Generate MP3 Audio for Real Estate Virtual Tours with Our TTS API

By PlayBossPay editorial team · Updated 2026-11-18

PlayBossPay helps real estate startups turn property listings into engaging audio tours via a simple API. Our text-to-speech solution integrates with your virtual tour platform to create immersive, multilingual voice experiences for buyers, letting you focus on growth while we handle the audio generation.

On this page, you will find concrete details on how to integrate our text-to-speech API into your application. Learn about our 8 professional voices, 23 supported languages, and straightforward pricing based on characters used, so you can start generating high-quality MP3 audio for your listings immediately.

Generate MP3 Audio for Real Estate Virtual Tours with Our TTS API

Frequently asked questions

What is text-to-speech for real estate?

Text-to-speech (TTS) converts your property listing text into natural-sounding audio files. Our cloud API accepts JSON requests and returns audio, allowing you to add voice narration to virtual tours. It supports 23 languages, enabling you to reach international buyers with localized audio descriptions of homes and apartments.

How does TTS enhance virtual property tours?

TTS adds an immersive audio layer to visual tours, guiding buyers through features and neighborhoods. You can use different voices for distinct sections, such as a calm narrator for living spaces or an energetic tone for promotional highlights. This keeps users engaged longer and provides accessible content for visually impaired buyers.

Can the API handle long property descriptions?

Yes, but you must split texts exceeding 4096 characters into smaller parts. Each request handles up to 4096 characters. You can then join the resulting audio files to create a continuous tour. This ensures consistent quality and avoids processing limits while maintaining the narrative flow of your property listings.

Which voices sound best for luxury listings?

For luxury properties, we recommend Aria for a warm, clear narrator or Orion for a deep, documentary-style tone. Atlas offers a neutral, news-like voice suitable for high-end data presentations. Sage provides a calm, instructional tone ideal for detailed feature explanations. Choose based on the specific mood you want to convey.

Does the API support Spanish for 'tts espanol'?

Yes, Spanish is one of our 23 supported languages. Any of our 8 voice presets can speak Spanish fluently. You should specify the language code in your request to ensure accurate pronunciation, especially if the text uses Latin script but isn't English. This ensures natural-sounding audio for Spanish-speaking buyers.

Is the generated audio suitable for commercial use?

Yes, the audio is suitable for commercial use. Each file contains an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain readings. You can use these audio files in your virtual tour platforms, marketing materials, and customer-facing applications without additional licensing fees.

How fast is the audio generation process?

Generation speed is roughly real-time, processing about 25 characters of text per second of audio. Short phrases take a few seconds, while longer texts take longer proportional to their length. Requests are processed sequentially, so high traffic may cause slight delays. The API returns the audio file once synthesis is complete.

Can I use the OpenAI SDK with your API?

Yes, you can use the official OpenAI SDKs. Simply change the base_url to https://api.playbosspay.com/v1 and use your PlayBossPay API key. The request shape matches the OpenAI speech endpoint exactly. This allows you to integrate our TTS service into your existing codebase with minimal changes to your initialization logic.

What happens if a request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry the request with adjusted parameters, such as splitting the text or changing the voice, without worrying about duplicate charges for failed attempts.

Do I need to pay for unused credits?

No, you only pay for what you use. Your balance does not expire, and there are no monthly subscriptions or minimum spend requirements. Unused credits remain in your account until you use them. You can top up with USDT on the TRON network whenever you need more credit for your tours.

Are there any hidden fees for the API?

No, there are no hidden fees. The price is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. There are no subscription fees, seat costs, or VAT invoices. You pay only for the characters processed in successful requests, with clear, upfront pricing.

Can I generate audio for multiple properties at once?

The API processes requests sequentially, one after another. You can send multiple requests concurrently from your application, but they will be queued and processed in order. Under load, a request may wait in the queue. For faster processing of many properties, consider staggering your requests or using a job queue.

Is the API easy to integrate with my startup's tech stack?

