The Simple TTS API Key for Teachers and Product Teams

By VoiceClass editorial team · Updated 2026-11-19

This page explains how VoiceClass provides a straightforward text-to-speech API designed for teachers and product teams building accessible audio content for schools. You will find clear details on integration using standard OpenAI SDKs, affordable pricing based on character count, and eight distinct voice presets suitable for classroom instruction.

We cover practical workflows, from signing up with a Google account to generating your first audio file. Whether you need support for 23 languages or simple rate limits for educational projects, this guide helps you integrate TTS into your curriculum or product with clarity and affordability.

The Simple TTS API Key for Teachers and Product Teams

Frequently asked questions

What is a TTS API key?

A TTS API key is a unique credential used to authenticate your requests to our text-to-speech endpoint. You use it by including it in the Authorization header as a Bearer token. Each account holds one active key, which can be regenerated at any time, immediately invalidating the previous one.

How do I get a TTS API key?

Visit our /get-api-key/ page to sign up using Google or an email and password. Once registered, your dashboard displays your API key, balance, and usage details. You can start sending requests immediately. The key is tied to your specific account on this site.

What is the Google Speech API?

The Google Speech-to-Text API is a separate service provided by Google for converting spoken audio into text. It is a distinct product from our VoiceClass platform. While both services handle audio, they operate on different infrastructure, pricing models, and voice technologies.

How does the TTS API differ from Google Speech?

Our API uses a simple POST endpoint compatible with OpenAI SDKs, whereas Google Speech-to-Text has its own specific protocols. We offer eight distinct voice presets and support 23 languages. Our pricing is character-based at $0.01 per 1,000 characters, with no monthly subscriptions or complex tier structures.

What is the cost of the TTS API?

The cost is $10 per 1 million characters. Failed requests are free, with charges returned in full. You can top up using USDT on the TRON network, starting at a minimum of $5. There are no monthly plans, seats, or minimum spending requirements.

How much does the TTS API cost per character?

The rate is $0.01 per 1,000 characters. Spaces and punctuation count toward this total. For example, generating 10,000 characters costs $0.10. This simple metric makes budgeting easy for schools and product teams without hidden fees for processing time or voice selection.

Are there any free trials available?

Yes, signing in with Google provides $0.50 of credit, valid for 7 days, allowing about 50,000 characters. Accounts created with email and password do not receive trial credit. You can use this to test integration before adding funds via USDT.

Which languages are supported?

We support 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. Vietnamese, Indonesian, and Thai are not supported.

Can I use the API for multiple languages?

Yes, any of the eight voices can speak any of the 23 supported languages. You can specify the language via an optional ISO code in the request. If omitted, the system guesses the language from the script, defaulting to English for Latin text.

What voices are available?

We offer eight presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). Voices are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark marking it as synthetic speech.

How many voices can I choose from?

You can choose from exactly eight voice presets. These include four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). Each voice has a distinct tone, from warm narration to deep documentary styles, suitable for various classroom materials.

Can I change voices after generating audio?

No, the voice is determined at the time of the request. Once the audio file is generated and returned, the voice is fixed. To use a different voice, you must send a new request with the desired voice parameter in the JSON body.

What are the rate limits?

You are limited to 60 requests per minute per key. Before your first top-up, this limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts are split into parts of up to 4,096 characters.

How many requests can I make per minute?

You can make 60 requests per minute with a funded account. New accounts without a top-up are limited to 10 requests per minute. This ensures fair usage. If you exceed the limit, requests may be delayed until the queue clears.

First request

curl

curl https://api.6wins.info/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.mp3

Why Choose This TTS API for Education?

Sound wave illustration for: Why Choose This TTS API for Education?

This API integrates directly with tools teachers and product teams already use. By adjusting the base URL, you can leverage familiar OpenAI SDKs to generate audio files without learning a new system.

Costs are straightforward: $0.01 per 1,000 characters. There are no monthly plans or hidden fees, making it easy to budget for classroom resources or student projects.

Generated audio features clear voices suitable for educational content. The system handles text processing efficiently, ensuring reliable output for learning materials.

Easy Integration with OpenAI SDKs

Easy Integration with OpenAI SDKs

Connect using standard libraries by simply changing the base_url to https://api.6wins.info/v1. This allows immediate use of existing codebases and developer workflows without significant refactoring.

The endpoint structure mirrors the OpenAI speech endpoint, ensuring a smooth transition for teams familiar with standard TTS implementations.

  • Compatible with official OpenAI SDKs
  • Standard JSON request format
  • Minimal code changes required

Affordable Pricing for Schools

Pay only for what you use at $10 per million characters. Failed requests are free, protecting your budget from unexpected errors.

