Frequently asked questions
Are the voices copyrighted?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This foundation allows us to provide clear, character-based voice lines for your educational modules without complex licensing hurdles for standard usage.
Do you store my course text?
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 and character count, strictly for billing purposes.
Can I use the voices commercially?
Yes. You can use the generated audio in commercial online courses and LMS platforms. The inaudible watermark marks the file as synthetic speech but does not restrict usage.
Who owns the generated audio?
You own the generated audio files created from your input text. We do not store the audio after delivery, and the input text is not used for training, ensuring your course content remains yours while we handle the synthesis process.
Is my API key secure?
Each account has one active key. You can issue a new key at any time, and the old one stops immediately. We use standard Bearer token authentication, and request metadata is kept for billing without exposing your actual course content.
Do you sell user data?
No. Input text is used only to produce audio and is not used for training. Generated audio is not stored. We retain request metadata like time and status solely for billing and usage tracking, ensuring your data privacy is respected.
Can I contact you by phone?
No, we do not have a phone number or live chat. Support is provided by email only. This keeps our overhead low, allowing us to focus on delivering a lightweight, cost-effective TTS API for educators and instructional designers.
Do you have a physical office?
We do not have a physical office or on-premise install option. We are a cloud-based API service, which allows us to remain lightweight and accessible for teachers and methodologists who need to integrate voice lines directly into their online modules.
Are the voices human or AI?
Our voices are based on licensed recordings from LibriTTS-R and public-domain audiobook readings from LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring transparency while providing clear, character-based narration for your educational content.
Can I request a new voice?
No, we do not offer custom voice design or voice cloning. We provide eight specific presets like Aria, Nova, and Atlas. If you need a different voice, you must choose from our existing library of eight character-based options.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, we do not offer traditional refunds, but your balance never expires. You can top up via USDT on the TRON network at any time.
Is the API open source?
No, we do not have an official SDK. You can use the official OpenAI SDKs by changing the base_url to https://api.combowin.top/v1 or use plain HTTP. Our API follows the same request shape as the OpenAI speech endpoint.
Can I use the voices in ads?
Yes, you can use the generated audio in ads. Our voices are based on licensed recordings from LibriTTS-R and public-domain readings from LibriVox. The inaudible watermark marks the file as synthetic, but there are no restrictions on commercial use in advertising.
Do you have a team of voice actors?
No, we do not have a team of voice actors. Our eight voices are based on licensed recordings from LibriTTS-R and public-domain audiobook readings from LibriVox. This allows us to offer consistent, clear narration without the variable costs of human actors.
How do you ensure quality?
We use licensed recordings from LibriTTS-R and public-domain LibriVox readings as our foundation. Each file includes an inaudible watermark to identify synthetic speech. Our eight presets are optimized for clarity, ensuring your educational modules sound professional and engaging for students.
What is your return policy?
Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer refunds for successful generations. Your balance does not expire, and you can top up via USDT on the TRON network whenever needed.
Who we are
AudioTeach is an independent storefront for a lightweight text-to-speech API dedicated to educators and instructional designers. We understand the unique needs of online course creation, focusing on delivering consistent, character-based voice lines without the overhead of large enterprise platforms.
Independent editorial team
Our team prioritizes clarity and ease of integration for LMS platforms, ensuring our API fits seamlessly into your existing teaching workflows without unnecessary complexity.
Focus on educational APIs
Our primary goal is to serve teachers, methodologists, and content creators who need reliable narration for online modules. We design our voice presets and documentation with educational use cases in mind, such as game show host styles or calm narrator tones.
No corporate backing
Unlike many tech startups, we are not backed by large venture capital firms or part of a bigger tech conglomerate. This independence allows us to keep our pricing simple and our development focused on what matters most to educators: clear audio and straightforward integration.
Voice licensing and sources
AudioTeach’s voice engine relies on recordings from the LibriTTS-R dataset. These recordings serve as the foundation for our eight distinct voice presets, ensuring consistent and natural-sounding output for educational content.
LibriTTS-R recordings
The core audio samples originate from the LibriTTS-R dataset, providing a diverse range of vocal timbres. These recordings are processed to create our eight preset voices, including both male and female options suitable for various instructional styles.
CC BY 4.0 license
All source recordings are licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This allows us to use these voices in our API service. You can use the generated audio in your courses without worrying about complex licensing restrictions for the voice itself.