Yes, integration is straightforward. We provide a standard JSON API compatible with the OpenAI SDK. You can use plain HTTP or any language that supports JSON. The /get-api-key/ page provides a ready-to-use curl example. Simply send your text, voice, and format preferences, and receive the audio file. It fits easily into modern web and mobile apps.

How many characters can I send in one request?

You can send up to 4096 characters per request. If your property description exceeds this limit, you must split it into smaller parts. Each part generates a separate audio file, which you can then join. This approach ensures consistent quality and avoids processing errors while allowing you to handle long-form content.

First request

curl

curl https://api.playbosspay.com/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Why Real Estate Startups Choose TTS

Sound wave illustration for: Why Real Estate Startups Choose TTS

Real estate buyers expect immersive experiences, but static listings often fall short. By adding voice narration to your virtual tours, you transform dry text into engaging audio guides that help prospects visualize living in a property. This simple enhancement keeps visitors on your page longer and builds an emotional connection before they even pick up the phone.

Our API provides multilingual support without requiring you to manage complex infrastructure. Whether your listing is in English, Spanish, or German, the system handles the audio generation so you can focus on scaling your platform.

Enhance Virtual Tours

Enhance Virtual Tours

Static images and text descriptions are common, but adding a warm narrator like Aria or an energetic promo voice like Felix turns a listing into a story. Buyers can listen while browsing, creating a more memorable experience that highlights key features without requiring them to read every word.

  • Convert listing descriptions into engaging audio tours
  • Keep visitors engaged with background narration
  • Improve accessibility for visual impairments

Multilingual Support

Real estate is local, but your audience is global. Our API supports 23 languages, allowing you to serve listings in Arabic, Chinese, Japanese, and more. If a buyer prefers Spanish or French, the system generates the audio in that language instantly, ensuring no language barrier stops a sale.

  • Support for 23 languages including English, Spanish, and German
  • Automatic language detection or explicit ISO code setting
  • Consistent voice quality across all languages

Scalable Infrastructure

As your startup grows, your audio needs grow with it. Requests are processed at roughly real-time speed, though under load they may wait in a queue. You can scale from a few listings to thousands without worrying about server capacity or complex deployment steps.

  • Handle up to 60 requests per minute per key
  • No server management required
  • Simple JSON integration fits existing workflows

Our TTS API Features

Sound wave illustration for: Our TTS API Features

Our API returns audio files, designed to keep your virtual tour tours responsive and engaging for potential buyers. Simply send text, and receive an MP3 file ready for immediate playback in your application.

Choose from eight distinct voice presets, ranging from warm narrators to deep documentary styles, ensuring your property descriptions match the tone of the listing. Each generated file includes an inaudible watermark that marks it as synthetic speech.

Fast MP3 Generation

Text is processed quickly, with typical generation speeds reaching roughly real-time for long descriptions. Short phrases are produced in just a few seconds, ensuring a smooth user experience without noticeable delays during property navigation.

Requests are processed sequentially, so under heavy load, a request may wait briefly in a queue. Failed requests incur no charge, ensuring you only pay for successful audio generation.

  • - MP3, WAV, OPUS, FLAC, PCM formats available
  • - Up to 4096 characters per request
  • - Automatic character splitting for longer texts

8 Professional Voices

Select from voices like Aria for a warm narrator or Orion for a deep documentary style. All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and can speak any of the supported languages.

Each voice offers a unique character, allowing you to create a consistent brand identity across your virtual tour platform. Mix and match voices for different property types or sections of a tour.

  • - Female: Aria, Nova, Luna, Sage
  • - Male: Felix, Milo, Atlas, Orion
  • - All voices support all 23 languages

23 Supported Languages

Speak to a global audience with support for 23 languages, including English, Spanish, German, French, and Japanese. Any voice can speak any of these languages, providing flexibility in your content strategy.

If the language is not specified, the system guesses from the script (Latin text defaults to English). For non-English Latin-script text, explicitly set the language parameter to ensure accurate pronunciation.

