Frequently asked questions
What is text-to-speech for kindergarten books?
It is a cloud API that converts your book text into audio files. You send text via a POST request and receive an audio file. You split long texts into parts and join the audio, allowing you to focus on the story.
How do I handle long texts in my API requests?
Split your text into parts of up to 4096 characters per request. The API processes these sequentially. You receive individual audio files for each part, which you then join to create the final audiobook. This ensures stable generation even for lengthy kindergarten books.
Which voices are best for children's stories?
Luna offers a soft, storytelling tone ideal for bedtime tales. Aria provides a warm, clear narrator style, while Nova brings a bright, upbeat energy. Sage is calm and instructional. All eight presets suit children’s content, based on licensed LibriVox recordings. Since any voice can speak any language, choose the tone that best matches your story’s mood rather than a single "best" option.
Does the API support multiple languages?
Yes, it supports 23 languages including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any supported language. If the language is not set, it is guessed from the script, but you should set it explicitly for non-English Latin-script text.
How much does it cost to convert a book?
The price is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free. There are no monthly plans, seats, or minimum spends. You pay only for the characters you successfully generate.
Are failed requests charged?
No. If synthesis fails, the charge is returned in full. You only pay for successful audio generation. This ensures you are not billed for errors or processing failures, making the pricing predictable for your content creation workflow.
Can I use the audio files commercially?
The source recordings are from LibriVox public-domain audiobooks. The generated audio files are returned in the response and not stored by the service. Input text is used only to produce the audio and is not used for training, supporting commercial use of your output.
How long does it take to generate audio?
Typical speed is roughly real time, about 25 characters per second of generation. Short phrases take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue. Longer texts take time proportional to their length.
Do I need to split texts manually?
You must split text into parts of up to 4096 characters for each API request. The API does not automatically split a single large input. You send multiple requests and join the resulting audio files yourself to create the complete audiobook.
What formats are available for download?
You can choose from mp3, wav, opus, flac, and pcm formats. Specify the format in the response_format field of your request. These options allow you to select the best balance of quality and file size for your specific kindergarten book distribution needs.
Is there a free trial available?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can test the API with this initial balance before making a top-up.
How do I pay with cryptocurrency?
Top-up is done via USDT on the TRON network (TRC-20) only. The minimum amount is $5. Credits are added automatically within minutes after the transfer. There are no cards, PayPal, or subscriptions. Your balance does not expire once credited.
What happens if the service is slow?
Requests are processed one after another. Under load, a request may wait in a queue. This can increase generation time beyond the typical real-time speed. There is no SLA or uptime guarantee. You may experience delays during high usage periods.
Can I change my API key later?
Yes, you can issue a new key at any time. The old key stops working immediately when the new one is issued. You have one active key per account. This allows you to rotate keys for security without interrupting your service long-term.
First request
curl
curl https://api.getx99.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.mp3How It Works for Children’s Books
Convert your kindergarten manuscripts into audio files by sending text via a standard POST request. The API accepts input up to 4096 characters per call, handling the synthesis process so you receive a clean audio file ready for distribution.
Send text up to 4096 characters
Submit your story text in JSON format. The system accepts up to 4096 characters per request, allowing you to process chapters or scenes efficiently without complex preprocessing.
Receive MP3 or WAV audio files
Get high-quality audio directly in your response. Choose from MP3 for web streaming or WAV for uncompressed quality, ensuring compatibility with all major audiobook platforms.
Split long texts automatically
For books exceeding single-request limits, split your text into 4096-character parts. The API processes each segment sequentially, so you must join the resulting audio files into a complete story.
Voices for Young Listeners
The API provides eight distinct voice presets designed to suit various storytelling moods. Each voice is generated from licensed recordings, ensuring a natural and engaging listening experience for young audiences without the need for complex audio engineering.
You can select from warm narrators, soft storytellers, or upbeat characters. The system handles the synthesis automatically, delivering high-quality audio files ready for your kindergarten book projects.
Warm and clear narrator styles
Aria offers a warm and clear narration style, ideal for straightforward reading. Her voice is clear, making it suitable for educational content or simple storybooks.
- Clear articulation
- Professional tone
- Ideal for educational content
Soft storytelling voices
Luna provides a soft, storytelling delivery that soothes young listeners. Sage offers a calm, instructional tone suitable for guided activities or moral stories. These voices create a comforting atmosphere for bedtime reading or quiet time.
Milos conversational style and Felix's energy can also be adapted for gentle, engaging storytelling depending on the book's pacing.
- Comforting tone
- Engaging pacing
- Suitable for bedtime
Bright and upbeat options
Nova brings a bright, upbeat energy to energetic stories. Felix delivers an energetic, promo-style voice that keeps children engaged. Atlas provides a neutral, news-like clarity for structured narratives, while Orion offers a deep, documentary-style depth for older listeners.
- High energy
- Clear and neutral
- Deep and engaging
Supported Languages
Lumivox supports 23 languages, allowing you to localize your kindergarten books for diverse audiences. You can generate audio in Arabic, Chinese, German, Japanese, Korean, and other supported languages.
English, Spanish, and French
These are the most common languages for early childhood content. Our engine handles them natively, ensuring clear pronunciation suitable for young listeners.
