Frequently asked questions
What is text-to-speech API?
A cloud API that converts text into audio files via a POST request. Send JSON with text, voice, and format settings, and receive the generated audio. It follows the same request shape as the OpenAI speech endpoint, allowing you to use standard OpenAI SDKs by changing the base URL to https://api.play4447.com/v1.
How do I download audio files?
Audio files are returned directly in the API response body. You do not need to download them from a separate link; the synthesis engine generates the audio and sends it back to your application immediately. Supported formats include mp3, wav, opus, flac, and pcm, which you specify in your request.
Which voices are best for narration?
For narration, we recommend aria (warm, clear narrator), luna (soft, storytelling), or atlas (neutral, news). These voices are designed for clarity and consistency, making them ideal for reading textbooks and lesson plans. You can also use sage for instructional content or milo for conversational educational materials.
How many languages are supported?
We support 23 languages, including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and Russian. Any voice can speak any of these languages. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text.
What is the character limit per request?
Each API request accepts up to 4096 characters of input text. For longer texts, you must split the content into parts of this size, generate audio for each part, and join the resulting audio files. This ensures efficient processing and reliable delivery of the final audio.
How much does the API cost?
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spend requirements, and your balance does not expire.
Is there a free trial available?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, allowing about 50,000 characters of generation. Accounts created with email and password start without trial credit. You can top up using USDT on the TRON network (TRC-20) with a minimum of $5.
Can I use the API for commercial projects?
Yes, the API is available for any use case, including commercial projects. Generated audio files carry an inaudible watermark marking them as synthetic speech. Input text is used only to produce audio and is not used for training, ensuring your content remains private and secure.
How do I split long texts into audio?
Split your text into chunks of up to 4096 characters. Send each chunk as a separate POST request to the /v1/audio/speech endpoint. Receive the individual audio files and join them in your application. This method ensures reliable synthesis, as each request is processed independently.
What formats are supported for download?
We support mp3, wav, opus, flac, and pcm formats. Specify your preferred format in the response_format field of your request. These options cover most educational and technical needs, from lightweight web playback to high-quality archival storage, without requiring additional conversion tools.
Does the API support streaming audio?
No, the API does not support streaming, WebSocket, or real-time partial audio. It returns the complete audio file after synthesis is finished. This design simplifies integration for batch processing of textbooks and lesson plans, where immediate streaming is not a requirement.
Is there an SLA for uptime?
No, we do not provide an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds to generate.
How do I contact support?
Support is available by email only. There is no phone number, live chat, or on-premise support. You can reach us through the contact page on our site. We do not offer SLAs, uptime guarantees, or certifications like SOC 2 or HIPAA, focusing on straightforward API access.
Are the voices realistic and natural?
Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They are clear and natural for educational content. Each generated file includes an inaudible watermark to mark it as synthetic speech. They do not mimic specific celebrities or politicians.
First request
curl
curl https://api.play4447.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 Educators
We process text through a straightforward API endpoint. Send your lesson content and receive generated audio files ready for classroom use or digital libraries.
Select from eight distinct voice presets tailored for educational clarity. Each voice offers a specific tone, from warm narration to clear instruction, ensuring the audio matches your teaching style.
Upload text or use the API
Input text directly into the API or upload documents. The system handles up to 4,096 characters per request; longer texts must be split and joined by the client. This ensures consistent audio generation without manual formatting.
- Send text via JSON body
- Automatic splitting for long texts
- Up to 4,096 characters per request
Choose from 8 clear voices
Pick from eight licensed voices based on real recordings. Options range from warm narrators like Aria to calm instructional voices like Sage. All voices support 23 languages, allowing you to match content to your audience.
- Aria for literature
- Atlas for news
- Sage for instruction
Download MP3, WAV, or FLAC
Generate audio in formats suitable for various devices. Choose MP3 for web players, WAV for high-quality editing, or FLAC for lossless storage. Files are returned directly in the response for immediate use.
- MP3 for web
- WAV for editing
- FLAC for storage
Why Teachers Choose Our API
Teachers and methodologists need reliable tools that integrate seamlessly with existing workflows, and our API delivers exactly that. By matching the OpenAI request shape, you can use familiar SDKs with a simple base URL change, eliminating the need to learn complex new systems.
Cost efficiency is critical for educational budgets. Our pricing model charges only for actual usage, ensuring you never pay for idle capacity or unused features during the school term.
