API Documentation for Real Estate Audio Generation

By VoxProp editorial team · Updated 2026-11-19

This documentation provides the technical reference for VoxProp’s text-to-speech API, designed specifically for real estate agencies generating voiceovers for virtual tours and property listings. You will find precise endpoint definitions, parameter details, and code examples to integrate audio generation directly into your workflow.

The guide covers authentication, request formatting, and response handling for all eight voice presets. It also explains rate limits, long-text chunking, and supported languages, enabling you to convert listing descriptions into clear, professional audio files efficiently without hiring external voice actors.

API Documentation for Real Estate Audio Generation

Frequently asked questions

How do I get my API key?

Sign up on the /get-api-key/ page using Google or an email and password. Your account is specific to this site. The dashboard displays your active API key, balance, and usage statistics. You can issue a new key at any time, which immediately invalidates the previous one.

Can I use the OpenAI Python SDK?

Yes. The API endpoint matches the OpenAI speech endpoint structure. You can use the official OpenAI SDKs by changing the base_url to https://api.x06.info/v1 and providing your VoxProp key. This allows you to use familiar libraries without writing custom HTTP client code.

What is the character limit per request?

Each request supports up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer texts, split the content into chunks of 4096 characters or less, generate audio for each part, and join the resulting audio files.

How do I specify the language?

Include the optional language field in your request with an ISO code. If omitted, the system guesses the language from the script, defaulting to English for Latin text. Explicitly setting the language ensures accurate synthesis for non-English Latin-script texts.

Does the API support SSML?

No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You provide plain text input. The system handles basic pronunciation automatically based on the specified voice and language, but offers no granular control over pauses or emphasis.

What happens if I exceed the rate limit?

The limit is 60 requests per minute per key. If you exceed this, requests may queue or fail. New accounts start with a 10 requests per minute limit until the first top-up. Failed requests do not consume your balance or credits.

Can I change the voice speed dynamically?

Yes. Include the speed field in your request JSON. Valid values range from 0.25 to 4.0. This allows you to adjust the playback speed of the generated audio dynamically for each specific synthesis request without needing post-processing.

Is the audio streamed or downloaded?

The API does not support streaming or WebSocket connections. It returns the complete audio file in the response body. You must wait for the full synthesis to complete before receiving the data. The file is returned in the requested format, such as MP3 or WAV.

How do I handle errors in the response?

The API returns standard HTTP status codes and error details in the JSON body. If synthesis fails, the charge is returned in full. Check the response status code to determine if the request succeeded or if an error occurred during processing.

Are the models tts-1 and tts-1-hd different?

No. Both models use the same engine and have the same price. The distinction is primarily for compatibility with OpenAI SDKs. You can use either model identifier in your requests without affecting the output quality or cost per character.

Can I use the API with AWS Lambda?

Yes. Since the API accepts standard HTTP POST requests with JSON bodies, you can integrate it with AWS Lambda. Use any HTTP client library available in your Lambda runtime to send text and receive the audio file response.

How do I revoke my API key?

You can issue a new API key at any time from your account dashboard. When you generate a new key, the previous one becomes invalid immediately. This effectively revokes access for any service using the old key without needing a separate revoke action.

What is the maximum speed setting?

The maximum speed setting is 4.0. The minimum is 0.25. You can adjust the speed for each request independently. This allows you to create faster or slower voiceovers depending on the pacing required for your real estate property videos.

Does the API support background generation?

No. The API is synchronous; it waits for synthesis to complete before returning the audio file. Requests are processed sequentially, so under load, a request may wait in a queue. You must handle the wait time in your application logic.

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.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.x06.info/v1", api_key="tts-...")

with client.audio.speech.with_streaming_response.create(
    model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
    response.stream_to_file("hello.mp3")

Node.js (openai)

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({ baseURL: "https://api.x06.info/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));
voice
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Authentication

Sound wave illustration for: Authentication

Secure access to the VoxProp API requires a valid Bearer token passed in the Authorization header of every request. Your unique API key is displayed on your dashboard at /get-api-key/ alongside your current balance and usage statistics. This key authenticates your identity and tracks character consumption against your account limits.

Use Bearer token in Authorization header

Use Bearer token in Authorization header

Include the header Authorization: Bearer tts-... in your HTTP requests. This simple standard ensures that only authorized accounts can generate audio files. The token validates against your active key without requiring additional session management.

One active key per account

One active key per account

Each account maintains a single active API key at any time. This design simplifies security management for real estate agencies, ensuring that only one credential is valid for all integrations, from virtual tour software to internal video production tools.

Revoke old key by issuing a new one

To revoke the current key, simply generate a new one from your dashboard. The previous key becomes invalid immediately, cutting off access instantly. This allows you to secure your account without waiting for a timeout period or manual deactivation.

