Frequently asked questions
How does this differ from Google GTTS python library?
This API uses the same request shape as OpenAI’s speech endpoint, allowing you to switch libraries easily by changing the base URL. It offers eight voice presets, multiple audio formats, and speed control. It is designed for scalable, programmatic integration into LMS platforms rather than simple local file generation.
What is the character limit per request?
Each API request accepts up to 4096 characters of input text. For longer course content, you should split the text into parts of this size and join the resulting audio files. This ensures consistent processing and allows for efficient handling of large educational materials within the API’s constraints.
Which voices support which languages?
All eight voice presets can speak any of the 23 supported languages. This includes English, Spanish, German, French, and many others. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text. You can explicitly set the language code for accuracy.
Can I use this for commercial courses?
Yes, the API is designed for scalable use in commercial environments like LMS platforms. Generated audio files are returned in the response and not stored by the provider. Input text is used only for synthesis and not for training, making it suitable for creating proprietary course content without licensing restrictions.
How do I authenticate in Python?
Authentication uses a Bearer token sent in the Authorization header. You can use the official OpenAI Python SDK by setting the base URL to https://api.t46.net/v1 and providing your API key. This allows you to leverage existing code structures while accessing our specific voice models and endpoints.
Is there a free trial available?
A free trial of $0.50 credit is available for accounts signed in with Google, valid for 7 days. This provides approximately 50,000 characters for testing. Accounts created with email and password do not receive this trial credit. The trial allows you to verify voice quality and integration before purchasing.
What audio formats are supported?
The API supports MP3, WAV, OPUS, FLAC, and PCM formats. You can specify the desired format in the request body. This flexibility allows you to choose the best balance between file size and quality for your LMS platform, whether you need lightweight MP3s or lossless WAV files.
How are failures handled in billing?
Failed requests are free. If synthesis fails, the charge is returned in full to your account balance. This ensures you only pay for successfully generated audio. You can monitor your usage and balance directly on the dashboard to track successful versus failed requests accurately.
Can I change my API key?
Yes, you can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to rotate keys for security without downtime, ensuring that only authorized applications can access your TTS services.
Does the API support speed adjustment?
The API supports speed adjustment between 0.25 and 4.0 times the normal rate. This allows you to slow down complex educational content for better comprehension or speed up simple updates. The speed parameter is included in the request body alongside the voice and model selection.
What languages are included?
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. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported. Any voice can speak any supported language.
Is the speech synthetic?
Yes, all generated speech is synthetic. Every audio file contains an inaudible watermark that marks it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.
How long does generation take?
Generation is roughly real-time for long texts, processing about 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so under heavy load, a request may wait in a queue. This predictable timing helps in planning API usage for large course batches.
Do I need to manage servers?
No, this is a cloud API. You send text via HTTP requests and receive audio files directly. There are no servers to manage, no software to install, and no infrastructure to maintain. You simply integrate the API into your application and pay for usage based on characters processed.
First request
curl
curl https://api.t46.net/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 edtech teams move beyond GTTS python
GTTS python libraries work well for simple demos, but they struggle when course libraries grow beyond a few hundred lessons. Managing local dependencies, handling environment drift, and ensuring consistent output across different development machines becomes a burden for edtech teams building scalable platforms.
Moving to a cloud API removes these operational headaches. By offloading synthesis to a dedicated endpoint, your infrastructure scales automatically with demand, allowing you to focus on content creation rather than maintaining voice-generation servers.
Reliable scaling for course libraries
When your catalog expands from dozens to thousands of lessons, local processing bottlenecks slow down updates. A cloud API handles high-volume batches without requiring you to provision additional hardware or manage queue systems.
- Handle thousands of audio files without server limits
- Process batches efficiently with 60 requests per minute
- Eliminate dependency on local machine performance
Consistent voice quality across modules
Using a single API endpoint ensures every lesson uses the exact same voice model, maintaining brand consistency across your entire LMS.
You select one of eight presets, such as Aria for narration or Sage for instruction, and every generated file matches that standard precisely.
- Uniform voice across all course content
- No version drift between dev and prod
- Standardized audio quality for learners
Reduced infrastructure overhead
You no longer need to maintain Python environments, install specific libraries, or allocate CPU cycles for audio generation. Your application simply sends text and receives audio files, reducing devops complexity.
This approach is particularly valuable for startups that want to keep their engineering team focused on product features rather than audio pipeline maintenance.
- Zero server maintenance for TTS
- Simple HTTP integration
- Lower operational costs
Python integration for course creators
We provide a straightforward API that integrates seamlessly with your existing Python workflows, allowing edtech teams to generate audio programmatically without managing complex infrastructure. By using the official OpenAI SDK, you can replace expensive voice-over production pipelines with a simple, scalable solution tailored for LMS platforms.
