Frequently asked questions
Is this the official Google TTS API?
No. CourseVoice API is an independent storefront for a cloud text-to-speech API. It is not affiliated with Google, OpenAI, or any other brand. The API uses a standard endpoint compatible with OpenAI SDKs, allowing you to integrate synthetic voice generation into your LMS without relying on Google’s specific infrastructure or branding.
What is the character limit per request?
The API accepts up to 4096 characters per request. For longer texts, you must split the input into parts of this size and join the resulting audio files. This limit applies to each individual API call, ensuring consistent processing performance for your e-learning content generation workflows.
How many voices are available?
There are 8 voice presets available: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These include female and male options with distinct tones, such as warm narration or energetic promo styles. All voices can speak any of the supported languages, providing flexibility for diverse course content.
Which languages are supported?
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. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script.
Does the API support streaming audio?
No, the API does not support streaming, WebSocket, or real-time partial audio. You send text via POST and receive a complete audio file. For real-time playback in your LMS, you must wait for the full file to generate. This ensures high-quality, complete audio segments for each request.
What is the pricing model?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spend requirements. You only pay for the characters you successfully process.
Is there a free trial available?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test the API with approximately 50,000 characters before committing to a top-up.
How do I pay for the API?
Payments are made via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are automatically added within minutes. There are no credit cards, PayPal, subscriptions, or invoices. Your balance does not expire, and you can issue a new API key at any time.
Can I use my own voice recordings?
No, custom voice cloning is not offered. You cannot upload your own voice or design custom voices. The 8 presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark marking it as synthetic speech, ensuring clear distinction from human-recorded audio.
Is there an SLA guarantee?
No, there is no Service Level Agreement (SLA) or uptime guarantee. There is no enterprise contract, on-premise install option, or data-center choice. Support is provided via email only. The API processes requests in a queue, so under load, generation may take longer than typical real-time speeds.
How long is the trial credit valid?
The $0.50 trial credit is valid for 7 days after signing in with Google. Accounts created with email and password do not receive this trial credit. The credit allows you to generate approximately 50,000 characters during this period to evaluate the API’s performance for your LMS integration.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generation. You can retry the request or adjust parameters like speed or voice, knowing that any failed attempt will not affect your balance.
Can I clone a celebrity voice?
No, the API does not offer custom voice cloning for customers. You cannot upload a voice sample to clone a celebrity or anyone else. The available voices are fixed presets based on licensed recordings. Each file carries a watermark indicating it is synthetic speech, distinct from human recordings.
Is there a minimum spend required?
No, there is no minimum spend required. You can top up with a minimum of $5 via USDT on TRON. There are no monthly plans, seats, or subscription fees. Your balance does not expire, and you can use any amount of credit for character generation as needed.
First request
curl
curl https://api.shweohh.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.mp3API for LMS Integration
CourseVoice API provides a simple JSON endpoint for integrating synthetic voice audio into your LMS. Send a POST request to the speech endpoint with your text and receive an audio file directly. This straightforward design removes the need for complex middleware, allowing your course engine to fetch narration on demand.
Simple JSON endpoint
The API accepts standard JSON bodies with fields like model, input, and voice. You send text up to 4096 characters and receive the audio file in formats like mp3 or wav. This direct request-response pattern fits easily into existing backend workflows for generating course audio.
OpenAI SDK compatible
The request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.shweohh.info/v1. This allows you to reuse existing client code and authentication logic without writing custom HTTP handlers for your LMS integration.
Generation speed
Audio generation is processed sequentially, with typical speeds approaching real-time for long texts. Short phrases may take a few seconds, while longer content generates at roughly 25 characters per second. Requests are queued under load, ensuring stable throughput for your course platform.
Voice Options for Education
CourseVoice API provides eight distinct voice presets designed to match the pacing and tone of educational content. These voices are based on licensed recordings, providing clear audio for lectures or tutorials.
Narrator voices
Aria offers a warm, clear narration ideal for structured courses, while Luna provides a soft, storytelling tone suitable for engaging narratives or soft skills training.
