Frequently asked questions
Is Amazon Polly Text to Speech better for schools?
We are not affiliated with Amazon Polly. Our API offers a simpler, fixed-rate model at $0.01 per 1,000 characters without enterprise contracts. While Polly requires complex setup, our service provides a straightforward REST API compatible with OpenAI SDKs, making it easier for educators to integrate audio directly into lesson plans without managing subscriptions or seats.
How does the cost compare to Amazon Polly?
Our pricing is transparent: $10 per million characters, or $0.01 per 1,000 characters. There are no monthly plans, seats, or minimum spends. Failed requests are free, and your balance never expires. Unlike complex cloud tiers, you pay only for what you generate, making it highly affordable for schools with limited budgets.
Can I use this API for educational videos?
Yes. You can send text via POST request and receive audio files in formats like MP3, WAV, Opus, FLAC, or PCM. The API supports speeds from 0.25 to 4.0, allowing you to adjust narration pace for video content. Generated audio is returned directly in the response, ready for immediate download and integration.
Does the API support multiple languages?
We support 23 languages, including English, Spanish, French, German, Chinese, Japanese, and Arabic. Any voice can speak any supported language. If you do not specify a language, the system guesses from the script, but we recommend setting the ISO code for non-English Latin text to ensure accurate pronunciation and clarity.
Is there a free trial available?
Yes. Signing in with Google gives you $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 later using USDT on the TRON network, with no minimum spend required to start using the service.
How long does audio generation take?
Generation is roughly real-time, processing about 25 characters of text per second of audio. Short phrases take a few seconds, while longer texts may queue if under load. Requests are processed sequentially, so high traffic might cause slight delays, but the output is delivered as a complete audio file ready for use.
Can I use custom voices?
No. We offer eight preset voices based on licensed recordings from LibriVox: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. We do not offer custom voice cloning, uploading your own voice, or emotion tags. Each generated file includes an inaudible watermark marking it as synthetic speech for transparency.
Is my student 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, such as time, character count, and status, solely for billing purposes. Your educational content remains private and is not repurposed for other uses.
What file formats are supported?
You can choose from MP3, WAV, Opus, FLAC, and PCM via the response_format parameter. These formats cover most educational needs, from web playback to high-quality archival. Simply specify your preferred format in the JSON body of your POST request to the /v1/audio/speech endpoint alongside your text and voice selection.
Do I need coding skills to use this?
Basic coding knowledge helps, but it is not strictly required. Our API follows the standard OpenAI speech endpoint shape, so you can use existing OpenAI SDKs by changing the base URL. We provide ready curl examples on the dashboard, and simple scripts can handle text splitting and audio joining for longer lessons.
How do I pay for the API?
We accept USDT on the TRON network (TRC-20) for top-ups. Minimum deposit is $5, and credits are added automatically within minutes. There are no credit cards, PayPal, or invoices with VAT. Your balance does not expire, and you can issue a new API key at any time if needed.
Is there a limit on characters?
Each request supports up to 4,096 characters. For longer texts, you should split the content into parts, generate audio for each, and join the files. This approach ensures reliable processing. We do not support streaming, so generating entire chapters requires multiple API calls or a script to handle the batching automatically.
Can I generate audio in bulk?
Yes. You can send multiple requests, each with up to 4,096 characters. The rate limit is 60 requests per minute per key (10 before the first top-up). For large projects, you can manage the queue yourself or use a script to split long texts and join the resulting audio files efficiently.
Is this API suitable for dyslexic students?
Yes. The clear, synthetic voices and adjustable speed (0.25x to 4.0x) help students control their reading pace. You can generate audio from textbooks or lessons and provide them as MP3 or WAV files. The consistent pronunciation makes it easier to focus on the content.
First request
curl
curl https://api.playd06.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 Switch from Amazon Polly?
Switching to VocalRead simplifies your audio workflow by removing the administrative overhead of enterprise contracts. We offer a straightforward API designed for educators who need reliable audio lessons without negotiating minimum spends or managing multiple billing tiers.
No complex pricing tiers
Our pricing is linear and transparent: $10 per million characters. There are no hidden fees, no subscriptions, and no volume commitments. This flat rate makes it easy to predict costs for entire school districts or individual classrooms without worrying about sudden price hikes.
- Flat rate of $0.01 per 1,000 characters
- No monthly minimums or commitment contracts
- Balance does not expire
Pay only for what you use
You only pay for successful generations. If a request fails, the charge is returned in full. This ensures your school budget is spent strictly on usable audio files, whether you are generating short phonics exercises or full-length reading materials.
- Failed requests are free
- Pay per character, not per second
- Start with a $0.50 free trial
Simple REST API integration
Our API follows the standard OpenAI shape, meaning you can use existing OpenAI SDKs by simply changing the base URL. This reduces the learning curve for your technical staff and allows for quick integration into your existing digital teaching platforms.
