Frequently asked questions
What is text-to-speech?
Text-to-speech (TTS) is a cloud API that converts written text into audio files. You send a JSON request with your property listing text, and receive an audio file back. It supports multiple languages and voices, allowing you to create engaging audio tours for your real estate virtual tours without recording human narrators.
How does TTS work for real estate?
Send property details via POST to /v1/audio/speech. The API synthesizes the text into audio using chosen voices like Aria or Felix. You can specify formats like MP3 or WAV. The audio is returned directly in the response, ready to be embedded in your virtual tour platform or website for buyers to listen to.
Which voice is best for luxury properties?
For luxury properties, we recommend Aria for a warm, clear narrator feel, or Atlas for a neutral, news-style delivery. Orion offers a deep, documentary tone suitable for high-end estates. Since any voice can speak any language, choose based on the desired emotional tone of your specific property listing.
Can TTS handle technical property terms?
Yes, the API reads standard text accurately. However, it does not support custom pronunciation lexicons or SSML. If specific terms need precise pronunciation, you may need to spell them out phonetically in the input text. The voices are trained on licensed recordings, ensuring clear articulation of standard English and other supported languages.
How do I integrate TTS into my website?
Use the OpenAI SDK or plain HTTP. Change the base_url to https://api.playbosspay.com/v1 and use your API key. Send a POST request with your property text to /v1/audio/speech. The response contains the audio file, which you can then play in your web player or download for your virtual tour platform.
Is the audio quality high enough for commercials?
Yes, the audio is generated from licensed recordings. Use the tts-1-hd model for higher quality. The audio carries an inaudible watermark marking it as synthetic.
Do I need to pre-generate all audio?
No, you can generate audio on demand. Send a request when a user views a property. For longer texts, split them into parts of up to 4096 characters. Join the resulting audio files. This allows for dynamic content updates without storing large audio libraries, though pre-generation can speed up user experience.
Can I change the voice after generation?
No, once the audio file is generated, the voice is fixed. To change the voice, you must send a new API request with the desired voice parameter. Each request generates a new audio file. You can issue a new API key at any time, but the audio content itself remains tied to the generation parameters.
How does language detection work?
If you do not specify a language, the API guesses it from the script. Latin script text defaults to English. For non-English Latin text, you should set the language parameter explicitly. Supported languages include Arabic, Chinese, French, German, Spanish, and others. If the language is not in the list, it may not be supported.
What if the text is in multiple languages?
The API does not support switching languages within a single request. You should split the text into separate requests for each language. Generate audio for each segment and join them. Ensure you specify the correct language code for each segment to avoid incorrect voice synthesis or defaulting to English.
Is there a limit on text length?
Yes, each request can handle up to 4096 characters. Spaces and punctuation count as characters. For longer property descriptions, split the text into parts. Generate audio for each part and join the files. This ensures optimal processing and avoids exceeding the character limit for a single synthesis job.
How long does generation take?
Generation takes roughly real time, about 25 characters per second. Short phrases take a few seconds. Requests are processed sequentially, so under load, you may experience queue delays. For urgent needs, ensure your API key is active and within rate limits to minimize waiting times for your virtual tour users.
Can I use the audio on social media?
Yes, you can use the generated audio on social media. The audio files are returned in your chosen format (MP3, WAV, etc.). Note that each file carries an inaudible watermark indicating it is synthetic speech. Ensure your usage complies with the platform's terms and any specific attribution requirements you choose to display.
Do I own the rights to the audio?
The voices are based on licensed recordings (LibriTTS-R, CC BY 4.0) from LibriVox public-domain audiobook readings. You pay for the synthesis service.
How do I handle failed requests?
Failed requests are free; the charge is returned in full if synthesis fails. You can retry the request with the same or modified parameters. Ensure your text is within the 4096 character limit and the voice is valid. Check your API key status and balance to ensure the request can be processed successfully.
What is the difference between tts-1 and tts-1-hd?
Both models use the same engine and price. The difference is audio quality. tts-1-hd provides higher fidelity audio. tts-1 is standard quality. Choose based on your budget and the desired audio experience for your real estate listings. Both support the same voices, formats, and speed settings.
Can I use the API for WhatsApp messages?
Yes, you can generate audio files and send them via WhatsApp. Generate the audio using the API, then attach the file to your WhatsApp message. This allows you to send voice notes of property listings to clients. Ensure the file format (e.g., MP3, WAV) is compatible with WhatsApp's audio message requirements.