Endpoints

Sound wave illustration for: Endpoints

The API exposes three primary endpoints for integration. The speech endpoint generates audio from text, while the voices and models endpoints provide metadata about available presets and engine configurations.

All endpoints require a Bearer token in the Authorization header for authentication. Use the GET endpoints to verify available resources before sending generation requests.

POST /v1/audio/speech for generation

Send text and voice parameters to receive an audio file. This is the core endpoint for converting listing descriptions into voiceovers.

The request body accepts JSON with model, input, voice, and format fields. Responses return the audio file directly or an error object.

  • Endpoint: POST https://api.x06.info/v1/audio/speech
  • Body: JSON object with text and voice selection

GET /v1/voices for available presets

Retrieve the list of eight voice presets (e.g., aria, nova, felix) and their supported languages. This helps you select the right tone for property tours.

Each voice is described by its character type, such as warm narrator or energetic promo.

  • Endpoint: GET https://api.x06.info/v1/voices
  • Returns: Voice ID, name, gender, and supported languages

GET /v1/models for engine details

Check the available models (tts-1 and tts-1-hd) and their specifications. Both models use the same engine and price.

This endpoint confirms the current engine status and supported output formats.

  • Endpoint: GET https://api.x06.info/v1/models
  • Returns: Model ID, name, and supported formats

Request parameters

Sound wave illustration for: Request parameters

The request body defines how your property description is converted into audio. You specify the model, the text itself, and which voice preset best suits the property’s tone. All parameters are sent as a single JSON object to the speech endpoint.

Accurate parameter usage ensures consistent audio quality and avoids unnecessary charges. The API validates inputs before synthesis, returning errors immediately if limits are exceeded or formats are invalid.

model: tts-1 or tts-1-hd

Select "tts-1" for standard generation or "tts-1-hd" for higher fidelity. Both models use the same engine and pricing ($10 per 1 million characters), so choose based on your audio quality needs for virtual tours.

None

  • tts-1: Standard quality, sufficient for most listing descriptions.
  • tts-1-hd: Enhanced clarity, ideal for detailed property features.

input: text up to 4096 characters

The input field accepts your property description as plain text. Spaces and punctuation count toward the 4096 character limit. For longer listings, split the text into chunks and join the resulting audio files afterward.

None

  • Maximum 4096 characters per request.
  • Spaces and punctuation count as characters.
  • Failed requests do not consume credit.

voice: one of 8 preset names

Choose a voice preset that matches the property’s vibe. Female voices like Aria or Nova suit modern, bright listings, while male voices like Atlas or Orion work well for professional, neutral descriptions. All voices support all 23 languages.

None

  • aria: Warm, clear narrator.
  • nova: Bright, upbeat.
  • luna: Soft, storytelling.
  • sage: Calm, instructional.
  • felix: Energetic, promo.
  • milo: Friendly, conversational.
  • atlas: Neutral, news.
  • orion: Deep, documentary.

Response formats

Sound wave illustration for: Response formats

Choose the output format that best suits your virtual tour player or listing platform. MP3 offers standard compression for efficient bandwidth usage, while WAV provides lossless quality for professional archival needs.

mp3: Standard compressed audio

MP3 is the default choice for most web-based property tours. It balances file size and quality, ensuring quick loading times for potential buyers viewing listings on mobile devices or slower connections.

wav: Lossless audio file

Select WAV when you need uncompressed, high-fidelity audio for professional presentations or offline playback. This format preserves every detail of the synthesized voice without data loss.

opus, flac, pcm: Other supported formats

Use OPUS for high-efficiency audio, FLAC for lossless compression, or PCM for raw, uncompressed data. These options allow flexibility depending on your specific infrastructure or player requirements.

Speed and language

Sound wave illustration for: Speed and language

Adjusting speech speed allows you to tailor the pacing of property descriptions to match the visual flow of virtual tours. You can slow down the narration for detailed feature lists or speed it up for quick overviews, ensuring the audio feels natural and professional without sounding rushed.

The API accepts a speed multiplier between 0.25 and 4.0. This gives you precise control over how quickly the voice actor reads the listing details, helping you synchronize audio with video cuts or highlight specific property features effectively.

Speed: 0.25 to 4.0 multiplier

Set the speed parameter to adjust the voice pace. Values range from 0.25 (slow) to 4.0 (fast). This is useful for matching narration length to video duration or emphasizing key selling points in property listings.

  • Use lower values (0.25–0.75) for detailed feature breakdowns.
  • Use higher values (1.5–4.0) for quick property summaries.
  • Default speed is 1.0 for natural pacing.

Language: Optional ISO code

Provide an ISO 639-1 language code (e.g., en, de, es) to ensure accurate pronunciation. While the system attempts auto-detection, explicitly setting the language guarantees correct output for multilingual listings or non-English markets.

  • Supported languages include English, German, Spanish, French, and others.
  • Explicitly setting language prevents mispronunciation errors.
  • See /v1/voices for the full list of 23 supported languages.