  • - English, Spanish, German, French, Italian
  • - Chinese, Japanese, Korean, Arabic, Hindi
  • - Danish, Dutch, Finnish, Greek, Hebrew
  • - Malay, Norwegian, Polish, Portuguese, Russian
  • - Swedish, Turkish, Swahili

How It Works

Sound wave illustration for: How It Works

Transform property listings into engaging audio tours by sending text through our simple API. You can generate high-quality speech for virtual tours without managing complex infrastructure.

Send Text via API

Send a JSON payload to the speech endpoint with your property description, desired voice, and audio format. The API accepts up to 4096 characters per request, handling standard text input efficiently.

  • POST to /v1/audio/speech
  • JSON body with model, input, and voice

Receive Audio File

Receive the synthesized audio file directly in the response. Choose from MP3, WAV, OPUS, FLAC, or PCM formats. Failed requests are free, so you only pay for successful generations.

Integrate with Your App

Use the official OpenAI SDK (by changing the base URL) or plain HTTP to integrate with your virtual tour platform. The API is designed for easy embedding into existing startup workflows.

Voice Options for Properties

Sound wave illustration for: Voice Options for Properties

Selecting the right voice transforms a static property listing into an engaging audio tour. Our eight presets allow you to match the tone of the home, whether it is a cozy starter house or a high-end luxury estate, ensuring the narration feels professional and inviting.

Warm Narrator (Aria)

Aria offers a clear, warm delivery ideal for storytelling. Her voice adds a personal touch to descriptions of living spaces, making potential buyers feel welcomed as they virtually walk through the front door.

  • Clear and professional tone
  • Ideal for residential descriptions
  • Based on licensed LibriTTS-R recordings

Bright & Upbeat (Nova)

Nova brings energy to your audio tours. Her upbeat style works perfectly for highlighting amenities like modern kitchens, backyard patios, or nearby recreational spots, keeping the listener engaged throughout the tour.

  • Energetic and positive
  • Great for feature highlights
  • Engaging pacing for buyers

Deep Documentary (Orion)

Orion provides a deep, authoritative voice suitable for luxury properties or historical homes. His tone conveys stability and prestige, perfect for detailing architectural significance or high-value investment features in the listing.

  • Deep and authoritative
  • Suitable for luxury listings
  • Conveys stability and prestige

Technical Specifications

Sound wave illustration for: Technical Specifications

Our API matches the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by changing the base_url to https://api.playbosspay.com/v1. This compatibility lets real estate startups integrate our text-to-speech solution into existing virtual tour platforms with minimal code changes.

OpenAI Compatible SDK

You can send requests using standard libraries like Python or Node.js. Just update the base URL and use your PlayBossPay API key for authentication. This approach ensures a familiar developer experience while leveraging our specialized TTS engine.

  • Compatible with official OpenAI SDKs
  • Simple base URL configuration
  • Standard Bearer token auth

Multiple Audio Formats

Generate audio in mp3, wav, opus, flac, or pcm formats. MP3 is ideal for web-based virtual tours due to its small file size and broad player support. WAV and FLAC offer lossless quality for high-fidelity audio presentations.

Simple JSON Body

Send a POST request to /v1/audio/speech with a JSON body. Include the model (tts-1 or tts-1-hd), your text input, the desired voice, and the response format. The API returns the audio file directly in the response.

  • Standard JSON request structure
  • Supports up to 4096 characters per request
  • Optional language parameter for non-English scripts
Technical Specifications

Pricing for Startups

Sound wave illustration for: Pricing for Startups

Our pricing model is designed for real estate startups that need predictable costs without the burden of unused capacity. You pay only for the characters processed in your text-to-speech requests, making it easy to forecast expenses for virtual tour audio generation.

Pay Per Character

The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters, so your billing reflects the exact text sent to the API.

