Cloud TTS API for Virtual Tour Audio Generation

By PropVoice editorial team · Updated 2026-11-18

PropVoice is a cloud text-to-speech API designed for no-code creators building virtual property tours. Send property descriptions as text and receive audio files. This API lets you turn listing details into guided walkthroughs without hiring voice actors or editing software.

You get a simple POST endpoint compatible with the OpenAI SDK, 8 licensed voices, and 23 languages. Sign up with Google for a free trial, pay only for characters used, and integrate audio into your tours in minutes. No coding skills required.

Cloud TTS API for Virtual Tour Audio Generation

Frequently asked questions

What is text to speech with download?

It is a cloud API where you send text and receive an audio file. You can download the generated speech in formats like mp3, wav, opus, flac, or pcm. This allows no-code creators to easily integrate natural-sounding audio into virtual property tours without managing complex infrastructure or streaming protocols.

Which voice is best for real estate descriptions?

Q: Which voice is suitable for real estate descriptions? A: For property tours, aria (warm, clear narrator) or sage (calm, instructional) are ideal for guided walkthroughs. Felix works well for energetic promos, while atlas provides a neutral news style. You can choose from eight presets including nova, luna, milo, and orion to match your brand’s tone.

How many characters can I send per request?

You can send up to 4096 characters per request. For longer property descriptions, split the text into parts of this size and join the resulting audio files. Each request counts characters including spaces and punctuation, so plan your script segments accordingly to stay within the limit.

What formats can I download?

You can download audio in mp3, wav, opus, flac, or pcm. These formats are specified in the request body. The generated files include an inaudible watermark marking them as synthetic speech. You receive the audio directly in the API response without it being stored on our servers.

Do I need coding skills to use this?

No coding skills are strictly required, but familiarity with HTTP requests helps. The API uses a standard JSON body similar to OpenAI’s format. You can use the official OpenAI SDKs by changing the base URL. Alternatively, use the ready curl example provided on the /get-api-key/ page.

Is there a free trial available?

Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password do not receive trial credit. You can use this to test voice quality and integration before purchasing a top-up for your tours.

How long does generation take?

Generation takes roughly real time, about 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Typical usage for property descriptions remains fast enough for smooth user experiences.

Can I use the audio commercially?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. You receive the audio file directly.

What happens if a request fails?

If synthesis fails, the charge is returned in full. Failed requests are free, so you are not billed for errors. This ensures you only pay for successful audio generation. You can retry the request or adjust parameters like speed or voice to resolve the issue.

Are there any monthly fees?

No, there are no monthly plans, seats, or minimum spend. You pay $0.01 per 1,000 characters. Balance does not expire. You can top up with USDT on the TRON network when needed. This model suits variable usage patterns typical for different property listing volumes.

How do I pay with USDT?

Top up using USDT on the TRON network (TRC-20) only. The minimum amount is $5. Credits are added automatically within minutes after the transfer. No cards, PayPal, or invoices are supported. Send the transfer to the address provided in your account dashboard to activate the balance.

Which languages are supported?

We support 23 languages including English, Spanish, German, French, Chinese, Japanese, Arabic, and Hindi. Any voice can speak any supported language. If the language is not set, it is guessed from the script (Latin text defaults to English). Unsupported languages include Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali. Set the language code explicitly for non-English Latin text.

Is my property data private?

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. Request metadata like time and status is kept for billing. Your property descriptions remain private and are not retained after generation.

Can I change my API key?

Yes, you can issue a new key at any time from your account. The old key stops working immediately when the new one is issued. You can have one active key per account. This allows you to rotate keys for security without interrupting your current services.

First request

curl

curl https://api.play33bm.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 choose TTS for property tours

Sound wave illustration for: Why choose TTS for property tours

Virtual property tours rely on clear communication. Text-to-speech API transforms written listing descriptions into natural-sounding audio files, allowing potential buyers to listen while browsing. This approach keeps visitors engaged longer by providing an auditory layer to visual content.

Natural narration for listings

Natural narration for listings

Select from eight licensed voices, such as Aria (warm, clear narrator) or Atlas (neutral, news), to match the property’s character. Each voice is based on licensed recordings, ensuring professional quality for your virtual walkthroughs without hiring voice actors.

  • Eight distinct voice presets available
  • Licensed from LibriVox recordings

Instant audio downloads

Send text and receive an audio file immediately. The API processes requests sequentially, delivering synthesized speech ready for integration into your tour platform. Failed requests are free, ensuring you only pay for successful audio generations.

No coding required

The API endpoint matches the OpenAI speech structure, so existing tools and no-code automations work by simply changing the base URL. Use the provided curl example or integrate directly into your preferred no-code workflow to generate audio from property descriptions.

