Text-to-Speech API for Real Estate Virtual Tours

By Vbee AI Voice editorial team · Updated 2026-11-18

Vbee AI Voice delivers a straightforward text-to-speech API designed for freelancers who need professional voiceovers for property listings and virtual tours. You send a script, and we return natural-sounding audio files quickly, allowing you to focus on the visuals rather than recording equipment or studio time.

This page outlines how to integrate our API into your workflow using standard JSON requests. You will find details on supported voices, pricing based on character usage, and technical specifications for developers. Whether you are creating detailed property descriptions or energetic promotional tours, Vbee provides the reliable audio generation you need.

Text-to-Speech API for Real Estate Virtual Tours

Frequently asked questions

What is Vbee text to speech?

Vbee is a cloud text-to-speech API that converts your property scripts into audio files. You send text via a POST request to our endpoint and receive an audio file in formats like mp3 or wav. It uses the same request shape as OpenAI, allowing you to use official OpenAI SDKs by simply changing the base URL to our API domain.

How does Vbee differ from other TTS APIs?

Vbee offers a straightforward API without complex integrations. It supports eight distinct voice presets, including warm narrators and energetic promo voices, all based on licensed recordings. We do not offer voice cloning or custom lexicons, focusing instead on reliable synthetic speech with inaudible watermarks for clear identification of generated audio.

Can I use Vbee for real estate virtual tours?

Yes, Vbee is tailored for freelancers creating voiceovers for property listings and virtual tours. You can generate natural-sounding audio quickly from your scripts, allowing you to focus on the visuals. The API supports multiple languages and provides various voice presets suitable for descriptive property tours and informational content.

How many characters can I send per request?

You can send up to 4096 characters per request. For longer scripts, split the text into parts of this size and join the resulting audio files. Spaces and punctuation count toward the character limit, which is used for billing at $0.01 per 1,000 characters.

What voices are available for property descriptions?

We offer eight presets: Aria (warm narrator), Nova (bright), Luna (soft storyteller), Sage (calm instructor), Felix (energetic promo), Milo (friendly), Atlas (neutral news), and Orion (deep documentary). Any voice can speak any supported language, allowing you to choose the tone that best fits your property listing style.

Does Vbee support multiple languages?

Yes, Vbee supports 23 languages including English, Spanish, French, German, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses it from the script, but setting it explicitly ensures accuracy for non-English Latin-script text.

How fast is the audio generation?

Generation is roughly real-time, processing about 25 characters of text per second of audio. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. This speed is efficient for generating voiceovers for multiple property listings.

Is there a limit on how many requests I can make?

You are limited to 60 requests per minute per key. Before your first top-up, this limit is 10 requests per minute. This rate limit ensures stable performance for your virtual tour projects. Failed requests are free: if synthesis fails, the charge is returned in full.

What payment methods are accepted?

We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits are added automatically within minutes. We do not accept credit cards, PayPal, or subscriptions. Your balance does not expire, and there are no monthly plans or minimum spend requirements.

Is my input text used for training?

No, your input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We keep request metadata like time and character count for billing purposes, ensuring your property scripts remain private and secure.

Do I need an SDK to use Vbee?

No, you do not need a specific SDK. You can use plain HTTP requests or the official OpenAI SDKs. To use OpenAI SDKs, change the base URL to https://api.playjay9.com/v1 and use your API key. This flexibility allows you to integrate Vbee into your existing freelancer workflows easily.

Can I clone a specific voice for my brand?

No, Vbee does not offer custom voice cloning. You cannot upload your own voice or design a custom voice. We provide eight preset voices based on licensed recordings. You can choose the preset that best matches your brand's tone and style.

Is there an SLA or uptime guarantee?

No, we do not provide an SLA or uptime guarantee. There is no enterprise contract, on-premise install, or data-center choice. We also do not hold certifications like SOC 2 or HIPAA. Our service is designed for freelancers who need reliable, straightforward API access without complex enterprise support structures.

How do I contact support?

