Frequently asked questions
Is the realistic voice generator truly free?
A free trial provides $0.50 credit, valid for seven days when you sign in with Google. This covers approximately 50,000 characters. Accounts created with email and password start without trial credit. After the trial, usage is billed at $0.01 per 1,000 characters. Failed requests are free, ensuring you only pay for successful audio generation.
Can I use the generated audio for commercial property listings?
Yes, the generated audio files are returned in the response and not stored by the API. You can use them for commercial property listings, virtual tours, and marketing materials. The input text is used only to produce the audio and is not used for training models. There are no restrictions on how you use the final audio files.
How many characters can I process in one request?
Each API request accepts up to 4,096 characters of text. If your property description exceeds this limit, you must split the text into parts of up to 4,096 characters each. You then generate audio for each part and join the resulting audio files to create the complete voiceover for your real estate listing.
Which voices sound best for luxury real estate?
For luxury properties, Atlas (neutral, news) or Orion (deep, documentary) provide a professional, high-end tone. Sage (calm, instructional) is also suitable for detailed property features. Aria (warm, clear narrator) works well for inviting tours. The choice depends on whether you want a neutral presentation or a warmer, storytelling approach for your virtual tour.
Do I need technical skills to use the API?
Basic technical skills are helpful but not strictly required. The API uses a standard JSON body, similar to the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base URL. A ready curl example is provided on the /get-api-key/ page.
What happens if the synthesis 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. The API processes requests sequentially, so under load, a request may wait in a queue, but it will eventually be processed or failed without cost to you.
Are the voices based on real people?
Yes, the eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech, distinguishing it from direct recordings while maintaining high quality and natural intonation for your property videos.
Can I generate audio in multiple languages?
Yes, the API supports 23 languages, including English, Spanish, German, French, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. If the language is not set, it is guessed from the script. For non-English Latin-script text, you should explicitly set the language parameter to ensure accurate pronunciation for your international listings.
How long does it take to generate a minute of audio?
Generation is roughly real time on long texts, processing about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue. For a one-minute video, expect near-real-time generation unless the system is heavily loaded.
Is there a limit on the number of API requests?
The rate limit is 60 requests per minute per API key. Before the first top-up, the limit is 10 requests per minute. This allows for efficient batch processing of property descriptions. If you need higher throughput, ensure your requests are spaced appropriately.
Can I change my API key if it gets compromised?
Yes, you can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This ensures that if your key is compromised, you can quickly revoke access without waiting for a manual review or support intervention, securing your account and billing information.
Does the API support SSML for better control?
No, the API does not support SSML (Speech Synthesis Markup Language). You cannot use SSML tags for pauses, emphasis, or pronunciation changes. Control is limited to the voice preset, speed (0.25–4.0), and language parameters. For precise timing, you may need to split your text into smaller segments and adjust the speed manually.
What payment methods are accepted?
The only accepted payment method is USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are added automatically within minutes after the transfer. There are no credit cards, PayPal, subscriptions, or invoices with VAT. Balance does not expire, and there are no monthly plans or minimum spend requirements.
How is the synthetic speech identified?
Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded in the audio data and is not audible to the human ear. It serves to identify the content as AI-generated, which can be useful for transparency in your real estate marketing materials or virtual tours.
First request
curl
curl https://api.x06.info/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.mp3Why agencies use TTS for real estate
Real estate agencies generate hundreds of property videos annually. Hiring voice actors for each listing creates significant cost and logistical friction. A text-to-speech API transforms written descriptions into professional audio instantly, removing the need to coordinate schedules, studios, and individual per-minute rates for every new video.
Cost-effective narration for hundreds of listings
Generating audio via API costs $0.01 per 1,000 characters. This flat rate scales efficiently with volume.
Consistent brand voice across all video tours
Using a single voice preset ensures your agency’s brand sounds identical across every listing, from luxury condos to family homes. Unlike varying human actors, the synthetic voice delivers uniform tone and pacing, reinforcing professional recognition.
Instant updates when property details change
Property listings frequently update with new prices, square footage, or features. With TTS, you regenerate the audio file in seconds by submitting the revised text. There is no need to re-book studio time or wait for an actor’s availability.
How the realistic voice generator works
Send your property description to the API endpoint. Each request accepts plain text up to 4,096 characters. The system processes inputs sequentially, so longer listings may require splitting into parts before joining the final audio files.
Choose from eight distinct voice presets. Each preset offers a specific tone suitable for real estate contexts, from neutral news styles to upbeat promotional highlights. You can also specify the language to ensure accurate pronunciation for international audiences.