Is the API secure?
Yes, use your Bearer token for authentication. Keep your API key secure. Each account has one active key; issuing a new one deactivates the old one immediately. Requests are sent over HTTPS. Input text is used only for synthesis and not for training. Metadata is kept for billing but input is not stored long-term.
How do I track usage?
Track usage via your account dashboard at /get-api-key/. It shows your balance, characters left, and usage history. The API keeps request metadata for billing. You can also monitor your API key status and balance directly from the dashboard to ensure you have sufficient credits for your virtual tour projects.
Can I customize the speed?
Yes, you can set the speed between 0.25 and 4.0. Adjusting the speed allows you to create faster or slower narration for your property tours. This is useful for highlighting key features or providing a relaxed listening experience. The speed parameter is part of the JSON request body sent to the API.
What formats are best for mobile?
MP3 is widely supported and offers good compression. WAV provides high quality but larger files. OPUS is an efficient format. FLAC is lossless. For mobile virtual tours, MP3 or OPUS are recommended for balance between quality and file size. Ensure your mobile player supports the chosen format for seamless playback.
Does the API support SSML?
No, the API does not support SSML. It processes plain text input. You cannot use SSML tags for pauses, emphasis, or pronunciation changes. If you need specific pacing, you can adjust the speed parameter or split the text into separate requests. This keeps the integration simple but limits fine-grained control.
Can I clone a specific voice?
No, custom voice cloning is not offered. You can choose from 8 preset voices like Aria, Nova, or Felix. These voices are based on licensed recordings. You cannot upload your own voice or design a custom voice. The available voices cover various tones suitable for real estate, from warm narrators to energetic promos.
Is there a free tier?
Yes, sign in with Google to get a $0.50 free trial, valid for 7 days. This covers about 50,000 characters. Email/password accounts start without trial credit. After the trial, you can top up with USDT on the TRON network. There are no monthly plans or minimum spend requirements.
How do I contact support?
Support is available by email only. There is no phone number or live chat. Visit the /contact/ page to send your inquiry. Support is provided by the team behind PlayBossPay. Response times may vary, so plan your virtual tour launches accordingly. Include your API key and details of your issue in the email.
Understanding TTS in Real Estate
Text-to-speech transforms static property listings into immersive audio tours, allowing potential buyers to experience a home’s narrative without staring at a screen. By sending text via our API, you receive high-quality audio files that enhance the storytelling of virtual tours.
This approach is particularly effective for real estate startups aiming to differentiate their offerings. It turns dry descriptions into engaging experiences, keeping visitors on your site longer and providing a modern touch to traditional property marketing.
Audio Enhances Listings
Audio adds an emotional layer to property data. When a buyer hears a warm, clear narrator describe a luxury penthouse or an energetic voice highlights a promo deal, the listing feels more personal and memorable compared to text-only content.
Listeners can multitask, listening to tour details while commuting or working, which increases the reach of your marketing materials.
- Creates an emotional connection with the property
- Allows users to consume content while doing other tasks
- Differentiates your startup from text-only competitors
Accessibility Benefits
TTS ensures your listings are accessible to users with visual impairments or reading difficulties. By providing audio versions of property descriptions, you comply with broader accessibility standards and reach a wider audience of potential buyers.
Our API supports 23 languages, including English, Spanish, and French, ensuring that non-native speakers or international buyers can understand the property details clearly.
- Supports users with visual or reading challenges
- Accommodates non-native speakers in multiple languages
- Improves overall user experience inclusivity
Engagement Metrics
Audio tours typically increase time-on-page metrics. Users spend more time listening to a property’s features than scanning bullet points, which signals higher interest to search engines and improves your site’s SEO performance.
Higher engagement rates often correlate with increased inquiry volumes. When buyers feel more connected to the property through audio, they are more likely to schedule a viewing or contact the agent.
Tracking these metrics helps you optimize your listings for better conversion rates over time.
- Increases average time spent on listing pages
- Reduces bounce rates by providing engaging content
- Correlates with higher inquiry and conversion rates
Choosing the Right Voice
Selecting the correct voice ensures your property tours sound professional and match the listing’s vibe. Our eight presets cover every tone you might need, from soft storytelling to energetic promotions.
Warm Narrator for Luxury
Use Aria for high-end listings. Her warm, clear narration highlights premium details without distracting from the visuals.
Energetic for Promos
Felix brings energy to quick sales or open house announcements. His upbeat tone keeps buyers engaged and excited.
