Frequently asked questions
What is a TTS API?
A text-to-speech API is a cloud service where you send text and receive an audio file. Our endpoint is POST https://api.6wins.info/v1/audio/speech. It uses the same request shape as OpenAI, so official OpenAI SDKs work by changing the base_url. You simply provide text, a voice, and format to get synthesized speech.
How does text-to-speech work?
You send a POST request with your text and voice selection to the API. The server processes the request and returns an audio file in formats like mp3, wav, opus, flac, or pcm. Each request handles up to 4096 characters. For longer texts, split them into parts and join the resulting audio files.
What is synthetic speech?
Synthetic speech is audio generated by a computer algorithm rather than recorded by a human. Every file we generate carries an inaudible watermark marking it as synthetic. This ensures transparency about the audio source while maintaining high clarity and natural flow suitable for educational and product content.
What is the difference between TTS and STT?
TTS (Text-to-Speech) converts written text into audio files. STT (Speech-to-Text) converts spoken audio into written text. Our platform focuses exclusively on TTS. We do not offer speech-to-text, translation, or dubbing pipelines. Use our API when you need to turn text into audible speech.
What is STT?
STT stands for Speech-to-Text, the process of converting spoken audio into written text. Our product is a Text-to-Speech API, so we do not offer STT features. If you need to transcribe audio, you will need a different service. We specialize in generating clear audio from your text inputs.
How do I convert text to speech?
Send a POST request to https://api.6wins.info/v1/audio/speech with your text, voice, and format. Use the OpenAI SDK by changing the base_url. Include your API key in the Authorization header. The API returns the audio file directly. You can adjust speed and language for precise control over the output.
What are the benefits of TTS?
TTS provides accessible audio content quickly and affordably. Our API is developer-friendly, integrating easily with existing workflows. You pay only for characters used, with no monthly plans. Failed requests are free. This makes it ideal for schools and product teams needing scalable, clear audio without complex infrastructure or subscriptions.
Is TTS realistic?
Our voices are based on licensed recordings from LibriTTS-R and LibriVox, offering warm, clear, and natural-sounding speech. Every file includes an inaudible watermark marking it as synthetic. The quality is suitable for educational narration and product demos, providing clarity without the need for human recording sessions.
What voices are available?
We offer eight presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). Each has a distinct tone, from warm narrator to deep documentary. Any voice can speak any of our 23 supported languages. You select the voice that best fits your content's mood and audience.
How many 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. Set the language parameter for non-English Latin-script text to ensure accuracy.
What is the API endpoint?
The main endpoint is POST https://api.6wins.info/v1/audio/speech. You also have GET /v1/voices to list voices and GET /v1/models. The request shape matches OpenAI’s speech endpoint. This allows you to use official OpenAI SDKs by simply changing the base_url to https://api.6wins.info/v1 for easy integration.
How do I get an API key?
Sign up on https://6wins.info/get-api-key/ using Google or email. Your account page displays your API key, balance, and usage. You can issue a new key at any time, which immediately invalidates the old one. Keys start with 'tts-' and are used for authentication in your API requests.
What is authentication?
Authentication uses a Bearer token in the Authorization header. Include your API key (starting with 'tts-') in every request. Each account has one active key. You can generate a new key anytime via your account page; the old key stops working immediately, ensuring secure access to your credits and data.
What are rate limits?
You are limited to 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load a request may wait in a queue. Longer texts take time proportional to length. Split texts over 4096 characters into parts to manage processing efficiently.
How much does it cost?
Pricing is $10 per 1 million characters ($0.01 per 1,000 characters). Spaces and punctuation count. Failed requests are free. Top-ups are via USDT (TRC-20) on the TRON network, minimum $5. No monthly plans or subscriptions. Balance does not expire. You pay only for what you generate successfully.
Is there a free trial?
Yes, signing in with Google gives $0.50 credit (about 50,000 characters) valid for 7 days. Email/password accounts start without trial credit. You can top up with USDT anytime. Failed requests do not consume credit. This allows you to test integration and voice quality before committing to larger usage.