  • Compatible with OpenAI SDKs
  • Simple JSON body structure

Supported voices for real estate

Sound wave illustration for: Supported voices for real estate

Selecting the right voice ensures your virtual property tour sounds professional and engaging. Our API offers eight distinct presets.

From warm narrations of property features to clear, instructional guides, you can match the audio tone to the specific listing type without needing voice actors.

Warm narrator for descriptions

Use Aria for welcoming property descriptions. Her warm, clear narration style creates an inviting atmosphere for luxury or family homes.

Luna offers a soft, storytelling approach ideal for highlighting unique architectural details or garden spaces in a virtual walkthrough.

  • Aria: Warm, clear narrator
  • Luna: Soft, storytelling voice

Clear instructions for tours

Nova provides a bright, upbeat tone perfect for modern apartments or quick property highlights. Sage delivers a calm, instructional voice, guiding users through room-by-room tours with clarity.

Milo’s friendly, conversational style works well for casual home tours, making the experience feel personal and approachable.

  • Nova: Bright, upbeat
  • Sage: Calm, instructional
  • Milo: Friendly, conversational

Neutral tone for facts

Atlas offers a neutral, news-style voice ideal for presenting factual data like square footage, price, or amenities without emotional bias.

Orion’s deep, documentary tone suits high-end commercial properties or detailed investment summaries, adding a sense of authority and seriousness.

  • Atlas: Neutral, news-style
  • Orion: Deep, documentary

Supported languages and formats

Sound wave illustration for: Supported languages and formats

PropVoice supports 23 languages, enabling global reach for property tours. Any voice can speak any supported language, covering major markets from English and Spanish to Arabic, Chinese, and Japanese.

23 languages for global reach

The API handles Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If the language is not specified, the system guesses from the script, defaulting to English for Latin text.

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

MP3, WAV, FLAC downloads

Receive audio in MP3, WAV, Opus, FLAC, or PCM formats. These standard file types integrate seamlessly with no-code tour builders and web platforms, ensuring compatibility across devices without requiring conversion.

Optional language tagging

For non-English Latin-script text, explicitly set the language parameter. This prevents incorrect voice selection and ensures accurate pronunciation for multilingual property listings.

How the API works

Sound wave illustration for: How the API works

The API endpoint POST https://api.play33bm.com/v1/audio/speech accepts your property description as JSON. You send the text, voice selection, and format in a single request.

The service processes the input and returns the audio file directly in the response. This allows download or integration into your no-code virtual tour workflow.

Send text via POST request

Send a POST request to https://api.play33bm.com/v1/audio/speech with a JSON body containing the model, input text, voice, and response_format. The text must not exceed 4096 characters.

Include your API key in the Authorization header as Bearer tts-.... You can specify parameters like speed (0.25–4.0) to adjust the narration pace for your property tour.

  • Endpoint: POST https://api.play33bm.com/v1/audio/speech
  • Body: JSON with model, input, voice, response_format
  • Auth: Authorization: Bearer tts-...

Receive audio file instantly

Upon successful synthesis, the API returns the audio file in your chosen format (mp3, wav, opus, flac, or pcm). Failed requests incur no charge.

For longer property descriptions, split the text into 4096-character chunks. Generate each part separately and join the resulting audio files to create a continuous tour narration.

Compatible with OpenAI SDK

The request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by setting base_url to https://api.play33bm.com/v1.

This compatibility allows no-code creators to easily integrate the TTS service into existing automation tools or custom scripts without learning a new API structure.

Pricing for tour creators

Sound wave illustration for: Pricing for tour creators

PropVoice charges $0.01 per 1,000 characters, scaling directly with your tour’s narration needs. Failed synthesis requests are free, ensuring you only pay for usable audio files delivered via our API.

Top-ups use USDT (TRC-20) with a $5 minimum. Credits are automatic and never expire.

Pay per character used

The rate is $10 per million characters. Spaces and punctuation count toward this total. Long property descriptions are split into 4,096-character chunks to ensure stable generation.

If synthesis fails, the charge is returned in full. This protects your budget during high-traffic listing updates.

  • $0.01 per 1,000 characters
  • Failed requests are free
  • USDT (TRC-20) top-ups only

Free trial with Google sign-in

Sign up with Google to receive $0.50 in credit, covering approximately 50,000 characters. This trial is valid for 7 days, allowing you to test audio quality for your first virtual tour without immediate payment.

Email-based accounts start without trial credit. You can add funds via TRC-20 transfers at any time to continue generating narration.

No monthly subscriptions

There are no seats, minimum spends, or recurring plans. You only pay for what you generate. Balance does not expire, so unused credits remain available for future property listings.