LibriVox public domain
The underlying recordings are derived from LibriVox, a platform dedicated to public domain audiobooks. This ensures that the base audio material is freely available.
Data privacy and usage
AudioTeach is built with a simple privacy principle: your input text is used exclusively to generate the audio file for your educational modules. Once the synthesis is complete, the generated audio is returned in the response and not stored on our servers for later use or retrieval.
Text used only for audio
We process your input text solely to produce the final audio file. The text is not archived, indexed, or repurposed after the request is fulfilled. This ensures that your lesson content remains private and is not retained beyond the immediate generation process.
No training on input data
Unlike many AI services, we do not use your input text to train our models or improve our voice engines. Your specific scripts and educational materials remain yours, ensuring that your unique course content is not absorbed into our general training data.
Metadata kept for billing
We retain minimal request metadata, including the timestamp, character count, and status, strictly for billing purposes. This data allows us to accurately charge your account (e.g., $0.01 per 1,000 characters) and verify usage without storing the actual content of your lessons.
Technical infrastructure
AudioTeach operates as a lightweight cloud-based API, designed specifically for educational workflows. We rely on standard HTTP requests to deliver synthesized audio files directly to your applications or LMS integrations without complex infrastructure dependencies.
There is no on-premise option available. Our service is entirely hosted in the cloud, ensuring you can start generating voice lines for online modules immediately without managing servers or hardware. This keeps the setup simple for teachers and instructional designers who need to focus on content rather than IT maintenance.
Cloud-based API
Our API endpoint, https://api.combowin.top/v1, processes text inputs and returns audio files via standard JSON requests. This architecture allows for easy integration with existing educational tools and platforms without requiring dedicated server space on your end.
- - Endpoint:
POST https://api.combowin.top/v1/audio/speech - - Input: JSON body with text, voice, and format
- - Output: Audio file (mp3, wav, opus, flac, pcm)
No on-premise option
We do not offer an on-premise installation. The entire processing engine runs on our cloud servers. This means you benefit from our maintenance and scaling efforts without needing to allocate local resources or worry about server uptime for your specific department.
- - No server hardware to manage
- - No local software installation required
- - Accessible from anywhere with internet
Standard HTTP requests
We use standard HTTP requests, making integration straightforward. You can use the official OpenAI SDKs by simply changing the base_url to our API endpoint, or use any standard HTTP client. This compatibility ensures that your existing codebases can leverage our TTS capabilities with minimal adjustment.
- - Compatible with OpenAI SDKs
- - Simple JSON request structure
- - Standard HTTP/HTTPS protocols

Support and contact
We prioritize clear, written communication for our educational API support. Our team is dedicated to helping educators and instructional designers resolve integration issues or billing questions efficiently without the noise of multiple channels.
Email support only
All inquiries are handled via email. This allows us to provide detailed, documented responses that you can reference later when configuring your LMS or course modules.
- Send queries to [email protected]
- Include your API key prefix for faster identification
No live chat or phone
We do not offer live chat or phone support. This keeps our operational costs low and ensures every message receives a thoughtful, written reply rather than a rushed verbal interaction.
Response time varies
Response times depend on the volume of requests. Since we are a small independent team, complex technical questions may take longer than simple billing updates. Check your spam folder if you do not hear back within 24 hours.
Limitations and honesty
We built AudioTeach for educators who need reliable voice lines without corporate overhead. We are an independent team focused on clear, character-based TTS for online modules, not a tech giant with infinite resources.
No SLA or uptime guarantee
We do not offer a Service Level Agreement or promise specific uptime percentages. Our cloud infrastructure handles requests sequentially, so during high load, synthesis may take longer than usual. We do not guarantee availability for critical, time-sensitive production workflows.
No certifications listed
We have not pursued formal certifications such as SOC 2, HIPAA, or GDPR compliance documents. While input text is not used for training, we do not hold third-party audit reports to verify our data handling practices beyond this statement.
Not affiliated with OpenAI
Our API endpoint structure mimics the OpenAI speech model for ease of use, but we are not affiliated with OpenAI, ElevenLabs, Google, or Amazon. We use our own licensed voice recordings from LibriVox, not OpenAI’s proprietary models.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Technical terms and specific instructions are articulated with precision.
23 languages
Any voice speaks any of these languages.