Calm for Instructions
Sage offers a calm, instructional tone perfect for guiding users through virtual tour controls or technical steps.
Technical Integration Steps
Integrating PlayBossPay’s TTS API into your real estate platform requires minimal code changes. Start by securing your API key from the dashboard and configuring your SDK’s base URL to https://api.playbosspay.com/v1. This allows you to use standard OpenAI-compatible libraries for seamless connectivity, as the API follows the same request shape.
API Key Setup
Authenticate requests using the Authorization: Bearer header with your unique key. Each account holds one active key; issuing a new one immediately invalidates the old one, ensuring secure access control for your development and production environments.
- Retrieve key from /get-api-key/
- Set base_url to api.playbosspay.com/v1
- Use Bearer token in headers
Text Formatting
Send property descriptions via a POST request to /v1/audio/speech. Ensure input text stays under 4096 characters. The API supports optional language ISO codes to guide pronunciation, though it defaults to English for Latin scripts.
- Max 4096 characters per request
- Specify voice (e.g., 'aria', 'atlas')
- Choose format (mp3, wav, etc.)
Audio Playback
The API returns the generated audio file directly in the response body. You can save this binary data to the user’s browser or for later playback. Ensure your player handles the selected response format correctly.
Handling Long Property Descriptions
When property descriptions exceed the 4,096 character limit per request, your system must split the text into smaller chunks. This ensures each API call stays within the single-request boundary, preventing truncation or errors during synthesis.
The API returns separate audio files for each segment. Your application is responsible for joining these files in order. This approach maintains audio quality and allows for efficient processing of long, detailed listing narratives.
Splitting Text
Divide the listing text into segments of up to 4,096 characters. Ensure breaks occur at natural sentence boundaries to avoid cutting off words mid-sentence, which improves the listener’s experience during the tour.
Send each segment as a separate POST request to the speech endpoint. Since requests are processed sequentially, consider queuing them to manage the 60 requests per minute rate limit.
- Maximum 4,096 characters per request
- Split at sentence boundaries for natural pauses
- Queue requests to stay under 60 RPM
Joining Audio Files
Receive the audio blobs or file URLs from each successful synthesis response. Concatenate these files in the exact order they were requested. The API does not handle long-form stitching, so your backend or client must merge them.
Ensure consistent formats (e.g., mp3 or wav) across all segments. Mismatched formats can cause playback issues when joining the final audio tour file for the buyer.
- Maintain original request order
- Use consistent response_format for all segments
- Merge files in your application layer
Seamless Playback
Test the joined audio for continuity. Since the TTS engine generates each segment independently, there may be slight gaps or variations in tone between chunks. Pre-listen to ensure the transition feels natural for a property tour.
For long tours, consider caching the final joined audio file. This reduces repeated API calls and storage costs, providing instant playback for subsequent visits to the same virtual tour.
- Cache joined audio to save costs
- Verify tone consistency between segments
- Test playback on mobile tour devices
Multilingual Support
Our API supports 23 languages, enabling you to reach global buyers without hiring separate voice actors. You can generate audio tours in Arabic, Chinese, French, Spanish, and more, all using the same simple endpoint.
The system automatically detects language from the text script. For non-English Latin text, we recommend explicitly setting the language parameter to ensure accuracy.
Detecting Language
The API guesses the language from the input text. Latin script defaults to English, so always specify the language for other languages to avoid misinterpretation.
- Automatic detection works best with distinct scripts like Chinese or Arabic.
- Latin script defaults to English if not specified.
Setting ISO Codes
Pass the ISO language code (e.g., 'fr' for French) in the request body. This ensures consistent voice output regardless of the input text's subtle variations.
All 8 voices can speak all 23 supported languages, giving you flexibility in tone across different regions.
- Use standard ISO 639-1 codes.
- Supported languages include German, Japanese, Korean, and Russian.
Global Buyers
Create multilingual virtual tours to engage international investors. Simply swap the voice or language code to localize the experience.
Note that Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and others are not supported, so verify your target markets before deployment.
- Reach buyers in 23 languages.
- Ensure audio files match the listing's target region.
Cost Optimization Strategies
Optimizing costs in your real estate TTS workflow hinges on precise input management and strategic audio storage. Since pricing is strictly $0.01 per 1,000 characters, understanding exactly how your property descriptions are counted ensures you only pay for what you generate.