23 languages available
Beyond the major languages, we support Danish, Finnish, Greek, Hebrew, Hindi, Italian, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Each voice can speak any of these languages, so you can mix and match voices for different characters or editions.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-detect or set language code
If you do not specify a language, the system guesses it from the script (Latin text defaults to English). For non-English Latin-script text, always set the language parameter to ensure correct pronunciation. Vietnamese, Indonesian, Thai, and Ukrainian are not supported.
Pricing for Publishers
Pricing is straightforward: $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward the total. For a typical kindergarten book, this allows you to budget audio production costs accurately without hidden fees.
$10 per million characters
Calculate costs based on your manuscript length. If your book contains 50,000 characters, the total cost is $0.50. This scale makes it feasible to produce full-length audiobooks without significant upfront investment.
Pay only for successful requests
If synthesis fails, you are not charged. The credit is returned in full. This ensures you only pay for usable audio files generated for your stories.
No monthly subscriptions
Start with a $0.50 trial credit valid for 7 days. Top up via USDT (TRC-20) with a minimum of $5. Balance does not expire, and there are no recurring fees or minimum spend requirements.
- USDT (TRC-20) payments only
- Minimum top-up: $5
- Balance does not expire
Technical Integration
Use the official OpenAI SDKs by changing the base_url to https://api.getx99.com/v1 and providing your Lumivox key. This allows you to leverage existing client libraries without learning a new interface.
OpenAI SDK compatible
Send standard JSON payloads with model, input, and voice fields. The endpoint accepts the same request shape as the OpenAI speech endpoint, ensuring immediate compatibility with your current codebase.
- Supports
tts-1andtts-1-hdmodels - Accepts
mp3,wav,opus,flac, andpcmformats
Simple JSON requests
Construct a POST request to /v1/audio/speech with your text and desired voice settings. You can also specify a speed between 0.25 and 4.0 to adjust the narration pace for young listeners.
Fast response times
Generation typically takes a few seconds for short phrases. For longer texts, the API processes requests sequentially, so you may experience brief queuing during high load. Audio is returned directly in the response body.

Data and Licensing
Lumivox API processes your kindergarten book text solely to generate the audio file. The input text is not used for training voice models or improving the system, ensuring your stories remain private and distinct.
Text not used for training
Your manuscript content is processed exclusively for the immediate synthesis task. It is not retained in any training datasets, so your unique stories do not influence future model outputs or become part of the engine’s learning pool.
Audio not stored by us
The generated audio file is returned directly in the API response and is not stored on our servers. Once you receive the file, we do not keep a copy of the audio, minimizing data retention risks for your content.
Watermarked synthetic speech
Every audio file generated by Lumivox includes an inaudible watermark. This mark identifies the file as synthetic speech, which is helpful for transparency when distributing kindergarten audiobooks to children or parents.
Why Choose This API
Lumivox is built for the specific workflow of children’s authors who need to convert long manuscripts into audio without manual chunking. The API handles splitting texts over 4096 characters, but you must join the resulting audio files, saving you the work of splitting.
Cost-effective for long books
At $10 per million characters, generating a full kindergarten book costs very little. You only pay for successful synthesis; failed requests are refunded in full.
- $0.01 per 1,000 characters
Easy to start with trial credit
Sign up with Google to receive $0.50 in trial credit, covering about 50,000 characters for seven days. This allows you to test voice quality and integration before committing to a top-up.
Transparent billing
Balance does not expire, and there are no hidden fees or monthly subscriptions. Payments are made via USDT on the TRON network, with automatic crediting within minutes. No invoices or VAT complications.
Getting Started
Creating audio for kindergarten books starts with a simple account setup. You can sign up immediately using your Google account for quick access to your dashboard and trial credit.
Sign up with Google
Visit the /get-api-key/ page and click the Google sign-in button. Your account is created instantly, and you receive $0.50 in trial credit valid for 7 days, allowing you to test the service without upfront payment.
Get your API key
Once logged in, your unique API key is displayed on the dashboard. Use this key in the Authorization: Bearer tts-... header for all requests. You can issue a new key at any time, which immediately invalidates the old one.
Try the demo
Use your trial credit to send a short text snippet. The API processes the request and returns an audio file, demonstrating the split-and-join workflow for longer children’s stories. Check the balance and usage stats on your dashboard to track consumption.
- Send up to 4096 characters per request
- Receive MP3, WAV, OPUS, FLAC, or PCM
- Test with any of the 8 voice presets
Support and Limits
Manage your production queue with clear rate limits and reliable payment options designed for self-publishers.
60 requests per minute
Each API key supports up to 60 requests per minute. This limit ensures stable generation for long texts that are split into chunks. Requests process sequentially, so heavy loads may queue briefly.
Email support only
We do not offer phone numbers or live chat. All inquiries are handled via email. This keeps our overhead low and allows for detailed, documented responses to your technical or billing questions.
USDT payments accepted
Top-ups are processed via USDT on the TRON network (TRC-20). Minimum deposit is $5. Credits appear automatically within minutes of transfer. No credit cards or subscriptions are required.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Male voices offer distinct tonal qualities for different narrative needs.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- TRON developer hub: TRC-20
- ISO 639 language codes
- OpenAI API reference: create speech
- Creative Commons Attribution 4.0
- LibriTTS-R paper (arXiv 2305.18802)
- W3C WAI: making audio and video accessible
- MDN: Web Speech API
- LibriVox public-domain audiobooks
- curl documentation
- Python documentation
- Tether (USDT)