Start with a $0.50 trial credit when signing in with Google, allowing immediate testing without financial commitment.

  • No monthly subscriptions
  • $0.01 per 1,000 characters
  • Free failed requests

Clear, Natural Voice Options

Choose from eight distinct voice presets, including warm narrators and calm instructional tones. Each voice is designed for clarity, ensuring students can easily follow audio content.

Voices are based on licensed recordings, providing high-quality audio suitable for both individual study and classroom presentations.

  • 8 distinct voice presets
  • Licensed audio recordings
  • Optimized for clarity

Key Features for Classroom Use

Sound wave illustration for: Key Features for Classroom Use

Our platform is built for educators and product teams who need reliable audio content without complex infrastructure. We focus on clarity and ease of integration, allowing you to generate high-quality speech files that fit seamlessly into learning modules or classroom resources.

Support for 23 Languages

Generate content in 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, making it easy to create diverse educational materials.

8 Distinct Voice Presets

Choose from eight licensed voice presets based on LibriTTS-R and LibriVox recordings. Select female voices like Aria for clear narration or Luna for storytelling, or male voices like Atlas for neutral news or Orion for documentary-style content. Each voice offers a distinct tone suitable for different teaching styles.

Audio Generation Speed

Long texts are processed at roughly real-time speed (about 25 characters per second). Short phrases may take a few seconds to generate. Requests are processed in order, so under load, a request may wait in a queue, but the output is always delivered as a complete audio file.

How It Works: Simple Steps

Sound wave illustration for: How It Works: Simple Steps

Getting started takes just minutes. Create your account via /get-api-key/ using Google or email, then access your unique API key and initial trial credit immediately.

The workflow is straightforward: send text via our API and receive audio files ready for your classroom or app, with no complex setup required.

Sign Up and Get Your API Key

Visit /get-api-key/ to register with Google or email. Upon signing in, you receive your API key and $0.50 in trial credit, valid for 7 days.

  • Google or email registration
  • Instant API key generation
  • $0.50 free trial credit

Send Text and Receive Audio

Submit text up to 4096 characters via POST request. The API returns an audio file in your chosen format (mp3, wav, etc.) within seconds.

  • Simple JSON request
  • Multiple output formats
  • Audio delivery in seconds

Use Pre-built Examples

Start with ready-to-use curl examples on the dashboard. Modify parameters like voice, speed, and format to suit your specific educational content needs.

  • Copy-paste curl commands
  • Adjustable voice and speed
  • No custom SDK required

Voices That Educate

Sound wave illustration for: Voices That Educate

The right voice transforms dry text into engaging learning material. Our eight presets are designed for clarity, ensuring students and product users hear every word distinctly without distraction.

Each voice carries a specific tone, from warm narration to energetic announcements. This variety helps teachers match audio content to the lesson's mood, making educational materials more accessible and enjoyable for diverse classrooms.

Female Voices: Aria, Nova, Luna, Sage

Aria offers a warm, clear narration style ideal for history lessons. Nova brings a bright, upbeat energy suitable for quick updates. Luna provides a soft, storytelling tone for reading sessions, while Sage delivers a calm, instructional voice perfect for step-by-step guides.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Male Voices: Felix, Milo, Atlas, Orion

Felix is energetic and great for promotional content or announcements. Milo sounds friendly and conversational, suitable for casual explanations. Atlas provides a neutral, news-like tone for factual data, and Orion offers a deep, documentary style for serious topics.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Voice Selection for Different Content

Match voice to content type for better retention. Use Sage for technical instructions or Luna for storytime. For quick quizzes or announcements, Nova or Felix keep students engaged. Atlas works well for reading news or factual updates clearly.

Languages Supported

Sound wave illustration for: Languages Supported

VoiceClass supports 23 languages, including English, Spanish, French, German, Chinese, and Japanese. This range covers the majority of classroom needs, from literature reading to language learning exercises.

Major World Languages

We support Arabic, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Each voice can speak any of these languages.

Automatic Language Detection

If you do not specify a language, the API guesses it from the script. Latin script text defaults to English. This works well for single-language content but may fail for mixed scripts.

Manual Language Setting

For non-English Latin-script text, set the language field explicitly. This ensures accurate pronunciation. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.

  • Set language for mixed-language texts.
  • Default is English for Latin script.
  • Check the /v1/voices endpoint for the full list.
Languages Supported

Pricing Overview

Sound wave illustration for: Pricing Overview

Our pricing is straightforward: $10 per million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful audio generation.

Pay Per Character

There are no monthly plans, seats, or minimum spends. You pay only for what you use, making it easy to budget for classroom projects or product features.

Free Trial with Google Login

Sign in with Google to receive $0.50 in trial credit, valid for 7 days. This provides about 50,000 characters to test the API before committing.