OpenAI SDK compatibility
Your existing codebase can connect to our API by simply updating the base_url to https://api.t46.net/v1 and using your unique API key. This ensures that standard Python libraries work immediately, minimizing the learning curve for developers already familiar with common TTS integrations.
- Standard JSON request structure
- Compatible with the official OpenAI SDK
- Easy base_url configuration
Simple POST requests
Sending text for synthesis requires a single POST request to /v1/audio/speech with your content in the JSON body. You can specify the model, voice, and format directly, receiving the audio file in response without needing to manage temporary files or complex state machines.
- JSON body input
- Direct audio file response
- Configurable voice and format
Automatic retry logic
For robust course generation, you can implement automatic retry logic to handle temporary rate limits or network issues. With a limit of 60 requests per minute, your scripts can gracefully queue requests, ensuring that large lesson libraries are processed efficiently without manual intervention.
- Handle 60 req/min limit
- Queue management for bulk uploads
- Reliable error handling
8 Premium Voices for diverse learners
Choosing the right voice ensures your course content resonates with diverse learners. LMS Voice Lab offers eight distinct presets, from immersive storytelling to clear instructional delivery.
Each voice is derived from licensed recordings, ensuring high-quality audio without the licensing headaches of traditional voice-over workflows. You can mix and match voices across modules to maintain engagement without breaking character consistency.
Narrator voices for storytelling
Use Aria’s warm, clear tone or Luna’s soft storytelling style to bring case studies and narratives to life. These voices maintain a natural rhythm that keeps students engaged during longer listening sessions.
Orion’s deep, documentary-style voice is ideal for historical modules or serious thematic content, providing a grounded auditory experience that complements visual materials without distraction.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling
- Orion: Deep, documentary
Instructional voices for tutorials
Sage delivers calm, instructional clarity perfect for step-by-step technical tutorials or complex explanations. His neutral delivery ensures that information remains the focus, reducing cognitive load for learners processing new concepts.
Atlas provides a neutral, news-style delivery that works well for factual content, quizzes, or standardized information delivery where consistency and neutrality are prioritized over emotional expression.
- Sage: Calm, instructional
- Atlas: Neutral, news
Engaging voices for marketing
Nova’s bright, upbeat tone and Felix’s energetic promo style are designed for promotional modules, course introductions, or call-to-action segments. These voices inject energy into your LMS, encouraging students to complete modules.
Milo’s friendly, conversational style bridges the gap between formal instruction and personal coaching, making complex topics feel approachable and reducing the friction of self-paced learning.
- Nova: Bright, upbeat
- Felix: Energetic, promo
- Milo: Friendly, conversational
Support for 23 Languages
LMS platforms serve global audiences, but inconsistent voice quality can undermine course credibility. Our API supports 23 languages, allowing you to maintain a consistent auditory brand across diverse modules without managing separate voice providers for each region.
English, Spanish, French, German
Core languages for broad reach are fully supported with any of the 8 voice presets. Whether you need a calm instructional tone for German tutorials or a bright upbeat voice for English marketing modules, the system adapts seamlessly.
Asian languages: Chinese, Japanese, Korean
Expand into high-growth markets with native-quality audio. The API supports Chinese, Japanese, and Korean natively, ensuring clear articulation for educational content.
European languages: Polish, Swedish, Dutch
Support regional learners with dedicated audio tracks. From Polish to Swedish and Dutch, every voice can speak any supported language, allowing you to localize course content efficiently while keeping infrastructure simple.
Formats for any LMS
We support standard audio formats to ensure compatibility with every major Learning Management System. Choose the right balance of quality, file size, and playback performance for your course library.
MP3 for web players
MP3 is the universal standard for web-based audio players. It offers excellent compression with minimal loss, ensuring fast loading times for students on any device or browser.
WAV for high-quality archives
WAV files provide lossless audio. Use this format for archival purposes or when your LMS requires lossless quality for accessibility compliance or professional course materials.
FLAC and OPUS for efficiency
FLAC and OPUS offer high compression ratios while maintaining high audio integrity. These formats reduce bandwidth usage and storage costs, making them ideal for large course libraries or mobile learners.

Transparent Pricing for Startups
LMS Voice Lab charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed synthesis requests are refunded entirely, ensuring you only pay for successful audio generation. This model aligns costs directly with usage, avoiding wasted spend on unused infrastructure.
Pay per character, not per minute
Our API charges based on input length. This benefits course creators who generate long educational texts, as voice speed variations do not alter the cost. You can predict expenses precisely by character count, making budget forecasting for large course libraries straightforward.