Understanding Text-to-Speech Technology
Text-to-Speech (TTS) technology transforms written content into audible speech, allowing educators and product teams to convert lesson plans, articles, or documentation into listenable formats without hiring voice actors. This process enables asynchronous learning and improves accessibility for students with reading difficulties or visual impairments.
When you send text to the VoiceClass API, the system processes the input through a neural engine that synthesizes human-like speech. The result is a downloadable audio file, ready for integration into learning management systems or classroom materials.
What is TTS?
TTS is a cloud-based service that accepts plain text and returns an audio file. It removes the need for recording studios, allowing teachers to generate audio on demand. The service supports 23 languages, ensuring materials can be localized for diverse classrooms.
- Converts text to spoken audio instantly
- Supports 23 languages including English, Spanish, and Chinese
- Works with standard text inputs like lesson plans or articles
How Text Becomes Audio
The API uses a neural network to analyze your input. It determines phonemes, intonation, and pacing based on the selected voice preset. The engine generates the audio file, handling punctuation and sentence structure naturally.
- Neural network processes input text
- Analyzes phonemes and intonation patterns
- Generates audio waveform instantly
Synthetic Speech Basics
VoiceClass uses voices derived from licensed recordings (LibriTTS-R) and public-domain audiobooks. Each generated file contains an inaudible watermark identifying it as synthetic. This ensures transparency while maintaining high-quality, natural-sounding speech for educational content.
- Based on licensed LibriTTS-R recordings
- Inaudible watermark marks synthetic speech
- Natural intonation and pacing
How the API Works
VoiceClass simplifies audio generation by handling the complex conversion of text into synthetic speech. You send a simple HTTP request with your text and voice preference, and our cloud infrastructure processes it to produce high-quality audio files ready for immediate use in your educational materials or classroom projects.
Sending Text to the API
To generate audio, send a POST request to https://api.6wins.info/v1/audio/speech. Include your text (up to 4096 characters), a voice preset like 'aria' or 'atlas', and your authentication key. You can also specify the response format (mp3, wav, etc.) and speed.
- Endpoint:
POST https://api.6wins.info/v1/audio/speech - Input: JSON body with
model,input,voice, andresponse_format
Receiving Audio Files
The API returns the generated audio file directly in the response body. Depending on your chosen format, you receive an MP3, WAV, FLAC, or PCM file. For texts exceeding 4096 characters, split the input into parts, generate each part, and join the resulting audio files.
Request and Response Cycle
Each request is processed sequentially. Typical generation speed is roughly real-time (25 characters per second), though short phrases may take a few seconds. Requests are queued under load, so processing time depends on current traffic. Failed requests incur no charge.
- Rate limit: 60 requests per minute per key
- Processing: Sequential, queued under load
Key Components of a TTS API
A TTS API relies on a clear structure to transform written words into spoken audio. The core components include the API endpoint, authentication, and the specific parameters that define how your text is processed and delivered.
Understanding these elements ensures smooth integration for educational tools and classroom resources, allowing teachers and developers to generate audio efficiently without unnecessary complexity.
API Endpoint and Method
All requests are sent via HTTP POST to https://api.6wins.info/v1/audio/speech. This endpoint accepts JSON bodies containing your text and voice settings, returning the generated audio file directly in the response.
The structure mirrors standard TTS APIs, making it easy to integrate with existing educational software or custom classroom tools.
- Endpoint: POST https://api.6wins.info/v1/audio/speech
- Method: HTTP POST
- Format: JSON request, audio response
Authentication Mechanism
Access is secured using a Bearer token. Include your API key in the request header as: Authorization: Bearer tts-... . Each account has one active key at a time, ensuring clear usage tracking for schools and teams.
If you need a fresh key, you can issue a new one at any time, and the previous one stops immediately.
- Header: Authorization: Bearer tts-...