Simple integration with OpenAI SDKs
Update your base URL to https://api.play4447.com/v1 and use the official OpenAI SDKs. This compatibility allows educators and developers to convert textbook text into audio files by changing the base URL in the OpenAI SDK.
- Same request shape as OpenAI speech endpoint
- Works with official OpenAI SDKs
- Standard JSON body structure
Pay only for what you use
Each request consumes characters based on the input text, including spaces and punctuation. You are charged $0.01 per 1,000 characters, ensuring costs align directly with the volume of lesson plans or textbooks converted.
- $10 per 1 million characters
- Spaces and punctuation count
- Failed requests are free
No monthly subscriptions required
Unlike many platforms that lock features behind recurring plans, we operate on a pay-as-you-go basis. There are no seats, minimum spends, or expiration dates on your balance, making it easy to budget for semester-long projects.
Supported Languages for Global Schools
VoxClass supports 23 languages, ensuring your educational materials reach diverse student populations. The API automatically detects language from the script, but you can explicitly set the ISO code for precision, especially with non-English Latin text.
Every voice supports all listed languages, providing consistent audio quality across subjects. Note that Vietnamese, Thai, and Ukrainian are not currently supported.
English, Spanish, French, and more
Core languages like English, Spanish, French, and Portuguese are fully supported. These are essential for standard curriculum delivery and language learning exercises.
- English, Spanish, French, Portuguese
Arabic, Chinese, German, Italian
Major global languages including Arabic, Chinese, German, and Italian are available. Each voice adapts naturally to the linguistic nuances of these languages.
Use these voices for multilingual lesson plans or regional textbook conversions.
- Arabic, Chinese, German, Italian
Russian, Japanese, Korean, and others
Additional support for Russian, Japanese, Korean, and 14 other languages like Hindi, Turkish, and Swahili. This allows schools with diverse demographics to access audio content without external tools.
Total of 23 languages are available for immediate use.
- Russian, Japanese, Korean, Hindi, Turkish, Swedish, Danish, Finnish, Norwegian, Polish, Greek, Hebrew, Malay, Swahili
Voice Options for Different Subjects
VoxClass provides eight distinct voice presets to match the tone of your educational materials. Each voice is derived from licensed recordings, ensuring high-quality synthetic speech that sounds natural in a classroom setting. These options allow educators to tailor the listening experience to the subject matter.
Aria for literature and narratives (warm, clear narrator)
Aria offers a warm, clear narrative tone ideal for reading short stories or poetry. Her voice helps students engage with literary texts without the distraction of inconsistent pacing found in less polished synthetic voices.
- Best for: Short stories, poetry, and creative writing assignments.
- Voice type: Female, warm, clear narrator.
Atlas for history and news (neutral, news)
Atlas delivers a neutral, news-style delivery perfect for historical documents or current events. His consistent tone ensures that factual content remains the focus, making him suitable for reading primary sources or informational texts.
- Best for: Historical texts, news articles, and factual reports.
- Voice type: Male, neutral, news style.
Sage for instructional content (calm, instructional)
Sage provides a calm, instructional voice that is excellent for step-by-step guides or lesson plans. Her steady pacing helps students follow complex instructions or review key concepts without fatigue during longer listening sessions.
- Best for: Lesson plans, instructions, and academic reviews.
- Voice type: Female, calm, instructional.
Pricing Designed for Schools
Pricing is straightforward: $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free, ensuring you pay only for successful audio generation. There are no monthly subscriptions, seats, or minimum spend requirements.
$10 per 1 million characters
Costs are calculated based on character count, including spaces and punctuation. This predictable rate allows schools to budget accurately for large textbooks or lesson plans without unexpected fees.
Free trial with Google sign-in
Sign up with Google to receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters for testing voices and formats before committing to larger purchases.
Top up with USDT for flexibility
Add funds via USDT on the TRON network (TRC-20). The minimum top-up is $5, with credits appearing automatically within minutes. Balances do not expire, and no VAT or invoices are involved.
- Minimum top-up: $5
- Supported network: TRC-20 (TRON)
- Credits credited automatically within minutes

Technical Specifications for Developers
The API follows the standard OpenAI request shape, allowing developers to use existing OpenAI SDKs by simply adjusting the base URL to https://api.play4447.com/v1. This ensures a familiar integration path for technical staff without requiring custom libraries.