Auto-detection for Latin script defaults to English

If you omit the language parameter, the system guesses the language based on the text script. For Latin-script text, it defaults to English. For other scripts, it attempts detection, but explicit codes are recommended for consistency.

  • Latin script defaults to English if not specified.
  • Non-Latin scripts trigger automatic detection.
  • Explicitly set language for reliable results in mixed-language listings.
Speed and language

Rate limits and errors

Sound wave illustration for: Rate limits and errors

VoxProp API enforces a rate limit of 60 requests per minute per active key once your account has been topped up. Before your first top-up, the limit is stricter at 10 requests per minute. This ensures stable performance for your real estate audio generation workflows.

60 requests per minute after top-up

Each API key allows a maximum of 60 requests per minute. This limit applies uniformly to all endpoints. If you exceed this threshold, you will receive a 429 Too Many Requests error until the window resets.

Queue processing under load

Requests are processed sequentially. During periods of high traffic, your request may wait in a queue before synthesis begins. This can increase latency, especially for longer texts or HD model requests. Be prepared for slight delays during peak usage times.

Errors return standard HTTP status codes

Standard HTTP status codes indicate success or failure. Common errors include 401 for invalid authentication, 400 for malformed requests (e.g., text exceeding 4096 characters), and 429 for rate limit exceeded. Failed synthesis requests are free, and any charges are returned in full.

Check the response body for detailed error messages to troubleshoot issues quickly. Ensure your text input respects character limits and that your API key is correctly formatted in the Authorization header.

  • 401: Unauthorized – Invalid or missing API key
  • 400: Bad Request – Invalid parameters or text length exceeded
  • 429: Too Many Requests – Rate limit exceeded

Code examples

Sound wave illustration for: Code examples

These examples demonstrate how to integrate VoxProp into your real estate workflow. Use the cURL command for immediate testing, the OpenAI SDK for seamless library integration, or Python for batch processing multiple property listings.

All examples use the standard API key format. Replace YOUR_API_KEY with your key from the dashboard. The base URL points to https://api.x06.info/v1.

cURL command for quick test

Send a simple request to verify your key and receive an audio file immediately.

This command generates a 5-second clip using the nova voice in English.

  • `curl -X POST https://api.x06.info/v1/audio/speech -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"model":"tts-1","input":"Welcome to this beautiful home.","voice":"nova","response_format":"mp3"}' -o speech.mp3`

OpenAI SDK with base_url change

Leverage the official OpenAI SDK by adjusting the base URL. This allows you to use familiar methods like audio.speech.create.

Configure the client to point to https://api.x06.info/v1 and pass your VoxProp API key.

  • import openai client = openai.OpenAI(api_key="YOUR_API_KEY", base_url="https://api.x06.info/v1")
  • `response = client.audio.speech.create(model="tts-1-hd", voice="atlas", input="Property located in downtown.", response_format="wav")`

Python snippet for batch processing

Process multiple property descriptions by splitting text into 4096-character chunks. Generate audio for each segment.

Combine the resulting files client-side to create a complete virtual tour narration. This ensures reliable handling of long listing details.

  • # Split text into chunks of 4096 characters
  • # Loop through chunks and call API
  • # Join output audio files using a library like pydub

Long text handling

Sound wave illustration for: Long text handling

For property descriptions exceeding 4096 characters, the API requires splitting the input text into smaller segments. Each segment must be processed individually to ensure consistent audio quality and to stay within the single-request character limit.

Split text into 4096 character chunks

Divide your listing description into parts of up to 4096 characters. Spaces and punctuation count toward this limit. Process these segments sequentially or in parallel, depending on your queue capacity and rate limits. Requests are processed one after another, so under load a request may wait in a queue.

  • Count characters including spaces and punctuation
  • Ensure each chunk is under 4096 characters
  • Handle partial sentences gracefully at boundaries

Generate audio for each chunk

Send each text chunk to the POST /v1/audio/speech endpoint. The API returns an audio file for each request. Typical generation speed is roughly real-time, so longer scripts will take proportional time. Requests are processed one after another, so under load, a request may wait in a queue.

  • Send each chunk independently
  • Receive individual audio files
  • Account for queue processing time

Join audio files client-side or via script

Once all audio files are generated, combine them into a single file. You can use client-side JavaScript or a backend script to merge the audio segments. This ensures a seamless voiceover for your virtual tour without noticeable gaps between chunks.

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.

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. Python documentation
  4. LibriVox public-domain audiobooks
  5. Creative Commons Attribution 4.0
  6. Tether (USDT)
  7. Node.js documentation
  8. LibriTTS-R corpus (OpenSLR 141)
  9. OpenAI API reference: create speech
  10. openai-node on GitHub
  11. MDN: Web Speech API
  12. IETF RFC 7845: Ogg Opus

More on this site