- One active key per account
- Instant key rotation supported
Input and Output Parameters
You send text (up to 4096 characters) along with voice selection and format preferences. The API returns the audio file in your chosen format, such as MP3, WAV, or OPUS.
Parameters like speed (0.25–4.0) and optional language codes allow fine-tuning for specific educational contexts, from language learning to accessible reading materials.
- Input: JSON with text, voice, format
- Output: Audio file (mp3, wav, etc.)
- Limits: 4096 chars per request
Voices and Languages
Our platform provides eight distinct voice presets, each crafted for specific tones like narration, instruction, or conversation. Whether you need the warm clarity of Aria for educational stories or the energetic delivery of Felix for promo content, every voice supports all 23 available languages. You can also adjust speech speed between 0.25x and 4.0x to match your audience's pace.
Each voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring high quality without the need for custom cloning. The system automatically detects the language from the script, but you can explicitly set the ISO code for non-English Latin text to ensure accurate pronunciation.
Voice Presets Explained
We offer eight presets categorized by tone. Female voices include Aria (warm narrator), Nova (upbeat), Luna (storytelling), and Sage (instructional). Male options feature Felix (energetic), Milo (conversational), Atlas (neutral news), and Orion (deep documentary). These voices are based on licensed recordings, ensuring consistent quality across all projects.
All voices support the full range of 23 languages, allowing you to maintain a consistent audio style even when switching languages. You can fine-tune the output by adjusting the speed parameter, making it easier for students to follow along with complex material.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Language Support and Detection
The API supports 23 languages, including Arabic, Chinese, English, French, German, Hindi, Japanese, Korean, Spanish, and more. It automatically detects the language from the script, defaulting to English for Latin-script text. For other languages using Latin characters, you should explicitly set the language parameter to avoid mispronunciation.
Languages not currently supported include Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali. This ensures that we only deliver high-quality synthesis for languages we have thoroughly tested and optimized for educational and product use cases.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Choosing the Right Voice
Select a voice that matches the tone of your content. Use Sage for instructional materials, Aria for storytelling, or Atlas for neutral updates. You can test different voices by sending short text samples via the API and listening to the resulting audio files. Adjusting the speed parameter also helps tailor the audio to your specific audience's needs.
Remember that every generated file carries an inaudible watermark marking it as synthetic speech. This is standard practice for TTS services and ensures transparency while maintaining the natural flow of the audio for your users.
Pricing and Usage
VoiceClass offers a straightforward, volume-based pricing model designed for educational institutions and product teams. There are no monthly subscriptions, seat licenses, or minimum spend requirements, allowing you to pay only for what you actually use. The standard rate is $10 per 1 million characters, which equates to $0.01 per 1,000 characters. Spaces and punctuation are counted as characters in this calculation, ensuring transparent billing.
Failed synthesis requests are free, so you are never charged for audio that fails to generate. This structure supports variable classroom usage or sporadic product updates without financial risk. You can top up your balance anytime via USDT on the TRON network (TRC-20), with a minimum deposit of $5. Credits are credited automatically within minutes, and your balance never expires.
Cost Structure
The cost is strictly proportional to input length. At $0.01 per 1,000 characters, generating a 4,000-character lesson takes approximately $0.04. This linear scaling makes it easy to predict costs for long-term projects like audiobook production or extensive accessibility libraries.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free
Free Trial Details
New accounts created with Google sign-in receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters of usage, sufficient for testing multiple voices and formats. Accounts created via email and password do not receive this initial trial credit.
- $0.50 trial credit for Google sign-ins
- Approximately 50,000 characters
- Valid for 7 days
- Email/password accounts start without credit
Monitoring Usage
Your dashboard displays your current balance, remaining characters, and usage history. You can issue a new API key at any time, which immediately invalidates the old one, helping you manage access across different teams or projects. Rate limits apply at 60 requests per minute per key, ensuring fair usage during peak teaching hours.
