Frequently asked questions
Is this text to speech app free for teachers?
Signing in with Google provides a $0.50 free trial valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without trial credit. Beyond the trial, pricing is $0.01 per 1,000 characters. There are no monthly plans or minimum spends, so you only pay for what you use.
Which voices are best for reading aloud in class?
Aria offers a warm, clear narrator style, while Luna provides a soft, storytelling tone. Sage delivers calm, instructional audio for lessons, and Milo sounds friendly and conversational. All eight voices support all 23 languages, allowing you to choose the tone that best fits your specific educational material.
How many languages does the API support?
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script.
Can I use this API for commercial school projects?
The API is available for any use case, including commercial school projects, as there are no restrictions on usage type. Generated audio files are not stored on our servers, but you receive the audio directly in the response. You own the output generated from your text input for your specific projects.
What happens if the audio generation 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. You can retry the request or adjust parameters like speed or voice without incurring additional costs if the initial attempt does not succeed.
Do I need to install any software to use the API?
No software installation is required. The API uses standard HTTP requests, so you can use the official OpenAI SDKs by changing the base URL or send plain HTTP requests. It works with any programming language or tool that can send JSON POST requests to the endpoint, making it easy to integrate.
Is the audio generated stored on their servers?
Generated audio is returned in the response and is not stored on our servers. Input text is used only to produce the audio and is not used for training. We keep request metadata, such as time and character count, solely for billing purposes. Your audio files are delivered directly to your application.
Can I change my API key if it gets compromised?
Yes, you can issue a new API key at any time. When a new key is issued, the old one stops working immediately. Each account has one active key at a time. You can manage your keys and view your balance and usage details on the /get-api-key/ page of your account.
What is the maximum text length for one request?
The maximum input text length is 4096 characters per request. For longer texts, you should split the content into parts of up to 4096 characters and join the resulting audio files. This allows you to generate audio for full lessons or books by processing them in manageable chunks via the API.
Does the API support special characters and punctuation?
Yes, spaces and punctuation count as characters in the pricing model. The API processes standard text inputs including special characters. Since pricing is based on character count, all standard typographic elements are included in the 4096-character limit per request, ensuring accurate audio generation for your formatted educational materials.
How long does it take to generate audio?
Typical speed is roughly real-time, generating about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts will take time proportional to their length, similar to real-time playback.
Can I use the generated audio in online courses?
Yes, you can use the generated audio in online courses. The API provides clear voices suitable for educational content. Each generated file carries an inaudible watermark marking it as synthetic speech. You receive the audio directly, allowing you to embed it in your course materials.
Is there a limit to how many students can use the audio?
There is no limit to how many students can use the generated audio. The rate limit applies to your API key (60 requests per minute), not to the number of end-users. You can distribute the audio files you generate to as many students as needed for your lessons or courses.
Do I need technical skills to integrate the API?
Basic technical skills are helpful but not extensive. The API uses a standard JSON body similar to OpenAI’s 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, making it easy to test and integrate into your workflow.
First request
curl
curl https://api.playt999.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 Need Reliable TTS
Text-to-speech technology provides consistent, high-quality audio that supports diverse learning needs. Unlike human-read recordings, an API generates predictable audio files that teachers can integrate directly into digital lessons or printed materials.
Accessibility for Diverse Learners
Students with visual impairments or dyslexia benefit from clear, synthetic narration that eliminates the variability of human reading. Reliable audio ensures every student accesses the same content at the same pace.
Support for Reading Difficulties
Text-to-speech aids comprehension by allowing students to listen while reading. This dual-input method reduces cognitive load, helping those who struggle with decoding text to focus on meaning and context.
Multi-Language Support
Educators can generate audio in 23 languages, supporting ESL students and language classes. The API handles automatic language detection for Latin scripts, ensuring accurate pronunciation without manual configuration.
How the API Works
The API accepts standard JSON payloads via a POST request, making integration straightforward for any developer familiar with basic HTTP requests. You send the text, voice, and format preferences, and receive an audio file in return.