- Standard POST /v1/audio/speech endpoint
- Compatible with official OpenAI SDKs
- Supports mp3, wav, opus, flac, and pcm formats
High-Quality Voices for Classroom Materials
VocalRead provides eight distinct voice presets designed specifically for educational content, ensuring your audio lessons sound professional and engaging. Whether you are creating storybooks or instructional guides, you can select the perfect tone for your audience.
Warm narrators for storytime
For reading materials and storytime sessions, use Aria for a warm, clear narration or Luna for a soft, storytelling feel. These voices create an inviting atmosphere that keeps students engaged without sounding artificial.
Clear voices for instructions
Instructional content benefits from Sage’s calm, instructional tone or Milo’s friendly, conversational style. They deliver clear directions for classroom activities, ensuring students understand tasks without ambiguity.
- Sage: Calm, instructional tone for step-by-step guides
- Milo: Friendly, conversational style for daily routines
Natural-sounding speech patterns
All voices are based on licensed recordings from LibriVox, providing natural speech patterns. Each generated file includes an inaudible watermark to mark it as synthetic speech, maintaining transparency.
Support for 23 Languages
VocalRead supports 23 languages, including English, Spanish, French, German, Japanese, and Arabic. This allows teachers to create diverse reading materials without needing separate services for each language. Every voice can speak any of these languages, ensuring consistent audio quality across your curriculum.
The API guesses the language from the text script, defaulting to English for Latin text, so you do not need to manually specify it for most cases. For non-English Latin-script text, you can set the language parameter explicitly. Unsupported languages like Vietnamese or Thai are clearly listed, so you know exactly what works.
English, Spanish, French, and more
Our API covers 23 languages, from widely taught ones like English and Spanish to others like Greek, Swahili, and Turkish. This range lets methodologists produce audio lessons for multilingual classrooms or language learning resources without switching providers.
Each voice maintains its character regardless of the language spoken. Whether you need a warm narrator for storytime or a calm voice for instructions, the tone remains consistent across all supported languages.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic language detection
The API guesses the language from the script, defaulting to English for Latin text. This simplifies integration for teachers who generate content quickly.
If the guess is incorrect, you can explicitly set the language field using the ISO code. This ensures accurate pronunciation for less common language combinations.
Consistent quality across languages
All 8 voices are based on licensed recordings and deliver high-quality synthetic speech in any supported language. The audio engine ensures natural speech patterns, making listening materials engaging for students.
Since every voice can speak any of the 23 languages, you can maintain a consistent auditory experience across different subjects and languages in your school’s digital library.
Easy Integration for Methodologists
Methodologists can integrate VocalRead immediately using standard OpenAI SDKs. Simply change the base_url to https://api.playd06.com/v1 and use your API key. This allows you to leverage familiar code structures without learning a new library.
Works with OpenAI SDKs
The API mimics the OpenAI speech endpoint shape. You can use official OpenAI SDKs by pointing them to our base URL. This reduces development time for technical staff creating audio lesson plans.
- Compatible with official OpenAI SDKs
- Standard JSON request body
- Easy
base_urlconfiguration
Simple curl commands
Test the service instantly with a single command. The /get-api-key/ page provides ready-to-use examples. Send text and receive audio files without complex authentication headers.
- Copy-paste ready examples
- Direct HTTP POST requests
- Audio response
Fast audio generation
Generate audio files quickly. Short phrases take just a few seconds. Longer texts are processed at roughly real-time speed, allowing for efficient batch creation of reading materials.
- Seconds for short phrases
- Real-time speed for long texts
- Sequential processing ensures consistency
Transparent Pricing for Schools
Our pricing is straightforward: $10 per million characters, which equals just $0.01 per 1,000 characters. This flat rate makes it easy to budget for audio lessons without worrying about complex tiers or unexpected overages.
$10 per million characters
Every character counts, including spaces and punctuation. This simple metric means you only pay for the text you actually convert, making it highly affordable for generating extensive reading materials or short classroom instructions.
No hidden fees
There are no monthly plans, seats, or minimum spend requirements. Failed requests are free, so you never pay for errors. Balance does not expire, allowing you to top up only when needed.
- No subscriptions or enterprise contracts
- Failed requests are refunded instantly
- Balance never expires
Free trial for new accounts
Start with $0.50 of credit (about 50,000 characters) valid for 7 days when you sign in with Google. This lets you test voice quality and integration before committing to any top-up.

Reliable and Fast
Synthesis typically runs at roughly real-time speed, processing about 25 characters per second. While short phrases take a few seconds to generate, longer texts are split into parts and joined seamlessly. Requests are processed in sequence, so under heavy load, you may experience brief queueing.
