Frequently asked questions
What is a text reader API for schools?
It is a cloud service where you send text and receive an audio file via a simple API endpoint. This allows teachers to convert reading materials into audio without technical overhead. You can generate accessible content for students quickly using standard HTTP requests, making it easy to integrate into existing educational workflows.
How does the French text reader work?
Send a POST request to the speech endpoint with your French text and set the voice parameter. You can optionally specify the language code to ensure accurate synthesis. The API processes the text and returns an audio file in your chosen format, such as MP3 or WAV, ready for classroom use.
Which voices are best for reading aloud in class?
Any of our eight voices suits classroom reading, as each can speak all 23 supported languages naturally. Aria offers a warm, clear narrator style, while Luna provides a soft, storytelling tone ideal for younger students. For instructional content, Sage delivers a calm, clear voice. Atlas provides a neutral news style, and Orion works well for documentary-style lessons. Choose based on your specific lesson context rather than assuming one voice is universally superior.
Does the API support languages other than French?
Yes, we support 23 languages including Arabic, Chinese, German, Hindi, Japanese, Spanish, and more. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses it, but for non-English Latin text, we recommend setting the language code explicitly for accurate results.
How much text can I process in one request?
Each request can handle up to 4096 characters of input text. If your material is longer, you can split it into parts of this size and join the resulting audio files. This ensures consistent quality and allows you to manage large textbooks or lesson plans efficiently through simple batching.
Is the API suitable for students with dyslexia?
Absolutely. Converting text to audio helps students who struggle with reading by providing an alternative way to access content. You can adjust the speed from 0.25 to 4.0 to match individual listening preferences, making it a versatile tool for creating accessible reading materials and supporting diverse learning needs in the classroom.
Do I need to install software to use this?
No, it is a cloud API. You simply send JSON requests to our endpoint and receive audio files. You can use the official OpenAI SDKs by changing the base URL or use plain HTTP. This means no software installation is required on your school’s computers or servers to get started.
How are the voices licensed?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures high-quality, legally sound audio for your educational projects. Every generated file also carries an inaudible watermark to identify it as synthetic speech, maintaining transparency in your educational content production.
Can I use this for commercial school projects?
Yes, you can use the generated audio for any purpose, including commercial school projects. You can use the audio files for educational purposes. You pay only for the characters processed, with no monthly plans or seats, making it affordable for individual teachers or entire school districts.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generations. If you encounter issues, you can retry the request or check your key status, knowing that your budget is protected against technical glitches.
Is my students' data stored?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata like time and status for billing purposes, ensuring your students' reading materials remain private and secure for educational use.
How fast is the audio generation?
Typical speed is roughly real time, about 25 characters of text per second of generation. Short phrases may take a few seconds, while longer texts process in real time. Requests are processed sequentially, so under heavy load, a request might wait in a queue before being synthesized.
Can I control the speed of the narration?
Yes, you can control the speed using the speed parameter in your request. The allowed range is from 0.25 to 4.0. This allows teachers to slow down narration for younger students or speed it up for advanced listeners, providing flexibility to match the listening pace of different age groups.
How do I pay for the API?
We accept USDT on the TRON network (TRC-20) with a minimum top-up of $5. Credits are added automatically within minutes. There are no credit cards or PayPal options. You can start with a $0.50 free trial when signing in with Google, or pay as you go with no monthly plans.
First request
curl
curl https://api.playz77.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.mp3Why Teachers Choose Our TTS API
LumaSpeak empowers educators to create accessible, multi-language audio content with a simple, affordable TTS API. By converting text to speech, you can support diverse learning needs without technical overhead.
With native voices for 23 languages and straightforward integration, you can easily enhance lesson plans and reading materials for all students.
Accessible Reading for All Students
Convert textbooks, handouts, and articles into audio files instantly. This supports students with dyslexia or visual impairments by providing alternative reading formats.
Each audio file is generated via a standard API call, ensuring consistent quality across all classroom materials.
- Support for struggling readers
- Accessible materials for visual impairments
- Consistent audio quality
Language Learning with Native Voices
Expose students to authentic pronunciation with 23 supported languages. From Arabic to Turkish, each voice delivers clear, natural speech.
Use the language parameter to ensure accurate accent and tone, even when the input text uses Latin script.
- 23 languages supported
- Authentic native pronunciation
- Precise language control
Simple Integration for Lesson Plans
Send text via a standard REST endpoint and receive an audio file. No complex setup or dedicated SDK required.
Use the OpenAI SDK by changing the base URL, or make a simple HTTP POST request to generate audio for your lessons.
- Standard REST endpoint
- OpenAI SDK compatible
- No dedicated SDK needed
Supported Languages for Classrooms
LumaSpeak supports 23 languages, including French, German, Spanish, and Arabic, enabling educators to create accessible content for diverse student populations. Each voice can speak any of these languages, ensuring consistent quality across different linguistic needs in the classroom.