Pricing for tour creators

Technical limitations to know

Sound wave illustration for: Technical limitations to know

The API enforces a strict 4096-character limit per request, meaning longer property descriptions must be split into parts. These segments are then joined to form the complete audio file. For texts exceeding this limit, you handle the splitting logic on your end before sending requests.

4096 character limit per request

Each POST request accepts a maximum of 4096 characters, including spaces and punctuation. If your property listing is longer, you must split the text into smaller chunks and concatenate the resulting audio files manually or via script.

Rate limits for stability

New accounts without a top-up are limited to 10 requests per minute. Once you add funds, the limit increases to 60 requests per minute. Requests are processed sequentially, so under load a request may wait in a queue.

No streaming audio support

The API returns the complete audio file only after synthesis finishes. It does not support WebSocket or partial streaming, so you cannot play audio incrementally. This is suitable for pre-generated tour audio but not for real-time interaction.

Voice presets overview

Sound wave illustration for: Voice presets overview

PropVoice provides eight distinct voice presets tailored for virtual property tours, allowing you to match the audio tone to the property’s character. Each voice is designed for clarity and natural flow, ensuring listing descriptions sound professional and engaging.

All voices are based on licensed recordings and every generated file carries an inaudible watermark that marks it as synthetic speech. You can choose from four female and four male presets to suit your brand voice.

Female: Aria, Nova, Luna, Sage

Aria offers a warm, clear narration style ideal for descriptive property overviews. Nova provides a bright, upbeat tone suitable for highlighting key amenities. Luna delivers a soft, storytelling voice for immersive walkthroughs, while Sage remains calm and instructional for detailed feature lists.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Male: Felix, Milo, Atlas, Orion

Felix brings an energetic, promo-ready tone for quick sales highlights. Milo offers a friendly, conversational style for personal property introductions. Atlas provides a neutral, news-style delivery for factual data points, and Orion delivers a deep, documentary voice for premium or historical listings.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Licensed from LibriVox

These voice presets are based on licensed recordings from LibriTTS-R, derived from LibriVox public-domain audiobook readings. This foundation ensures high-quality, natural-sounding synthetic speech suitable for professional real estate applications.

Data privacy and usage

Sound wave illustration for: Data privacy and usage

Your property descriptions are processed strictly to generate the audio file and are not retained for model training. This ensures that your unique listing details remain proprietary and are not used to improve the underlying voice engine.

The generated audio is returned directly in the API response and is not stored on our servers after delivery. You maintain full control over your content assets immediately upon generation.

Text not used for training

Input text is used solely for synthesis. Unlike many consumer TTS services, we do not harvest your property listings or tour scripts to train future voice models. Your data remains yours.

This approach is ideal for no-code creators who want to keep their listing narratives exclusive without worrying about their text becoming part of a public dataset.

Audio returned in response

The synthesized audio file is delivered instantly in the HTTP response body. We do not store the generated MP3, WAV, or FLAC files on our infrastructure after delivery.

This reduces storage dependency and ensures that your tour audio is only available where you choose to host it, whether on your website or a third-party platform.

Metadata kept for billing

We retain minimal request metadata including the timestamp, character count, and status code. This data is used exclusively for accurate billing and tracking your usage limits.

All other request details are discarded after processing, ensuring that your billing records are precise without retaining unnecessary content data.

Get started today

Sound wave illustration for: Get started today

Create your account in seconds using your Google credentials or a standard email and password. Once registered, you are immediately directed to the dashboard where your unique API key is displayed, ready for integration with no-code platforms.

Sign up with Google or email

Visit the /get-api-key/ page to begin. You can choose Google authentication for instant access or use a traditional email and password setup. This creates an independent account specific to play33bm.com.

Get your API key instantly

Upon registration, your API key is generated immediately. Use this key with the Authorization header to start sending requests. You can also issue a new key at any time, which instantly invalidates the old one.

  • Key format: tts-...
  • Starts with $0.50 trial credit for Google sign-ins
  • Email-only accounts start with zero balance

Download your first audio

With your key, send a POST request to the speech endpoint. Provide your property description text and select a voice like Aria or Atlas. The API returns the audio file directly in the response, ready for your tour.

  • Base URL: https://api.play33bm.com/v1
  • Supports OpenAI SDK structure
  • Try the provided curl example on the dashboard

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. openai-node on GitHub
  3. MDN: Web Speech API
  4. LibriTTS-R corpus (OpenSLR 141)
  5. openai-python on GitHub
  6. Python documentation
  7. Node.js documentation
  8. curl documentation
  9. LibriTTS-R paper (arXiv 2305.18802)
  10. LibriVox public-domain audiobooks
  11. OpenAI API reference: create speech
  12. IETF RFC 7845: Ogg Opus

More on this site