By adjusting the base URL in the official OpenAI SDKs, you can use existing client libraries to interact with VocalClass without rewriting your code. This compatibility simplifies adoption for teams already familiar with the standard SDK workflow.
Simple JSON Integration
Send your text content in a JSON body to the speech endpoint. The API processes the request and returns the audio file directly in the response, ready for immediate playback or download in your preferred format.
OpenAI SDK Compatibility
Use the official OpenAI SDKs by pointing the base URL to our API endpoint. This allows you to leverage familiar methods and structures, reducing the learning curve for integrating text-to-speech into your educational applications.
Instant Audio Generation
Text is converted to audio at roughly real-time speed for long texts (about 25 characters per second). Short phrases may take a few seconds to generate, and requests are processed sequentially, so under load, a request may wait in a queue.
Voice Selection for Education
Choosing the right voice ensures students engage with the material without distraction. VocalClass offers eight presets designed for clarity and natural pacing, allowing educators to match the tone to the lesson type.
You can select from warm narrators for stories or calm instructors for explanations.
Clear Narration Voices
Aria provides a warm, clear narration ideal for reading literature or historical texts. Nova offers a bright, upbeat tone suitable for younger students or energetic lesson introductions.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
Instructional Tone Options
Sage delivers a calm, instructional voice perfect for step-by-step tutorials or exam instructions. Luna’s soft storytelling style works well for narrative-driven language lessons or reading comprehension exercises.
- Sage: Calm, instructional
- Luna: Soft, storytelling
Neutral News Style
Atlas provides a neutral, news-style voice for factual content or current events. Milo offers a friendly, conversational tone for dialogue practice or interactive quizzes.
- Atlas: Neutral, news
- Milo: Friendly, conversational
Supported Languages and Scripts
VocalClass supports 23 languages, enabling educators to generate audio for diverse classroom materials and accessibility needs. Any voice can speak any of the supported languages, allowing you to mix voices and languages in your educational content.
23 Languages Available
The API 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. Any voice can speak any of these languages, allowing you to mix voices and languages in your educational content.
Automatic Language Detection
When you do not specify a language, the system guesses it from the text script. For non-English Latin-script text, you should set the language parameter explicitly to ensure accurate pronunciation.
Latin Script Defaulting
Latin script text defaults to English if no language is set. This simplifies integration for English-language lessons but requires explicit configuration for other Latin-based languages like Spanish or French.
Pricing for Educational Use
VocalClass charges $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full if synthesis fails.
Pay Per Character
You only pay for what you generate. Typical speed is roughly real time, producing about 25 characters of text per second. Short phrases may take a few seconds, and requests are processed sequentially, so high load may cause slight queueing.
- No hidden fees per format or voice
- Full refund on failed synthesis
No Monthly Fees
There are no monthly plans, seats, or minimum spend requirements. Your balance does not expire. Top-ups via USDT on the TRON network are credited automatically within minutes. No cards, PayPal, subscriptions, or VAT invoices are needed.
Free Trial Credit
Sign in with Google to receive $0.50 in credit, valid for 7 days. This covers approximately 50,000 characters, enough to test integration. Accounts created with email and password start without this trial credit.

Technical Specifications
Understand the technical constraints to plan your lesson audio generation efficiently. Our API processes requests sequentially, meaning long texts are split and joined automatically. Typical generation speed is roughly real-time, producing about 25 characters of text per second of audio.
Short phrases may take a few seconds to synthesize. During high load, requests may wait in a queue. Understanding these limits helps you schedule batch processing for classroom materials without unexpected delays.
Rate Limits Explained
Your API key allows 60 requests per minute under normal usage. New accounts start with a limit of 10 requests per minute until the first top-up is processed. This ensures stable service for classroom deployments.
- 60 requests/minute after top-up
- 10 requests/minute for new accounts
- Sequential processing may cause queueing
Audio Formats Available
Choose the format that best fits your LMS or device. We support mp3, wav, opus, flac, and pcm. MP3 and OPUS offer small file sizes for web delivery, while WAV and FLAC preserve high fidelity for listening stations.
All generated files include an inaudible watermark identifying them as synthetic speech, ensuring transparency in educational content.