Endpoint: POST /v1/audio/speech
Send text via JSON to the speech endpoint. The system accepts models "tts-1" or "tts-1-hd" with identical engines and pricing. Text is limited to 4096 characters per request; longer texts must be split and joined by the client.
- Base URL: https://api.play4447.com/v1
- Auth: Bearer tts-<key>
- Models: tts-1, tts-1-hd
Supports MP3, WAV, OPUS, FLAC, PCM
Choose the audio format that fits your LMS or classroom tools. MP3 offers efficient compression for web streaming, while WAV and FLAC provide lossless quality for archival or high-fidelity playback. PCM is available for raw data processing.
- MP3, WAV, OPUS, FLAC, PCM
Rate limit: 60 requests per minute
Each API key supports 60 requests per minute, ensuring stable generation during lesson prep. New accounts start with a 10 requests/minute limit until the first top-up. Requests process sequentially, so queues may form under heavy load.
Common Use Cases in Education
Transforming dense educational materials into accessible audio formats is a practical way to support diverse learning styles. Educators can convert lesson plans and reading passages into speech, allowing students to listen rather than just read.
This approach reduces screen time and makes content available during commutes or breaks, ensuring learning continues beyond the classroom environment.
Converting textbooks to audio
Educators can feed raw text from digital textbooks directly into the API to generate clear audio files. This allows students with reading difficulties or visual fatigue to consume curriculum materials through listening.
Since the API handles up to 4096 characters per request, long chapters can be split and joined by the client.
- Supports 23 languages including English, Spanish, and Chinese
- Compatible with standard MP3 and WAV formats
- No complex software setup required for teachers
Creating listening exercises
Teachers can generate specific dialogue or narration for listening comprehension tests. By adjusting the speed parameter, educators can tailor the audio difficulty to match student proficiency levels.
Using different voices like Felix for energetic prompts or Sage for calm instructions adds variety to audio quizzes, keeping students engaged without needing multiple human voice actors.
Generating audiobooks for students
Short stories and literary excerpts can be converted into high-quality audio files using voices like Aria for narratives or Orion for documentaries. This creates audio files for classroom libraries.
The inaudible watermark confirms the synthetic origin, which is useful for tracking generated educational content. Students can listen to these files on any device with basic audio capabilities.
Data Privacy and Security
When you send text to the VoxClass API, it is processed solely to generate the audio response. Once the file is delivered to your classroom or platform, the original text is not stored or reused for any other purpose.
Unlike many consumer services, we do not use your lesson plans or textbook excerpts to train our models. Your educational content remains yours, ensuring that sensitive curriculum data stays within your control without being repurposed for algorithmic improvement.
Input text used only for generation
The text you submit via the POST endpoint is used exclusively to create the audio file for that specific request. It is not archived for long-term storage or analysis.
No training on your data
Your input texts are not added to our training datasets. This ensures that your specific pedagogical materials remain distinct from the general data used to maintain the base engine.
Metadata kept for billing only
We retain minimal metadata, including the timestamp, character count, and status of each request. This information is kept strictly to calculate your usage and process your USDT top-ups accurately.
- Timestamp and character count
- Request status (success/failure)
- Used for invoice verification
Get Started Today
Create your account on the /get-api-key/ page using Google or an email address. The dashboard immediately displays your active API key, current balance, and a ready-to-use cURL example for generating audio.
Once registered, you can start sending text to the API. The system processes requests sequentially, converting your educational materials into clear audio files without complex setup.
Sign up with Google or email
Accounts are created directly on the site. Using Google provides instant access, while email registration requires no third-party dependency. Each account is tied to the specific site domain.
- Google or email registration available
- Accounts are site-specific
Get your API key instantly
Your dashboard shows the API key immediately after creation. You can issue a new key at any time, which invalidates the previous one instantly. Use this key with the OpenAI SDK by changing the base URL.
- Key visible in dashboard
- Instant key rotation support
Try the free trial credit
Signing in with Google grants $0.50 of trial credit, valid for 7 days. Email-based accounts start without this credit. You can top up later using USDT on the TRON network.
- $0.50 credit for Google sign-ins
- 7-day validity period
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Empowering educators with adaptable frameworks to nurture critical thinking and foster genuine curiosity in every learner.
23 languages
Any voice speaks any of these languages.