Character Counting
Every character, including spaces and punctuation, counts toward your 4,096-character limit per request. To avoid unnecessary charges, strip trailing whitespace from your listing descriptions before sending them to the API. This simple cleanup step reduces waste without affecting the final audio quality.
- Spaces and punctuation count as characters.
- Aim for concise, clean text inputs.
Caching Audio
Property listings rarely change their core description text. By storing generated audio files locally or on your CDN, you eliminate redundant API calls for static content. This is especially effective for long-term listings where the voiceover remains unchanged for months.
- Store generated MP3s or WAVs for static listings.
- Replay cached audio instantly for returning users.
Batch Processing
When updating a large inventory, process multiple listings during off-peak hours to manage queue latency effectively. While each request is processed sequentially, batching your integration logic ensures consistent throughput without overwhelming the 60 requests-per-minute limit during high-traffic viewing periods.
- Respect the 60 requests per minute limit.
- Queue updates during low-traffic windows.
Common Use Cases
Integrating text-to-speech transforms static property data into immersive experiences, allowing potential buyers to engage with listings on their own terms. By converting written descriptions into natural-sounding audio, you enable hands-free exploration, which is particularly useful for users browsing on mobile devices or those with visual impairments.
Virtual Walkthroughs
Pair your API with 360-degree images to create guided audio tours. As users navigate rooms, the TTS engine reads the property details, highlighting unique features like architectural details or recent renovations.
- Sync audio cues with virtual camera movements for a guided tour experience.
- Use voices like Aria for a warm, inviting narration style suitable for luxury homes.
Listing Announcements
Automate social media or email updates by converting new listing summaries into audio clips. This adds a personal touch to notifications, increasing open rates and engagement compared to plain text alerts.
Generate short, energetic clips using Felix to announce price drops or open house events, capturing attention quickly in crowded digital feeds.
- Convert markdown listing summaries into MP3 files for email newsletters.
- Use speed settings (0.25–4.0) to keep announcements concise and engaging.
Multimedia Brochures
Embed audio players directly into digital brochures or property websites. Buyers can listen to detailed property histories, neighborhood guides, or amenity descriptions while scrolling through high-resolution images.
Support global buyers by generating audio in multiple languages, such as Spanish or French, to cater to international interest without hiring separate voice actors.
- Generate audio in 23 languages to reach diverse buyer demographics.
- Use FLAC format for high-quality brochures where file size is less critical.

Quality Assurance
Ensure your property audio tours deliver a polished experience by verifying voice quality, timing, and file integrity before deployment. Consistent quality builds trust with potential buyers, whether they are listening to a luxury listing or a quick neighborhood overview.
Listening Samples
Review generated audio for clarity and natural flow. Use the eight preset voices to match the property’s vibe, such as Aria for warm narrations or Felix for energetic promos.
- Test voice tone against property type
- Check for unnatural pauses or artifacts
- Verify watermark presence in synthetic files
Latency Checks
Monitor generation speed, which averages real-time (25 characters per second). Short phrases may take a few seconds to process, while longer texts queue under load.
- Measure time-to-first-byte for short clips
- Monitor queue delays during peak hours
- Ensure playback starts promptly after generation
Format Verification
Confirm audio files match your requested format (mp3, wav, opus, flac, or pcm). Verify that files play correctly across different virtual tour platforms and devices.
- Validate file extension matches request
- Test playback on mobile and desktop
- Check bitrate and codec compatibility
Troubleshooting
Even with robust integration, minor hiccups can occur when generating audio for property tours. Understanding common pitfalls like audio glitches, voice mismatches, or rate limits helps you resolve issues quickly without disrupting the buyer experience.
Most problems stem from input formatting or API constraints. By checking your text structure and monitoring request volumes, you can maintain smooth audio playback for your virtual tours.
Audio Glitches
Glitches often result from exceeding the 4096-character limit per request. If your property description is long, split the text into smaller chunks and join the resulting audio files seamlessly.
- Ensure no single request exceeds 4096 characters.
- Verify that joined audio files play without gaps.
- Check for encoding errors in unsupported formats.
Voice Mismatch
If the voice does not match the language, ensure you set the language parameter explicitly. Latin-script text defaults to English, so non-English Latin text requires a specific ISO code.
- Set
languagefor non-English Latin text. - Verify voice compatibility with the target language.
- Avoid guessing language for mixed-script content.
Rate Limit Hits
You are limited to 60 requests per minute per key. If you hit this limit, requests will wait in a queue. Monitor your usage and adjust batch processing to stay within limits.
- Limit to 60 requests per minute.