USDT Top-Up Options

Top up your balance using USDT on the TRON network (TRC-20). The minimum deposit is $5, and funds are credited automatically within minutes. Balance never expires.

Technical Details for Developers

Sound wave illustration for: Technical Details for Developers

Integration is straightforward for developers familiar with standard HTTP clients. You send a JSON payload to the speech endpoint, and the API returns the generated audio file directly in the response, ensuring seamless integration into existing educational platforms or classroom management systems.

The system supports audio formats including MP3, WAV, OPUS, FLAC, and PCM, with speed adjustment options ranging from 0.25 to 4.0. This allows teachers to tailor the listening experience for different age groups or language learners without needing complex post-processing tools.

Endpoint: POST /v1/audio/speech

Send your request to https://api.6wins.info/v1/audio/speech using the HTTP POST method. The endpoint accepts a JSON body containing the text input, voice selection, and desired output format. Authentication is handled via a Bearer token in the Authorization header.

Request Format and Fields

The JSON body requires the input text (up to 4096 characters), a voice preset from our eight options, and a model choice of either "tts-1" or "tts-1-hd". You can also specify response_format (mp3, wav, opus, flac, pcm) and an optional language ISO code to override automatic detection.

  • model: "tts-1" or "tts-1-hd"
  • input: string, max 4096 characters
  • voice: one of 8 presets
  • response_format: mp3, wav, opus, flac, pcm
  • speed: 0.25–4.0
  • language: optional ISO code

Rate Limits and Queues

Your API key allows 60 requests per minute once funded, or 10 per minute during the free trial phase. Requests are processed sequentially, meaning longer texts or high volume may enter a brief queue. Failed requests incur no charge, and audio is returned in the response.

Data Privacy and Usage

Sound wave illustration for: Data Privacy and Usage

We prioritize your data’s integrity in educational settings. The text you send to generate speech is processed solely to create the audio file. It is not ingested into our models or used to improve our training datasets, ensuring your lesson plans and student materials remain private.

Input Text Not Used for Training

Your input text is used exclusively for the immediate synthesis task. We do not use your input text for training.

Audio Not Stored After Generation

Once the audio file is generated and delivered to your application via the API response, it is not stored on our servers. This ensures that your final audio products remain under your control, without lingering copies in our infrastructure.

Billing Metadata Retained

We keep only the necessary metadata for billing purposes: the time of the request, the character count, and the status. This minimal record allows for accurate invoicing and troubleshooting without storing the actual audio or text content.

Getting Started Today

Sound wave illustration for: Getting Started Today

Start by visiting the /get-api-key/ page and signing up with your Google account or email. You will immediately receive an API key, a balance of $0.50 for trial, and a ready-to-use cURL example to test the connection.

Once you have your key, you are ready to generate audio. Send a short text request to the API endpoint, and receive an audio file in seconds. This simple workflow allows you to create classroom materials or product demos without complex setup.

Create an Account

Visit the /get-api-key/ page to create your account. You can sign in using Google for immediate access to your trial credit, or use a standard email and password. Your account dashboard displays your API key, current balance, and usage statistics.

Accounts are specific to this site, so ensure you are on 6wins.info. No credit card is required to start, and you can issue a new key at any time if needed.

  • Sign up via Google or email/password
  • Immediate access to $0.50 trial credit
  • Dashboard shows key, balance, and usage

Generate Your First Audio File

Use the provided cURL example or the OpenAI SDK to send a POST request to the API endpoint. Include your text, select a voice like 'Aria' for narration, and choose a format like MP3. The system processes the request and returns the audio file directly.

Remember that requests are processed sequentially, so longer texts may take a few seconds. Failed requests are free, ensuring you only pay for successful audio generation.

  • Use POST /v1/audio/speech endpoint
  • Select voice and response format
  • Receive audio file directly in response

Explore the Documentation

Visit the /docs/ page for detailed information on request fields, rate limits, and supported languages. The documentation includes examples for various programming languages and explains how to handle text splitting for longer content.

You can also check the /pricing/ page to understand character costs and the /about/ page to learn more about our mission to support educators and product teams.

  • Detailed API reference and examples
  • Rate limit and language details
  • Pricing and account management info

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This efficiency supports high-volume reading assignments without breaking the department budget.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. MDN: Web Speech API
  3. LibriTTS-R corpus (OpenSLR 141)
  4. openai-node on GitHub
  5. Python documentation
  6. Creative Commons Attribution 4.0
  7. LibriTTS-R paper (arXiv 2305.18802)
  8. OpenAI API reference: create speech
  9. W3C WAI: making audio and video accessible
  10. openai-python on GitHub
  11. curl documentation
  12. TRON developer hub: TRC-20

More on this site