Input your property description text
Paste or send your listing description via a JSON body. The API accepts up to 4,096 characters per request. For longer texts, split the content into parts and combine the resulting audio files afterward.
- Max 4,096 characters per request
- Split and join for longer listings
- Spaces and punctuation count as characters
Select a voice style from our 8 presets
Choose one of eight distinct voice presets. Each voice provides a consistent tone, whether you need a calm instructional style for guided tours or a bright upbeat tone for highlights. All voices can speak any of the 23 supported languages.
- 8 distinct voice presets
- Adjustable speed from 0.25x to 4.0x
- All voices support all 23 languages
Download MP3, WAV, or other audio formats
Receive the generated audio file directly in your response. You can select from multiple formats including MP3, WAV, Opus, FLAC, and PCM. The audio is returned immediately after synthesis completes.
- MP3, WAV, Opus, FLAC, PCM
- No streaming or WebSocket required
- Inaudible synthetic watermark included
Voices optimized for property descriptions
Select from eight voice presets. Each voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring clear narration for your property videos. You can choose from male and female presets, such as Atlas, Sage, and Nova, to fit the tone of your listing.
Atlas: Neutral and professional for news-style updates
Atlas offers a neutral, clear tone ideal for straightforward property listings or news-style updates. Its steady delivery ensures that key details about the property are communicated without distraction, making it perfect for factual descriptions.
- Neutral and professional tone
- Ideal for factual listings
- Clear and steady delivery
Sage: Calm and instructional for guided tours
Sage provides a calm and instructional voice, perfect for guiding viewers through a virtual tour. Its soothing tone helps maintain engagement while highlighting features, making it suitable for detailed walkthroughs.
- Calm and instructional
- Ideal for guided tours
- Soothing tone for engagement
Nova: Bright and upbeat for promotional highlights
Nova brings a bright and upbeat energy, ideal for promotional videos or social media clips. Its lively tone adds excitement to property highlights, making your listings stand out in a crowded market.
- Bright and upbeat energy
- Ideal for promotions
- Adds excitement to listings
Languages for international markets
VoxProp supports 23 languages, enabling agencies to reach global buyers without hiring local voice talent. Every voice can speak any supported language, ensuring consistent quality across diverse markets.
Specify the ISO language code in your API request to ensure correct pronunciation. If omitted, the system guesses from the script, defaulting to English for Latin text.
English, Spanish, and French for major markets
These languages are supported. Use English for domestic listings, Spanish for US Hispanic markets, and French for Canadian or European properties.
German, Italian, and Portuguese for European listings
Reach European audiences with clear, natural-sounding narration. The system handles these languages accurately, allowing you to localize property details efficiently for international buyers.
Japanese, Korean, and Chinese for Asian properties
Target the Asian real estate market with voice synthesis in Japanese, Korean, and Chinese.
Free trial and API access
Agencies can start testing the TTS API immediately with a free trial. New accounts signed in via Google receive $0.50 in credit, covering approximately 50,000 characters of narration. This allows you to generate sample audio for your first property listing.
The trial is valid for 7 days. If you create an account using only an email and password, no trial credit is applied. You can generate a new API key at any time, which instantly invalidates the previous one for security.
Start with $0.50 free credit for 50,000 characters
The trial credit lets you test voice quality and integration speed without risk. Since short phrases take a few seconds to generate, you can evaluate multiple voice presets quickly. Failed requests are free, so you can refine your prompts without cost.
Sign up with Google for instant access
Visit the /get-api-key/ page to sign in with your Google account. This method grants immediate access to your dashboard, API key, and trial balance. Accounts created with just an email address do not receive the initial credit.
Use standard OpenAI SDK or simple HTTP requests
The API follows the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base URL to https://api.x06.info/v1. Alternatively, send a simple POST request to /v1/audio/speech with your JSON payload.

Technical integration for agencies
The API uses a standard REST endpoint at https://api.x06.info/v1/audio/speech. Send a POST request with your property text, selected voice, and desired format to receive an audio file. This structure works with existing HTTP libraries and the OpenAI SDK.
You can generate audio in MP3, WAV, Opus, FLAC, or PCM formats. Choose the format that best fits your video editing workflow or web player requirements without additional conversion steps.
REST API endpoint compatible with existing workflows
The endpoint https://api.x06.info/v1/audio/speech accepts JSON bodies. Pass your text, voice preset, and language code. The system returns the audio file directly, integrating seamlessly into your content management or video production pipeline.
You can use the official OpenAI SDK by pointing it to our base URL, or send simple HTTP POST requests. This flexibility allows developers to build custom automation for listing updates without learning a new interface.