- Wait in queue if limit is reached.
- Monitor usage via the dashboard.
Best Practices
Integrating text-to-speech into real estate tours requires more than just API connectivity; it demands careful preparation of the source text to ensure natural auditory delivery. By structuring your property descriptions with clear punctuation and avoiding ambiguous abbreviations, you enable the TTS engine to generate smoother, more professional audio tours that enhance the buyer's experience without sounding robotic or disjointed.
Consistency in voice selection and tone across all your listings builds a recognizable brand identity for your virtual tour platform. Whether you are using a warm narrator for luxury estates or a calm voice for instructional guides, maintaining uniform audio quality helps potential buyers focus on the property details rather than noticing jarring transitions between different voice presets or styles.
Clear Text Structure
Prepare your property descriptions before sending them to the API. Remove special characters that might confuse the synthesizer, such as complex mathematical symbols or excessive punctuation marks. Break long paragraphs into shorter sentences to match the 4096-character limit per request, ensuring each segment represents a complete thought.
Avoid using abbreviations like 'st.' or 'ave.' unless you explicitly spell them out as 'street' or 'avenue'. This prevents the TTS engine from pronouncing them incorrectly, such as reading 'st.' as 'st' with a clipped sound, which can disrupt the immersive feel of a virtual walkthrough.
- Spell out numbers and symbols for accurate pronunciation
- Use clear sentence boundaries to aid natural pacing
- Remove complex special characters that may cause errors
Consistent Tone
Choose a single voice preset for your entire platform to maintain a cohesive brand experience. For example, use 'sage' for instructional content and 'aria' for luxury listings, but ensure these choices are applied uniformly across all properties. This consistency helps users develop an auditory association with your brand.
Match the voice character to the property type. A deep, documentary-style voice like 'orion' suits large estate tours, while a bright, upbeat voice like 'nova' works well for quick promotional highlights. Avoid switching voices within a single property tour to prevent user confusion.
- Select one voice per property type
- Maintain uniform voice usage across all listings
- Match voice character to property luxury level
User Testing
Conduct listening tests with real users before launching a new tour feature. Ask testers to evaluate the audio clarity, pacing, and emotional tone of the generated speech. This feedback loop helps you identify any awkward phrasing or pronunciation issues that your internal team might have missed.
Test the audio on various devices, including mobile phones and desktop speakers, to ensure the sound quality is optimal across all playback environments. Pay attention to how the audio integrates with the visual elements of your virtual tour platform, ensuring it enhances rather than distracts from the visual experience.
- Gather feedback from real users
- Test audio on multiple devices
- Evaluate integration with visual elements
Future Scalability
As your real estate startup scales, the API easily handles increasing inventory volumes. You can process thousands of property descriptions daily by splitting long texts into 4,096-character segments and joining the resulting audio files. This ensures consistent playback quality whether you have ten listings or ten thousand.
Growing Inventory
The system is designed for high throughput. As you add more properties, you can manage volume by batching requests or using multiple API keys to bypass the 60 requests per minute limit per key. This allows you to generate tours for large portfolios without significant latency.
- Handle unlimited property listings
- Batch processing for efficiency
- No hard cap on inventory
New Markets
Expanding into new regions is straightforward. With support for 23 languages, you can instantly localize your audio tours for global buyers. The API automatically detects language from script or allows explicit ISO code setting, ensuring accurate pronunciation for diverse markets without additional engineering.
- Support for 23 languages
- Automatic language detection
- Instant global localization
Tech Stack Updates
Your integration remains future-proof. Since the API follows the standard OpenAI request shape, you can use existing SDKs or simple HTTP calls. This flexibility means you can easily update your virtual tour platform or switch technologies without rewriting your audio generation logic.
- Standard API compatibility
- Flexible SDK usage
- Easy tech stack migration
Support & Resources
PlayBossPay provides straightforward support via email for any integration questions or billing inquiries. We do not offer live chat or phone support, so please allow time for a detailed written response.
Email Support
Send your technical details or account questions to our support team. We handle all communications asynchronously to ensure accuracy.
- Email only
- No phone number
- No live chat
Documentation
Visit /docs/ for complete API reference, including the /v1/audio/speech endpoint and voice list. Use the provided curl examples to test quickly.
- API reference
- Curl examples
- Voice list
Community
Check /about/ for brand details. While we do not host a dedicated forum, you can reference our public facts for accurate comparisons.
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.
23 languages
Any voice speaks any of these languages.