Conversational tones
Nova brings a bright, upbeat energy to product demos or quick tips. Milo delivers a friendly, conversational style perfect for onboarding sequences or casual Q&A modules.
News and docs
Atlas ensures neutral, clear delivery for technical documentation or news-style updates. Orion adds a deep, documentary tone for premium content or in-depth historical overviews.
Supported Languages
CourseVoice API supports 23 languages, allowing you to localize content for global learners without managing multiple voice providers. The engine handles script detection automatically, ensuring correct pronunciation for mixed-script inputs.
Developers can override detection by explicitly setting the ISO language code. This ensures consistent output even when the text contains ambiguous Latin characters that might otherwise default to English.
23 languages included
Our API supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. All 8 voice presets can speak any of these languages, giving you flexibility in tone and style regardless of the target language.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi
- Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-language detection
If you do not specify a language, the API guesses it from the text script. Latin script defaults to English. This works well for single-language courses but may misinterpret mixed-language content.
Manual language set
For non-English Latin-script text, always set the language field. This prevents incorrect voice selection and ensures accurate pronunciation. For example, setting language: 'de' ensures German voices are used for German text, even if it contains English loanwords.
Developer Experience
Integration takes minutes, not days. The API mirrors the OpenAI speech endpoint structure, allowing you to swap the base URL and begin sending requests immediately. This compatibility means your existing HTTP clients and libraries work out of the box without custom adapters.
You do not need to manage a proprietary wrapper. We provide a standard REST interface that fits naturally into your CI/CD pipelines and backend services. Debugging is straightforward using standard HTTP status codes and JSON responses.
Fast integration
Change your base URL to https://api.shweohh.info/v1 and use your API key. The request shape matches the OpenAI speech endpoint, so you can often update a single configuration variable in your codebase.
We provide a ready curl example on the dashboard to verify connectivity instantly. Most developers can generate their first audio file shortly after account creation.
- Compatible with OpenAI SDKs by changing base_url
- Standard JSON request/response format
- Works with any HTTP client library
No custom SDK
We do not maintain a language-specific SDK. This keeps the interface stable and version-agnostic. You use the same HTTP client you already trust, whether it’s Python requests, Node fetch, or Go net/http.
This approach reduces dependency bloat and ensures your integration survives SDK deprecations. You control the client versioning and error handling logic directly in your application code.
Standard HTTP
All requests are standard POST/GET calls over HTTPS. Authentication is handled via the Authorization header with a Bearer token. Responses return audio data or JSON error details.
Rate limits are enforced per key. You can monitor your request volume and balance directly in the dashboard without parsing custom response headers.
- No proprietary protocols or WebSockets
- Simple Bearer token authentication
- Predictable HTTP status codes
Pricing Model
CourseVoice API charges $0.01 per 1,000 characters, with spaces and punctuation counted toward the total. Failed requests are free, ensuring you only pay for successful audio generation. This model scales naturally with your course library size, eliminating waste from unused capacity.
Pay per character
You are billed strictly for the input text length. At $10 per million characters, costs remain predictable regardless of audio duration. Short phrases and full lessons are priced identically per character unit.
No monthly fees
There are no subscriptions, seats, or minimum spend requirements. Balance does not expire. You can top up via USDT (TRC-20) on the TRON network, with a minimum of $5. No invoices or VAT are involved.
Transparent rates
Rates are fixed: $0.01 per 1,000 characters. Both tts-1 and tts-1-hd use the same engine and price. You can monitor usage and remaining balance directly in the dashboard without hidden tiers.

Technical Limits
Understand the operational boundaries of the CourseVoice API to plan your LMS architecture correctly. Input text is capped at 4096 characters per request, requiring your system to split longer lessons into manageable segments. Audio formats include mp3, wav, opus, flac, and pcm, allowing flexible delivery to your course engine.
4096 char limit
Each API call accepts a maximum of 4096 characters for the input field. Spaces and punctuation count toward this limit. For longer course modules, your application must split the text, send multiple requests, and join the resulting audio files.