Support is available by email only. There is no phone number, live chat, or dedicated account manager. You can reach us via the contact page on our site. We aim to provide helpful, direct assistance for any issues you encounter with your API key, billing, or integration.

First request

curl

curl https://api.playjay9.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

Turn property scripts into professional voiceovers

Sound wave illustration for: Turn property scripts into professional voiceovers

Transform written scripts into clear audio for your real estate projects. The API accepts up to 4,096 characters per request, processing text sequentially to generate natural-sounding voiceovers efficiently.

This workflow lets you focus on visuals while automated synthesis handles the narration, delivering reliable results for property listings and virtual tours.

Describe property details

Describe property details

Input specific features like square footage or room layouts. The API converts these details into clear, professional audio suitable for listing videos.

Use voices like Aria or Sage for warm, clear narration that highlights key selling points without distracting from the visual tour.

  • Ideal for detailed property descriptions
  • Clear, narrator-style output
  • Supports up to 4,096 characters per request

Guide viewers through virtual tours

Create step-by-step audio guides that lead viewers through a virtual property. The system handles sequential requests to join audio parts seamlessly for longer tours.

Maintain a consistent tone throughout the tour using preset voices like Milo or Atlas, ensuring a cohesive listening experience.

  • Sequential audio generation
  • Consistent voice tone
  • Supports 23 languages

Create engaging listing videos

Add voiceovers to your listing videos quickly. Short phrases generate in seconds, while longer scripts are processed in real-time queues.

Use upbeat voices like Nova or Felix for promotional content, or calm tones for instructional guides, tailored to your specific listing needs.

  • Fast generation for short scripts
  • Real-time processing for long texts
  • No manual editing required

How the Vbee TTS API works

Sound wave illustration for: How the Vbee TTS API works

Vbee AI Voice converts your property scripts into audio through a simple API endpoint. Send a JSON payload via POST to /v1/audio/speech, including the text, voice selection, and desired output format.

Send text via POST request

Construct your request body with the input field containing your script (up to 4096 characters) and specify a voice like nova for bright tours or sage for calm guides. Include your Authorization: Bearer header with your API key.

  • Endpoint: POST https://api.playjay9.com/v1/audio/speech
  • Supports tts-1 and tts-1-hd models
  • Max 4096 characters per request

Receive audio in MP3, WAV, or OPUS

The API returns the synthesized audio file directly in the response body. You can choose from MP3, WAV, OPUS, FLAC, or PCM formats to match your video editing workflow. Failed requests incur no charge.

  • Formats: MP3, WAV, OPUS, FLAC, PCM
  • Audio returned in response body
  • No charge on synthesis failure

Support for 23 languages

Generate voiceovers in 23 languages, including English, Spanish, French, and German. If the language field is omitted, the system guesses the language from the script, defaulting to English for Latin text.

  • 23 supported languages
  • Automatic language detection
  • Explicit language code recommended

Voice options for real estate content

Sound wave illustration for: Voice options for real estate content

Selecting the right voice ensures your property descriptions sound professional and engaging. Our eight presets cover the full range of real estate content needs, from detailed room features to energetic promotional highlights.

Warm narrator for detailed descriptions

Aria offers a warm, clear tone ideal for detailing property features. Her calm delivery helps viewers absorb specific details about layouts and finishes without distraction.

  • Aria: Warm, clear narrator
  • Ideal for long property descriptions

Bright and upbeat for promotions

Nova brings bright energy to promotional content. Her upbeat style works well for highlighting key selling points or creating engaging listing videos.

  • Nova: Bright, upbeat voice
  • Best for promotional highlights

Calm and instructional for guides

Sage provides a calm, instructional tone perfect for virtual tour guides. Her steady pace helps viewers follow along smoothly as they explore the property.

  • Sage: Calm, instructional voice
  • Optimized for tour guidance

Pricing for high-volume freelancers

Sound wave illustration for: Pricing for high-volume freelancers

Vbee TTS API charges $0.01 per 1,000 characters, making it cost-effective for high-volume freelancers producing property listings and virtual tour scripts. Failed requests are free, so you only pay for successful audio generation.