- mp3, wav, opus, flac, pcm
Character Limits Per Request
Each API call accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer lessons, split your text into chunks and join the resulting audio files.
This limit ensures consistent processing speed.
- Max 4096 characters per request
- Spaces and punctuation count
- Split and join for longer texts
Data Privacy and Usage
Your students' reading materials are secure with us. We use the input text solely to produce the audio file and do not use it for training our models or improving the voice engine. This ensures that your specific lesson content remains private and is not repurposed by our system.
Text Not Used for Training
Unlike many consumer-grade services, VocalClass does not retain your instructional texts for algorithmic learning. The data is processed strictly for the immediate generation of the audio file, ensuring that your pedagogical materials remain exclusively yours.
No Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once you download the file to your classroom device or learning management system, we hold no copy of the audio, minimizing data exposure.
Request Metadata Retention
We retain minimal request metadata, including the timestamp, character count, and request status, solely for accurate billing and troubleshooting. This data does not include the content of the text or the resulting audio, ensuring your educational content remains anonymous in our logs.
Getting Started Quickly
Start by creating an account on the /get-api-key/ page. You can sign in instantly with your Google account to receive a $0.50 trial credit (valid for 7 days) or use an email and password.
Once registered, the dashboard displays your API key, balance, characters left, usage, and a ready curl example. This key authenticates all requests to the API base URL.
Sign Up with Google
Visit the registration page and select "Sign in with Google." This method automatically grants you $0.50 in trial credit, sufficient for approximately 50,000 characters. The credit expires in 7 days, giving you time to test the service without immediate payment.
- Instant account creation
- $0.50 trial credit included
- No credit card required
Generate Your API Key
After signing up, your unique API key is displayed immediately on the dashboard. This key follows the format tts-... and is used in the Authorization header for all requests. You can generate a new key at any time; the previous one stops working instantly.
- Key format:
tts-... - Instant revocation on regeneration
- One active key per account
First Curl Example
Test the API with a simple command. Replace YOUR_API_KEY with your key from the dashboard. This request generates speech using the nova voice in MP3 format.
```bash curl -X POST "https://api.playt999.com/v1/audio/speech" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Hello world", "voice": "nova", "response_format": "mp3"}' \ -o speech.mp3 ```
Common Educational Use Cases
VocalClass enables educators to convert lesson texts into clear audio files for accessible learning materials. This supports students with reading difficulties or visual impairments by providing consistent, high-quality narration without the variability of human recording.
The API’s straightforward integration allows teachers to generate audio on demand. This is ideal for creating reusable listening resources that students can access anytime, ensuring consistent pronunciation across all class materials.
Audiobook Creation
Convert textbook chapters or reading lists into audio format. With a 4,096-character limit per request, longer texts are split and joined seamlessly. This creates durable listening resources.
Use the 'aria' or 'nova' voices for engaging narration. The process is simple: send the text via POST request and receive the audio file directly. No complex studio setup is required.
- Ideal for long-form reading assignments
- Consistent narration tone across chapters
- No storage costs for generated audio
Listening Comprehension
Generate clear audio versions of exam questions or reading passages. Students with dyslexia or processing difficulties benefit from hearing the text before reading it. This supports diverse learning needs effectively.
Use the 'sage' voice for calm, instructional tones. The audio is generated quickly, allowing teachers to update materials as needed. Failed requests are free, ensuring cost efficiency.
- Supports students with dyslexia
- Quick generation for updated materials
- Clear, calm instructional tone
Language Learning Materials
Create pronunciation guides for the 23 supported languages. Teachers can generate specific phrases for students to practice. The API supports automatic language detection, simplifying the creation of multilingual resources.
Use the 'luna' voice for soft storytelling or 'atlas' for neutral news-style reading. This variety helps students distinguish between narrative and formal speech styles in their target language.
- Supports 23 languages
- Automatic language detection
- Variety of voice tones for context
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Effective teaching strategies empower educators to adapt dynamically to diverse classroom needs and foster meaningful student engagement.
23 languages
Any voice speaks any of these languages.