  • Transparent, usage-based billing
  • Failed requests are free

No Monthly Fees

There are no monthly plans, no seats, and no minimum spend. You can top up your balance whenever needed and use it as your virtual tour tours expand or contract.

Free Trial Credit

Sign up with Google to receive $0.50 of trial credit, valid for 7 days. This gives you about 50,000 characters to test voice quality and integration speed before committing.

Supported Languages

Sound wave illustration for: Supported Languages

Our TTS API supports 23 languages, allowing you to reach global audiences with consistent voice quality. Whether your listing is in English, Spanish, German, or any of the other supported languages, the engine handles the nuances accurately.

You can specify the language via an ISO code in your API request to ensure correct pronunciation, especially for non-English texts in Latin script. This ensures your virtual tours sound natural and professional for every buyer.

English & Spanish

English and Spanish are fully supported with all 8 voice presets. These languages cover the majority of international real estate markets, ensuring clear and engaging audio for property descriptions.

Bullets: [

German & French

German and French are included in our 23 supported languages, with dedicated voice profiles that maintain clarity and tone. Use these to localize tours for European markets without extra integration work.

Bullets: []}, {

Global Reach

Beyond English, Spanish, German, and French, we support 19 additional languages including Arabic, Chinese, Japanese, and Portuguese. This allows startups to scale their virtual tour offerings to diverse buyer bases worldwide.

Bullets: [

Reliable Performance

Sound wave illustration for: Reliable Performance

Text-to-speech generation runs at roughly real-time speed, processing approximately 25 characters per second for long property descriptions. Short phrases may take a few seconds to complete.

Because requests are processed sequentially, heavy load might introduce brief queue delays. Requests are processed sequentially, so under load a request may wait in a queue.

Real-Time Generation

Synthesis speed matches spoken pace, ensuring audio files are ready shortly after the text is submitted. Long property listings are split internally into 4,096-character segments and joined seamlessly.

60 Requests Per Minute

Each API key supports up to 60 requests per minute once your account is active. New accounts start with a limit of 10 requests per minute until the first top-up is processed.

  • Standard limit: 60 requests/minute
  • Trial limit: 10 requests/minute

Automatic Failover

If synthesis fails due to server issues, your balance is not charged. The request is marked as failed, allowing you to retry without penalty.

Get Started Today

Sound wave illustration for: Get Started Today

To begin, visit our /get-api-key/ page and sign up using your Google account or an email and password. This creates your independent account on playbosspay.com, where you will immediately receive $0.50 in free trial credit valid for seven days.

After registration, you will see your unique API key, current balance, and a ready-to-use curl example. You can start generating audio instantly without entering a credit card or committing to a monthly plan.

Sign Up for Free

Navigate to the sign-up page and choose Google authentication or email registration. Accounts are created per site, so ensure you are on playbosspay.com. Your trial credit activates immediately upon sign-in.

Get Your API Key

Once logged in, your dashboard displays your active Bearer key. You can issue a new key at any time, which immediately invalidates the old one. Use this key with the OpenAI SDK by pointing your base URL to https://api.playbosspay.com/v1.

  • Copy your key from the dashboard
  • Update your SDK base_url
  • Revoke old keys instantly if needed

Start Generating Audio

Send a POST request to /v1/audio/speech with your listing text. Receive an MP3 file ready to embed in your virtual tour platform. With 60 requests per minute, you can process multiple property listings quickly.

  • Post text to the speech endpoint
  • Receive MP3, WAV, or OPUS
  • Integrate directly into your app

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Our platform empowers startups to create immersive virtual tours for real estate properties, transforming how clients experience homes from anywhere.

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. openai-node on GitHub
  4. TRON developer hub: TRC-20
  5. IETF RFC 7845: Ogg Opus
  6. FFmpeg documentation
  7. W3C WAI: making audio and video accessible
  8. LibriTTS-R corpus (OpenSLR 141)
  9. LibriVox public-domain audiobooks
  10. Tether (USDT)
  11. OpenAI API reference: create speech
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site