- Endpoint: POST https://api.x06.info/v1/audio/speech
- Authentication: Bearer token via Authorization header
- SDK compatibility: Works with OpenAI Python/Node SDKs
Support for MP3, WAV, Opus, FLAC, and PCM formats
Select your preferred output format using the response_format parameter. MP3 is ideal for web players, while WAV and FLAC offer lossless quality for professional editing. PCM provides raw data for specialized audio processing.
- MP3: Standard for web and mobile playback
- WAV/FLAC: High-quality formats for post-production
- Opus/PCM: Efficient or raw data options
Rate limits suitable for batch processing tours
The API allows 60 requests per minute per key. This limit supports batch processing of multiple property listings without significant delays. Short phrases take a few seconds to generate, while longer descriptions process in roughly real time.
image]:
Data privacy and licensing
VoxProp ensures your property data remains private. The input text you submit is used exclusively to generate the audio file and is not used for training our models. This means your listing details stay proprietary, giving you full control over your content without contributing it to public datasets.
Input text used only for generation, not for training
Your property descriptions are processed solely to create the audio output. We do not retain your text for model improvement, ensuring your unique selling points and specific details remain confidential to your agency.
Generated audio includes synthetic watermarking
Every audio file generated by VoxProp carries an inaudible watermark. This digital marker clearly identifies the file as synthetic speech, helping you maintain transparency with your clients and ensuring the audio is recognized as AI-generated content.
Metadata kept for billing, audio not stored long-term
We retain request metadata, including time, character count, and status, strictly for billing accuracy. The generated audio files are returned directly in the API response and are not stored on our servers long-term, minimizing data retention risks.
Pricing for high-volume usage
Pricing for high-volume usage is straightforward and scales with your content needs. You pay a flat rate of $0.01 per 1,000 characters, which includes spaces and punctuation. Failed requests are free, ensuring you only pay for successful audio generation.
Flat rate of $0.01 per 1,000 characters
Each request charges based on the character count of the input text. With a limit of 4,009 characters per request, longer listings are split and processed sequentially. This predictable cost structure allows agencies to budget accurately for hundreds of property videos without surprise fees.
No monthly fees or minimum spend required
There are no subscriptions, seats, or minimum spend requirements. You can use the API for a single video or for thousands of listings. Your balance does not expire, allowing you to top up only when you need more generation capacity for upcoming listing seasons.
Pay with USDT on the TRON network
We accept USDT on the TRON network (TRC-20) for all top-ups. The minimum deposit is $5, and credits are added automatically within minutes of transfer confirmation. This method avoids credit card processing fees and supports direct, efficient payments for agencies operating globally.
Common use cases for agencies
Agencies leverage TTS to produce consistent, professional audio for various real estate media formats without the overhead of hiring voice talent for every single listing.
This approach ensures brand consistency across all content types while allowing instant updates when property details change.
Voiceovers for YouTube property reviews ['Generate clear narration for listing tours directly from your description text. This allows agencies to maintain a steady publishing cadence for YouTube channels without scheduling studio time.', 'The API processes text up to 4096 characters, suitable for standard video length segments.'] ['Sync audio with walkthrough footage', 'Maintain consistent narrator tone across channels', 'Update audio instantly if listing details change']
Audio guides for virtual reality tours ['Create immersive audio guides for VR property tours using voices like Sage for guided instructions or Atlas for neutral updates. This enhances user engagement without requiring human recording for every virtual space.', 'Audio files are downloadable in formats like MP3 or WAV for easy integration into VR platforms.'] ['Guided tour narration', 'Multilingual support for global clients', 'Seamless integration with VR environments']
Automated narration for social media clips ['Automate voiceovers for short-form video content on platforms like Instagram or TikTok. Convert listing highlights into engaging audio clips quickly, enabling higher volume content production.', 'Use the API to generate clips in seconds, keeping up with social media trends without manual recording efforts.'] ['Quick turnaround for trending listings', 'Consistent brand voice on social platforms', 'Easy integration with video editing workflows']
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. He is perfect for reading property specifications, legal descriptions, or factual data where clarity and professionalism are prioritized over emotion.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-python on GitHub
- TRON developer hub: TRC-20
- W3C WAI: making audio and video accessible
- Node.js documentation
- FFmpeg documentation
- IETF RFC 7845: Ogg Opus
- OpenAI API reference: create speech
- Tether (USDT)
- LibriTTS-R paper (arXiv 2305.18802)
- Python documentation
- LibriVox public-domain audiobooks