With no monthly subscriptions or minimum spend, you pay only for what you use. The balance never expires, allowing you to top up as needed without worrying about losing unused credits.

$0.01 per 1,000 characters

Each request processes up to 4,096 characters. Pricing is straightforward: $10 per million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the character limit.

No monthly subscriptions

There are no seats, no annual plans, and no recurring bills. You maintain one active API key per account and can issue a new one at any time, with the old key stopping immediately.

Pay with USDT (TRC-20)

Top-ups are processed via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes of transfer. No cards, PayPal, or VAT invoices are supported.

  • Minimum top-up: $5
  • Network: TRON (TRC-20)
  • Credited within minutes

Technical integration for developers

Sound wave illustration for: Technical integration for developers

Integrate the Vbee TTS API using the official OpenAI SDKs by simply changing the base_url to https://api.playjay9.com/v1. This allows you to use familiar libraries while leveraging our specific endpoints for speech synthesis.

The API accepts standard JSON request bodies, making it easy to incorporate into existing automation pipelines using the OpenAI SDK or plain HTTP. You can control voice selection, audio format, and speech speed directly through the input, voice, and speed parameters.

OpenAI SDK compatible

Use the official OpenAI SDKs by setting the base_url to https://api.playjay9.com/v1. This ensures compatibility with your existing code structure without requiring a complete rewrite.

The same request shape used for the OpenAI speech endpoint works here, allowing you to swap in our service with minimal configuration changes.

  • Compatible with existing OpenAI SDK implementations
  • Simple base_url configuration change

Standard JSON request body

Send a POST request to /v1/audio/speech with a JSON body containing the text, voice, and format. The API returns the audio file directly in the response.

You can specify response_format (mp3, wav, opus, flac, pcm) and speed (0.25–4.0) to tailor the output for your virtual tour needs.

  • POST /v1/audio/speech endpoint
  • Supports mp3, wav, opus, flac, pcm formats
  • Adjustable speed from 0.25 to 4.0

Rate limits of 60 requests/minute

Each API key is limited to 60 requests per minute, which is sufficient for most freelance workflows. Before the first top-up, the limit is 10 requests per minute.

Requests are processed sequentially, so under high load, a request may wait in a queue. Plan your batch generations accordingly to avoid delays.

  • 60 requests per minute per key
  • 10 requests per minute before first top-up
  • Sequential processing may cause queuing under load
Technical integration for developers

Quality and authenticity

Sound wave illustration for: Quality and authenticity

Vbee AI Voice ensures high-quality audio by sourcing its voice models from licensed recordings. We use the LibriTTS-R dataset under CC BY 4.0 and public-domain audiobook readings from LibriVox, providing a reliable foundation for your real estate content.

Licensed from LibriTTS-R and LibriVox

Our eight voice presets are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures your voiceovers are built on legitimate, high-quality source material without the risk of copyright infringement.

Inaudible watermark on audio

Every generated audio file includes an inaudible watermark that clearly marks the content as synthetic speech. This helps maintain transparency with your viewers and distinguishes AI-generated narration from human-recorded tracks in your virtual tours.

No training on your input text

Your input text is used solely to produce the audio file and is not used for training purposes. We do not store or reuse your specific property descriptions to improve our models, ensuring your unique listing data remains private.

Supported formats and languages

Sound wave illustration for: Supported formats and languages

The API returns audio in five standard formats: MP3, WAV, FLAC, PCM, and OPUS. Choose MP3 or OPUS for efficient web streaming in virtual tours, or WAV/FLAC for high-fidelity archival. PCM provides raw data for custom pipelines.

All 23 supported languages are available with every voice preset. If the language isn't specified, the system guesses it from the script, defaulting to English for Latin text. For non-English Latin scripts, explicitly set the language code to ensure accuracy.

MP3, WAV, FLAC, PCM, OPUS

Select the output format that best fits your deployment. MP3 and OPUS offer small file sizes ideal for quick loading in browser-based property tours. WAV and FLAC provide lossless quality for professional recordings. PCM is available for raw audio processing.