French Pronunciation Accuracy
Teachers can rely on clear, native-quality pronunciation for French texts. The API handles phonetic rules automatically, making it ideal for language learning exercises where accurate auditory models are essential for student development.
Support for 23 Languages
The platform supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This wide range allows methodologists to prepare multilingual reading materials without needing multiple specialized tools.
- Arabic, Chinese, Danish, Dutch, English, Finnish
- French, German, Greek, Hebrew, Hindi, Italian
- Japanese, Korean, Malay, Norwegian, Polish, Portuguese
- Russian, Spanish, Swahili, Swedish, Turkish
Auto-Detection vs Manual Selection
By default, the API guesses the language from the text script, defaulting to English for Latin characters. For non-English Latin-script text, such as French or German, you should explicitly set the language parameter to ensure accurate synthesis and avoid mispronunciation.
Voices Tailored for Education
The right voice transforms how students engage with text. LumaSpeak offers eight distinct presets designed to match different classroom needs, from clear narration to friendly conversation. Each voice is based on licensed recordings, ensuring high-quality, consistent audio for your lessons.
Educators can choose between warm narrators like Aria and Luna, or energetic tones like Felix and Milo. These options help keep students engaged whether they are listening to a story or reviewing key concepts.
Clear Narration Voices
Aria and Luna provide warm, clear voices ideal for storytelling and reading materials. Aria’s clarity makes complex texts easier to follow, while Luna’s soft tone suits longer, narrative-driven lessons.
Sage offers a calm, instructional tone perfect for step-by-step guides or educational explanations. These voices ensure that pronunciation remains consistent across all materials, aiding students who rely on audio for comprehension.
- Aria: Warm, clear narrator for general reading.
- Luna: Soft, storytelling voice for narratives.
- Sage: Calm, instructional tone for lessons.
Friendly Conversational Tones
Nova and Milo bring energy and approachability to educational content. Nova’s bright tone works well for engaging younger students, while Milo’s friendly style suits conversational language learning exercises.
These voices help create a more inviting atmosphere for language practice.
- Nova: Bright, upbeat voice for engagement.
- Milo: Friendly, conversational tone for practice.
Neutral News-Style Delivery
Atlas delivers a neutral, news-style voice suitable for factual content and current events. His tone is professional and clear, making him ideal for history or science lessons.
Orion provides a deep, documentary-style voice for more serious or detailed topics. Both Atlas and Orion ensure that information is delivered with authority and clarity, supporting students in understanding complex subjects.
- Atlas: Neutral, news-style voice for facts.
- Orion: Deep, documentary tone for details.
How It Works for Teachers
LumaSpeak simplifies audio generation for educators. You send a text payload via a standard POST request to our API endpoint, and receive a synthesized audio file in return. This straightforward workflow allows teachers to convert lesson texts into listening materials without complex setup.
Send Text, Receive Audio
Integration is immediate. By pointing your OpenAI SDK or HTTP client to https://api.playz77.com/v1, you can start generating speech in minutes. The API accepts simple JSON bodies, making it easy to automate audio creation for digital worksheets or reading assignments.
Support for Long Lesson Texts
Each API call handles up to 4096 characters. For longer stories or articles, split the text into chunks and join the resulting audio files. This ensures high-quality generation even for extended reading materials, keeping the process manageable for methodologists designing comprehensive curricula.
Multiple Audio Formats Available
Choose from mp3, wav, opus, flac, or pcm formats to suit your classroom technology. MP3 and Opus are ideal for web delivery, while WAV and FLAC offer uncompressed quality for local playback. This flexibility ensures compatibility with various learning management systems and devices.
Pricing Built for School Budgets
LumaSpeak charges a flat rate of $10 per million characters, making it easy to predict costs for classroom projects. Spaces and punctuation count toward the total, but failed requests are free. This pay-as-you-go model ensures schools only pay for what they actually use, with no hidden fees or wasted budget on unused credits.
There are no monthly subscriptions, no minimum spend requirements, and no annual contracts. Your balance never expires, so you can top up only when needed. This structure is ideal for schools with varying project timelines, allowing methodologists to allocate funds precisely where they are needed most without committing to fixed monthly overheads.
Pay Per Character Used
At $0.01 per 1,000 characters, generating a 4,000-character lesson plan costs just $0.04. You can generate audio for hundreds of students for the price of a single coffee. If a synthesis fails, the charge is returned in full, so you never pay for errors.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Failed requests are free
No Monthly Subscriptions
Unlike traditional software licenses, there are no recurring fees. You top up your balance with USDT on the TRON network (minimum $5) and use it until it runs out. There is no need to manage seats, licenses, or renewal dates for your team of teachers.
- No monthly plans
- No seats or licenses
- Balance does not expire
Free Trial for New Accounts
Sign up with Google to receive $0.50 in free credit, enough for about 50,000 characters. This allows you to test the API quality and generate audio for a short story or two before committing. Accounts created with email and password start without this trial credit.