- Rate: $0.01 per 1,000 characters
- Charges apply only to successful requests
- Failed requests receive full credit refunds
No monthly subscriptions
We offer flat-rate pricing without monthly plans, seats, or minimum spend requirements. There are no recurring fees for API access, allowing startups to scale up or down based on actual enrollment needs. Top-ups via USDT on TRON are processed automatically, keeping your balance available for immediate use.
- No monthly subscriptions or recurring fees
- No minimum spend or seat limits
- Balance does not expire
Free trial with Google sign-up
New accounts signed in with Google receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters of free audio generation, allowing you to test voice quality and integration before committing funds. Email-based accounts start with zero balance and require an immediate top-up.
- Google sign-up grants $0.50 credit
- Trial valid for 7 days
- Approximately 50,000 characters of free usage
Data Privacy for Student Content
Course creators often worry about student data. Our API treats input text as a transient input. We do not use your course scripts or student-generated text to train our models, ensuring your intellectual property remains yours.
When synthesis completes, the audio file is returned directly in the response. We do not persistently store the generated audio files on our servers. This reduces liability and keeps your LMS as the single source of truth for your content.
Input text not used for training
We do not use your input text for model improvement. Your course content, whether it is a lecture script or a student essay, is processed solely to generate the requested audio file. This separation ensures that your unique educational material does not become part of our training dataset.
No persistent storage of generated audio
The synthesized audio is delivered via the API response and is not saved to our long-term storage by default. This means your LMS platform retains full control over where the final audio files are hosted, whether in AWS S3, your own server, or a dedicated CDN. We act as a processor, not a storage provider.
Metadata kept only for billing
We retain minimal request metadata, including timestamp, character count, and status, strictly for accurate billing and usage tracking. This data is not used to profile your users or to improve the voice engine. Once billing is reconciled, this metadata remains separate from your educational content, maintaining a clear boundary between operational data and creative assets.
Technical Specs for Developers
Developers integrating the TTS API into LMS platforms should note the 4096-character input limit per request. For longer course content, split the text into chunks and join the resulting audio files. Requests are processed sequentially, so under load, a request may wait in a queue, taking a few seconds for short phrases or roughly real-time speed for longer texts.
4096 character limit per request
Each API call accepts up to 4096 characters, including spaces and punctuation. To handle extensive lesson scripts, split the input into manageable parts and concatenate the generated audio segments.
Speed control from 0.25x to 4.0x
Adjust the playback speed between 0.25x and 4.0x using the speed field. This allows you to tailor audio for different learning levels or accessibility needs without re-generating the audio.
Automatic language detection
The API guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script content, explicitly set the language field to ensure accurate synthesis across the 23 supported languages.
Get Started with Python
Start by creating an account on the /get-api-key/ page using Google or your email. This grants immediate access to a free trial credit of $0.50, valid for seven days, which covers approximately 50,000 characters. You will receive a unique API key to authenticate your requests.
Once registered, you can integrate the TTS API directly into your Python projects. The service is fully compatible with the official OpenAI SDK, requiring only a simple configuration change to point to our API base URL.
Sign up for a free API key
Visit the /get-api-key/ page to register using Google or your email address. Upon sign-up, you receive a free trial credit of $0.50, valid for seven days, covering about 50,000 characters. Your account page displays your active API key, current balance, and usage statistics.
- Sign up via Google or email/password
- Receive $0.50 trial credit (7 days)
- View key, balance, and usage instantly
Use the OpenAI SDK with base_url
The API endpoint follows the same request shape as OpenAI’s speech endpoint. Install the openai Python package and configure the client by setting the base_url to https://api.t46.net/v1. Use your API key for authentication via the Authorization: Bearer header.
This setup allows you to use standard SDK methods without writing custom HTTP logic. The SDK handles JSON serialization and response parsing, ensuring reliable integration with your existing Python workflows.
- Install
openaiPython package - Set
base_urltohttps://api.t46.net/v1 - Use
Authorization: Bearer tts-...key
Generate your first audio file
Send a POST request to /v1/audio/speech with your text, chosen voice, and desired format. The API returns the audio file directly in the response, ready for immediate playback or storage in your LMS.
For texts exceeding 4,096 characters, split the input into smaller segments, generate audio for each part, and join the files. This ensures consistent quality and avoids request limits.
- POST to
/v1/audio/speech - Receive audio file in response
- Split text >4096 chars for longer content
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. From warm narrators to energetic promotional voices, the selection covers most common eduse scenarios.
23 languages
Any voice speaks any of these languages.