- View balance and character count
- Issue new keys anytime
- 60 requests per minute limit
- Automatic credit via USDT
Integration Methods
Integrating VoiceClass is straightforward whether you prefer command-line tools or code. You can generate audio instantly using simple cURL commands or leverage familiar libraries for seamless application development.
cURL Requests
Use cURL for quick testing. Send a POST request to the API endpoint with your JSON payload, including the model, voice, and text. The API returns the audio file directly.
- Use
POST https://api.6wins.info/v1/audio/speech - Include
Authorization: Bearer tts-...header
OpenAI SDK Integration
The API mirrors the OpenAI speech endpoint structure. Update your SDK’s base_url to https://api.6wins.info/v1 and use your VoiceClass key. Existing OpenAI code works with minimal changes.
- Set
base_urltohttps://api.6wins.info/v1 - Use standard OpenAI SDK clients
Manual HTTP Requests
For custom integrations, send standard HTTP POST requests. Ensure your JSON body contains the required fields like model, input, and voice. The response delivers the audio file in your chosen format.

Data Privacy and Security
VoiceClass treats your data with clarity and minimal retention. We do not hoard your content, ensuring that your educational materials remain yours. Our architecture is designed for simplicity, avoiding complex data silos that complicate privacy audits for school IT teams.
When you send text, it is processed solely to generate the audio file you request. Once the audio is delivered, the input text is not stored for long-term use, nor is it used to train our models. This ensures that student readings or teacher notes stay private.
Input Text Usage
Your input text is used exclusively for the immediate synthesis of the audio file. We do not retain the text after generation for training purposes, meaning your curriculum content remains distinct from our model development data. This separation ensures that sensitive student information or proprietary teaching materials are not ingested into our training sets.
Audio Storage Policy
Generated audio is returned directly in the API response and is not stored on our servers after delivery. You are responsible for storing the resulting audio files on your own infrastructure or LMS. This gives your school full control over where the audio lives and how long it is kept.
Metadata Retention
We keep request metadata—such as timestamp, character count, and status—for billing and usage verification only. This minimal data allows us to ensure accurate charging and helps you monitor API usage within your classroom or product team. No other personal data is retained beyond what is necessary for service operation.
Common Use Cases in Education
Educators can transform static textbooks into engaging audio content for students with dyslexia or visual impairments. By sending chapter text to the API, teachers generate clear, natural-sounding narrations using voices like Luna for storytelling or Sage for instructional content.
This workflow supports differentiated learning without requiring recording studios. Students listen to high-quality audio versions of course materials, improving comprehension and allowing review during commutes or downtime.
Creating Audiobooks
Teachers can convert entire chapters into audio files for classroom libraries. Using the tts-1 model, texts are processed efficiently; for longer books, you must split the text into segments.
The resulting audio files are ready for distribution via LMS platforms or classroom devices. With a voice like Aria, the narration remains warm and clear, keeping students engaged with classic or modern literature.
- Convert PDF or plain text chapters to audio
- Use Luna for storytelling or Sage for instructions
- Distribute via standard audio players
Audio for Accessibility
The API provides MP3, WAV, and OPUS formats suitable for various assistive technologies. Synthetic speech carries an inaudible watermark, ensuring content is clearly identified as generated, which aids in transparency.
Students can adjust playback speed using the API’s speed parameter, ranging from 0.25x to 4.0x, allowing personalized listening speeds for better retention and comprehension.
- Support for MP3, WAV, OPUS, FLAC, PCM
- Adjustable speed from 0.25x to 4.0x
- Inaudible watermark for synthetic identification
Language Learning Tools
Educators can generate pronunciation examples in 23 supported languages, including Spanish, French, and German. Teachers input phrases and receive audio in seconds, helping students hear accurate native-like intonation.
Since any voice can speak any supported language, teachers can mix voices to demonstrate different accents or styles, enhancing auditory learning without needing multiple native speakers.