Real-time generation
Standard generation delivers audio at a pace comparable to natural speech. For short phrases, expect a few seconds of latency. Longer texts are split into 4096-character chunks and stitched together automatically.
- ~25 characters generated per second of audio
- Sequential processing may cause brief waits under load
- Split-and-join workflow ensures no data loss
Multiple format support
Receive audio in mp3, wav, opus, flac, or pcm formats to suit different classroom devices. Choose the codec that best fits your teaching platform or hardware requirements without losing quality.
- mp3, wav, opus, flac, pcm
- Optimized for various classroom devices
Standard API endpoints
Use the familiar POST endpoint at /v1/audio/speech with a JSON body. It mirrors the OpenAI speech structure, so you can reuse existing code. Simply update your base URL to https://api.playd06.com/v1.
- POST /v1/audio/speech
- JSON body compatible with OpenAI SDKs
- Base URL: https://api.playd06.com/v1
Data Privacy for Students
We prioritize your students' data privacy by ensuring that input text is used solely for the immediate production of audio files. Input text is used only to produce the audio and is not used for training. This guarantees that the specific stories, exercises, and reading materials you upload remain private and are not ingested into any public training datasets.
Generated audio is returned in the response and not stored. We retain only the essential request metadata—such as timestamp, character count, and status—strictly for billing and usage verification purposes. This minimal data approach ensures that your educational content remains transient and secure.
Text not used for training
Our API processes your text exclusively for synthesis. We do not harvest or reuse your classroom materials to train our models, keeping your educational resources distinct from our training data.
No long-term storage
Generated audio is returned in the response and not stored on our servers. We keep only minimal request metadata (time, characters, status) necessary for accurate billing and service verification.
Secure API keys
Each account is secured with a unique Bearer token. You can issue a new key at any time, instantly invalidating the previous one to prevent unauthorized access to your usage and balance.
Get Started Today
Creating audio lessons has never been simpler. Start by signing up with your Google account to receive a free trial balance of $0.50. This gives you 50,000 characters to test the voices without any credit card details or enterprise contracts.
Once registered, your unique API key appears instantly on your dashboard. You can generate your first audio file immediately using the ready-made curl example or the OpenAI SDK. No complex onboarding or waiting periods—just access to reliable synthetic speech for your classroom materials.
Sign up with Google
Visit the /get-api-key/ page and click the Google sign-in button. Within seconds, your account is created with a $0.50 trial credit valid for seven days. This allows you to explore the 8 voice presets and 23 languages.
Get your API key instantly
After signing in, your dashboard displays your active API key immediately. Copy this key to use in your requests. You can also view your current balance, character usage, and a pre-configured curl command ready to paste into your terminal.
Start generating audio
Use the provided curl example or integrate with the OpenAI SDK by changing the base URL to https://api.playd06.com/v1. Send your lesson text via a POST request to /v1/audio/speech and receive an audio file. Top up with USDT (TRC-20) anytime you need more characters.
- POST https://api.playd06.com/v1/audio/speech
- Supports mp3, wav, opus, flac, and pcm formats
- 60 requests per minute standard limit
Compare Features
Comparing TTS providers helps schools choose the right balance of cost and quality. While major platforms offer enterprise-grade features, they often come with complex pricing tiers and hidden costs that don't fit educational budgets.
Our API simplifies this by offering a flat rate of $10 per million characters with no minimum spend. This transparency makes it easier for methodologists to predict costs for entire reading materials without worrying about tiered usage limits.
Vs Amazon Polly
Amazon Polly requires managing multiple voices and complex SSML tags for nuanced reading. Our API offers eight high-quality presets that sound natural out-of-the-box, with automatic language detection removing the need for manual configuration.
- No SSML required for basic use
- Simple REST API instead of complex XML
- Flat rate vs. tiered pricing
Vs Google TTS
Google TTS often requires significant setup to achieve natural-sounding results. Our voices, based on licensed recordings, deliver clear, warm narration suitable for classrooms immediately. You get high-quality audio with just a simple text input.
- Pre-tuned for clarity
- No neural voice training needed
- Instant generation
Vs ElevenLabs
ElevenLabs offers advanced features like voice cloning, but at a higher price point. Our $0.01 per 1,000 characters is significantly more affordable for bulk lesson generation. You get reliable, watermark-secured audio without the enterprise contract.
- $0.01 per 1k chars
- No cloning required
- No enterprise contracts
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. However, its pricing structure can become complex and expensive as usage scales, often requiring careful monitoring to avoid unexpected costs.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriVox public-domain audiobooks
- Creative Commons Attribution 4.0
- TRON developer hub: TRC-20
- openai-python on GitHub
- IETF RFC 7845: Ogg Opus
- W3C WAI: making audio and video accessible
- curl documentation
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
- Python documentation
- LibriTTS-R paper (arXiv 2305.18802)