- $0.50 free credit with Google sign-in
- Approx. 50,000 characters
- Valid for 7 days

Technical Ease for Methodologists
Methodologists appreciate that LumaSpeak uses the same request structure as the OpenAI speech endpoint. By simply updating the base_url to https://api.playz77.com/v1, you can leverage official OpenAI SDKs without learning a new library. This compatibility ensures that existing Python or Node.js scripts for audio generation work with minimal code changes.
Communication happens via a standard REST endpoint, making it easy to integrate with learning management systems or custom teacher dashboards. You send a JSON payload with your text and preferred voice, and receive an audio file directly in the response. No complex WebSocket connections or proprietary clients are required.
OpenAI SDK Compatible
Use the official OpenAI SDK by pointing it to our base URL. This allows teachers and developers to use familiar tools like openai-python without writing custom HTTP handlers.
- Same request shape as OpenAI speech endpoint
- Works with official OpenAI SDKs
- Minimal code changes for integration
Standard REST Endpoint
The API accepts POST requests to /v1/audio/speech. This standard approach means you can test it with curl or any HTTP client instantly.
- Simple JSON input
- Direct audio file output
- No proprietary protocols
Clear Documentation Provided
Documentation at /docs explains all parameters, including voice selection and format options. It includes ready-to-use examples for common educational languages.
- Detailed parameter guide
- Ready-to-use curl examples
- Voice and format lists
Data Privacy and Licensing
LumaSpeak prioritizes educator privacy by ensuring that the text you submit is used solely for generating the requested audio file. We do not retain your input text for model training or future development, keeping your lesson plans and student materials distinct from our dataset.
Voice quality is guaranteed through professional licensing. Each voice preset is based on recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox, ensuring clear, legal usage rights for your classroom audio files without complex clearance processes.
Text Not Used for Training
When you send text to our API, it is processed to create the audio response and is not stored in a training pool. Your specific educational content remains private and is not used to improve our general voice models.
Licensed Voice Recordings
Our eight voice presets are built on high-quality, licensed source material. The LibriTTS-R dataset and LibriVox public domain recordings provide a robust foundation for consistent, clear speech suitable for academic listening exercises.
Synthetic Watermark Included
Every audio file generated includes an inaudible watermark. This marks the file as synthetic speech, which is helpful for verifying the origin of audio content used in student materials or published assignments.
Common Use Cases in Education
Educators can transform static texts into engaging audio resources instantly. By converting lesson materials or stories into speech, teachers provide accessible reading options for students with dyslexia or visual fatigue, ensuring everyone can enjoy the same content through listening.
The API supports long texts by splitting them into 4096-character segments, allowing entire chapters or articles to be processed in one workflow. This reliability makes it easy to build consistent audio libraries for classroom use without technical overhead.
Audio Books for Struggling Readers
Teachers can generate high-quality audio versions of textbooks or storybooks using voices like Aria or Luna. These clear, narrator-style voices help students follow along with complex texts, reducing cognitive load and improving comprehension for those who struggle with decoding written words.
- Convert textbooks into accessible audio formats
- Use warm, clear voices like Aria for narration
- Supports texts up to 4096 characters per request
Listening Comprehension Exercises
Create custom audio exercises by inputting specific vocabulary or sentences. The API’s consistent speed and clear articulation make it ideal for testing listening skills. Teachers can adjust the speed between 0.25 and 4.0 to match different proficiency levels.
- Generate custom audio for vocabulary practice
- Adjust speed from 0.25 to 4.0
- Suitable for listening practice
Multilingual Storytelling
Bring language lessons to life with native-sounding voices in 23 languages. Whether teaching French, Spanish, or Japanese, educators can provide authentic pronunciation models. The API supports auto-detection or manual language selection to ensure accurate accent and intonation.
- Supports 23 languages including French and Spanish
- Native-like pronunciation for language learning
- Manual language code override available
Get Started with LumaSpeak
Start by creating a free account on playz77.com using your Google credentials or email. You immediately receive a $0.50 trial credit, valid for seven days, which covers approximately 50,000 characters of speech generation.
Create Your Account
Visit the /get-api-key/ page to sign up. Accounts are independent per site, so ensure you are on playz77.com. No credit card is required for the trial, making it risk-free for teachers and methodologists to explore the API.
Get Your API Key
Once registered, your dashboard displays your unique API key and current balance. The key starts with 'tts-'. You can issue a new key at any time, which instantly invalidates the old one. Use this key in your Authorization header for all requests.
- Use the key format: Bearer tts-...
Test with French Text
Send a POST request to https://api.playz77.com/v1/audio/speech. Include your text, select a voice like 'aria', and set the language to 'fr' for accurate French pronunciation. Receive the audio file directly in formats like mp3 or wav.
- Endpoint: POST https://api.playz77.com/v1/audio/speech
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the right voice is essential for maintaining student engagement during language learning.
23 languages
Any voice speaks any of these languages.