- Support for 23 languages including Spanish, French, German
- Any voice can speak any supported language
- Quick generation for pronunciation practice
Technical Requirements
Your infrastructure must support stable HTTP/HTTPS connectivity to send text payloads and receive audio files efficiently. Standard web servers and modern programming environments handle the required JSON requests without special hardware.
Internet Connection
Ensure your network allows outbound requests to api.6wins.info. Most standard firewalls permit this traffic on ports 80 and 443. A stable connection prevents timeouts during audio synthesis, especially for longer texts exceeding 4096 characters which require sequential processing.
- Outbound HTTPS access required.
- Standard ports 80 and 443.
- Stable connection prevents timeouts.
Software Dependencies
You need a standard HTTP client capable of sending JSON bodies and handling binary audio responses. The official OpenAI SDK works by pointing base_url to https://api.6wins.info/v1. Alternatively, any tool like curl or a simple script using requests or axios suffices.
- Standard HTTP client.
- OpenAI SDK compatible.
- curl or script-based tools.
Rate Limits Considerations
Each API key allows 60 requests per minute, or 10 per minute before your first top-up. Exceeding this limit returns a 429 error. For classrooms generating many audio files simultaneously, implement simple retry logic with exponential backoff to manage the queue effectively.
- 60 requests per minute per key.
- 10 requests/minute before top-up.
- Implement retry logic with backoff.
Troubleshooting Common Issues
When integrating VoiceClass, you may encounter predictable hurdles. Most issues resolve quickly without needing to wait for support, especially if you understand the API’s constraints regarding authentication, volume, and file formats.
Authentication Errors
Ensure your request includes the correct Authorization: Bearer tts-... header. Remember that each account has only one active key; issuing a new key immediately invalidates the old one. Verify your key matches the one shown on your /get-api-key/ dashboard.
- Check for trailing spaces in your key
- Regenerate key if lost; old key stops instantly
Rate Limit Exceeded
New accounts start with a limit of 10 requests per minute. After your first top-up, this increases to 60 requests per minute. If you exceed this, wait briefly before retrying. Failed requests do not count against your limit.
- New accounts: 10 req/min
- Post-top-up: 60 req/min
Audio Format Issues
Specify one of the supported formats: mp3, wav, opus, flac, or pcm. If you request an unsupported format, the API may return an error. Ensure your playback software supports the selected format, as some educational platforms default to MP3.
- Supported: mp3, wav, opus, flac, pcm
Future of TTS in Education
Synthetic speech continues to improve in naturalness, helping teachers create engaging audio lessons without recording their own voices. The consistent voice presets and multi-language support make it easier to produce accessible content for diverse classrooms.
As AI advances, educators can expect faster generation times and more nuanced voice options, making audio integration into daily teaching workflows even smoother and more reliable.
Trends in Synthetic Speech
Voice quality is steadily improving, allowing teachers to produce clear, human-like audio for lessons and readings. The ability to generate speech in multiple languages supports language learning and inclusive education.
The consistent engine behind tts-1 and tts-1-hd ensures predictable results, making it easier for educators to plan audio content without worrying about inconsistent voice outputs.
- Improved naturalness in voice output
- Consistent engine performance
- Multi-language support for diverse classrooms
Accessibility Improvements
TTS API empowers students with visual or reading difficulties to access text-based materials through audio. Teachers can quickly convert textbooks, worksheets, or announcements into listenable formats.
With voice presets like aria or luna, educators can choose tones that match the content, enhancing comprehension and engagement for students with different learning needs.
- Support for visual impairments
- Customizable voice tones
- Quick conversion of text to audio
Integration with Learning Platforms
The API’s simple request structure allows seamless integration with learning management systems. Educators can automate audio generation for lessons, quizzes, or notifications.
By using standard HTTP requests or OpenAI SDK, schools can embed TTS into existing digital tools without complex setup, saving time and technical resources.
- Easy API integration
- Automation of audio content
- Compatibility with existing LMS
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.
23 languages
Any voice speaks any of these languages.
