to our clients without additional royalty fees.

Users of our API do not need to attribute each generated audio file individually.

  • Commercial use permitted under CC BY 4.0
  • Simplified compliance for generated audio files

From LibriVox public domain

The source recordings come from LibriVox, where volunteers read books in the public domain. These recordings form the backbone of our voice models, providing a rich, human-like base for our synthetic engines.

Because the source material is public domain, we avoid the recurring costs associated with proprietary voice actors.

  • Source recordings from volunteer-read public domain books
  • No recurring royalty fees for voice talent

Data policy

Sound wave illustration for: Data policy

PropVoice prioritizes data privacy. We process input text solely to generate the requested audio file and do not use your property descriptions to train our models. This ensures your unique listing copy is not repurposed for future model improvements.

Text not used for training

Your property descriptions are used exclusively for synthesis. Once the audio is generated, the text is not retained for machine learning purposes, keeping your listing content distinct from our training data.

Audio returned in response

Generated audio files are delivered directly in the API response. We do not store the audio files after delivery, ensuring that your virtual tour audio remains transient and under your control.

Metadata kept for billing

We retain request metadata, including timestamps, character counts, and status, strictly for billing accuracy. This allows us to verify charges against your usage.

Honest limitations

Sound wave illustration for: Honest limitations

PropVoice prioritizes stable file generation over complex, real-time streaming. Our API returns complete audio files (mp3, wav, opus, flac, pcm) rather than partial streams. This ensures that your virtual property tour audio is coherent and ready to embed directly into your no-code website or tour builder.

There is no SSML support for fine-grained control over pauses or emphasis, and we do not offer custom voice cloning. You choose from our eight licensed presets.

No streaming audio

We do not offer WebSocket or streaming endpoints. Each POST request returns a fully synthesized audio file. Short phrases may take a few seconds to generate, and under load, requests queue sequentially.

This means you cannot play audio word-by-word as it is generated.

  • Returns complete files (mp3, wav, opus, flac, pcm)
  • No real-time partial audio chunks
  • Simpler integration for static embeds

No SSML support

Our API does not support Speech Synthesis Markup Language (SSML). You cannot use tags to control pauses, volume, or pronunciation within the request. Voice characteristics are determined by the selected preset (e.g., aria for narration, atlas for news-style delivery).

If you need specific pacing, you can insert ellipses (...) or commas in your text to create natural breaks.

  • No SSML tags
  • No custom pauses or volume control
  • Rely on text punctuation for natural flow

No voice cloning

We do not offer custom voice cloning or upload-your-own-voice features. All audio is generated from eight presets based on licensed recordings from LibriTTS-R (CC BY 4.0). These voices are consistent.

If you require a unique voice, you would need to use one of our existing presets. We do not build custom models for individual clients.

  • No custom voice uploads
  • No cloning of specific individuals
  • Eight consistent, licensed presets

Contact and support

Sound wave illustration for: Contact and support

All inquiries go through email.

Email support only

Send your message to the contact form or support email.

No phone or live chat

We do not offer phone numbers or live chat widgets.

Response within 24 hours

Why we built this

Sound wave illustration for: Why we built this

PropVoice allows no-code creators to turn property descriptions into audio without hiring voice actors or learning complex tools. Our API fits directly into virtual tours, letting users generate guided walkthroughs with a single request.

Need for no-code solutions

Our API sends text and returns audio, fitting seamlessly into tools like Zapier or Make.com.

The process is simple: send a property description, receive an MP3 or WAV file.

  • Works with Zapier, Make, and other no-code automation tools
  • Simple JSON input and audio output
  • No coding required to integrate

Real estate specific features

The 8 voice presets allow creators to match the tone of the property. Support for 23 languages helps reach international buyers.

Each audio file includes an inaudible watermark, marking it as synthetic.

  • 8 voice presets for different property tones
  • Support for 23 languages
  • Inaudible watermark in every audio file

Transparent pricing

Pricing is $0.01 per 1,000 characters, with no monthly plans. Failed requests are free, so you only pay for successful audio generation. You can top up with USDT on TRON, with a minimum of $5 and no expiration.

  • $0.01 per 1,000 characters
  • No monthly plans or subscriptions
  • Free failed requests

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Explore every room in stunning detail with our easy virtual tours designed for no-code creators.

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. LibriTTS-R paper (arXiv 2305.18802)
  4. Node.js documentation
  5. Creative Commons Attribution 4.0
  6. openai-node on GitHub
  7. openai-python on GitHub
  8. FFmpeg documentation
  9. ISO 639 language codes
  10. LibriTTS-R corpus (OpenSLR 141)
  11. Python documentation
  12. Tether (USDT)

More on this site