Rate limits
The API allows 60 requests per minute per key. New accounts without top-ups are limited to 10 requests per minute. Under heavy load, requests may queue sequentially, affecting generation speed for bulk content creation.
Audio formats
Specify the output format using the response_format parameter. Supported formats are mp3, wav, opus, flac, and pcm. Choose based on your platform’s bandwidth and compatibility requirements. MP3 is generally optimal for web delivery.
Audio Quality
CourseVoice API delivers audio at roughly real-time speed, processing approximately 25 characters of text per second. While short phrases take a few seconds to generate, longer texts are handled efficiently by splitting input into 4096-character segments and joining the resulting audio files.
Real-time speed
Requests are processed sequentially, so under heavy load, generation may queue briefly. However, typical usage remains close to real-time, ensuring your LMS students receive audio without significant delay.
Synthetic watermark
Every generated audio file contains an inaudible watermark marking it as synthetic speech. This ensures transparency for your learners and helps distinguish AI-generated narration from human-recorded content in your course library.
High fidelity
Voices are derived from licensed LibriTTS-R and LibriVox recordings, providing clear, natural-sounding narration suitable for educational content. The API supports high-quality output formats including WAV, FLAC, and Opus to match your platform’s audio standards.
Use Cases
CourseVoice API integrates directly with LMS platforms to automate voiceover generation for lesson content. By sending text to the speech endpoint, your system receives synthesized audio files ready for playback, eliminating manual recording workflows.
This approach allows for consistent audio quality across thousands of courses without hiring voice actors for every update.
Course narration
Generate consistent voiceovers for video lessons and text-based modules. The API handles up to 4,096 characters per request, allowing you to split longer scripts and join the resulting audio files seamlessly.
Voices like Aria and Luna provide clear, instructional tones suitable for educational content, while Felix works well for promotional course trailers.
- Automate audio generation for new or updated courses
- Maintain consistent narrator voice across entire curricula
- Support multiple languages for global course expansion
Accessibility audio
Convert text-heavy course materials into audio for learners with visual impairments or dyslexia. Since input text is not used for training, student privacy is preserved during generation.
The synthetic watermark ensures users know the audio is AI-generated.
- Improve compliance with accessibility standards
- Reduce production time for audiobooks and reading materials
Video dubbing
Produce audio tracks in 23 supported languages to localize video content. Set the language parameter explicitly for Latin-script text to ensure accurate pronunciation.
Use MP3 or WAV formats for easy integration with standard video players.
- Localize content for diverse student demographics
- Integrate audio into existing video workflows
Get Started
Access the CourseVoice API by visiting the /get-api-key/ page. Sign up using your Google account or create a standard email and password. Once registered, you receive a unique API key and can immediately view your balance and usage statistics.
This is the only place to issue new keys; generating a new one instantly invalidates the previous one. You can start integrating the TTS endpoint into your LMS platform right away without waiting for approval or manual setup.
Sign up now
Visit the registration page to create your account. Choose Google sign-in for speed or use email credentials. You will receive your API key immediately upon verification.
Accounts are scoped to this domain. Ensure you are registering on shweohh.info to access the correct API base URL.
- Google or email registration
- Instant API key issuance
- Key rotation available
Free trial credit
New Google sign-ups receive $0.50 in credit, covering approximately 50,000 characters. This trial is valid for seven days. Email-based accounts start with zero balance.
Top-ups require USDT (TRC-20) on the TRON network. Minimum deposit is $5, credited automatically within minutes. No credit cards or subscriptions are needed.
API documentation
Complete technical details, endpoint schemas, and code examples are available at /docs/. The API follows the OpenAI speech endpoint structure, allowing use of standard OpenAI SDKs with a simple base_url change.
Use the provided curl examples to test your key. Check /v1/voices to list available presets and confirm supported languages before implementation.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. You only pay for what you use, with no monthly minimums or seats to manage.
23 languages
Any voice speaks any of these languages.