  • MP3: Compressed, widely compatible
  • WAV: Lossless, high quality
  • FLAC: Lossless, compressed
  • PCM: Raw audio data
  • OPUS: Efficient streaming

English, Spanish, French, German

Support includes English, Spanish, French, and German, alongside 19 other languages like Italian, Portuguese, and Dutch. Each voice can speak any supported language, allowing you to maintain a consistent brand tone across different markets without hiring multiple voice actors.

Arabic, Chinese, Japanese, Korean

We also support Arabic, Chinese, Japanese, and Korean, as well as Scandinavian and Slavic languages. If the language field is omitted, the system infers the language from the script. For Latin-script texts in other languages, explicitly set the language parameter to avoid defaulting to English.

Why choose Vbee for virtual tours

Sound wave illustration for: Why choose Vbee for virtual tours

Vbee TTS API is built for the specific workflow of real estate freelancers. Instead of juggling multiple tools or waiting for custom voice actors, you generate professional voiceovers directly from your listing scripts. This allows you to focus on editing the visuals while the API handles the audio synthesis quickly and reliably.

Fast generation for short scripts

Real estate scripts are typically concise, often under 200 words. Short phrases take a few seconds to generate, allowing you to iterate quickly. Even with longer tour scripts, generation takes roughly real-time speed, so a 60-second voiceover takes about 60 seconds to produce. You can generate multiple variations of a property description without significant delay.

Reliable queue processing

Requests are processed sequentially, so under load a request may wait in a queue. If you are generating many listings at once, requests may wait briefly in a queue rather than failing. This system prevents bottlenecks and ensures that every property script gets converted to audio, even during peak usage times. You do not need to manage complex server infrastructure.

Simple billing without invoices

Pay only for what you use with no monthly subscriptions or minimum spends. Billing is straightforward: $0.01 per 1,000 characters. Payments are made via USDT (TRC-20), eliminating the need for invoices, VAT handling, or credit card processing. Your balance never expires, so you can top up when convenient and use funds across multiple projects.

Get started with a free trial

Sound wave illustration for: Get started with a free trial

Start testing Vbee AI Voice immediately with a $0.50 credit valid for seven days after signing in with Google. This allowance covers approximately 50,000 characters, enough to generate several property listing scripts and virtual tour voiceovers without any upfront payment or credit card.

The setup takes less than a minute. Once authenticated, you receive your API key instantly and can begin sending requests to the speech endpoint right away.

$0.50 credit for 7 days

Your free trial provides $0.50 of usable credit, equating to roughly 50,000 characters. This is sufficient to test multiple voices and formats for your real estate projects.

The trial period lasts seven days from signing in with Google. Unused balance does not roll over, but it gives you ample room to verify quality before purchasing more.

  • Valid for 7 days
  • Approx. 50,000 characters
  • No credit card required

Sign up with Google

Click the 'Sign in with Google' button on the /get-api-key/ page. This method automatically qualifies you for the trial credit, which email-only accounts do not receive.

The process is secure and requires only your existing Google credentials. No additional verification steps delay your access to the API.

Instant API key issuance

Upon successful authentication, your unique API key is displayed immediately. You can copy it directly into your scripts or the OpenAI SDK configuration.

The key is active for 60 requests per minute. You can issue a new key at any time if needed, with the old one stopping instantly.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Freelancers can now showcase properties seamlessly with immersive virtual tours that captivate potential buyers instantly.

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. LibriTTS-R paper (arXiv 2305.18802)
  3. Node.js documentation
  4. Tether (USDT)
  5. MDN: Web Speech API
  6. IETF RFC 7845: Ogg Opus
  7. TRON developer hub: TRC-20
  8. OpenAI API reference: create speech
  9. LibriVox public-domain audiobooks
  10. FFmpeg documentation
  11. Creative Commons Attribution 4.0
  12. W3C WAI: making audio and video accessible

More on this site