Frequently asked questions
Is Lectera affiliated with OpenAI?
No. Lectera is an independent storefront for a distinct text-to-speech API. While our endpoint structure mimics the OpenAI speech endpoint for easy integration, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We operate as a separate entity providing our own infrastructure and voice models.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These recordings form the basis for our synthetic speech generation. Every generated audio file carries an inaudible watermark that explicitly marks it as synthetic speech, ensuring transparency about the audio's origin.
Is my data safe?
Yes. Your 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, characters, and status, strictly for billing purposes. This ensures your content remains private and is not repurposed for model improvement.
How do I contact support?
Support is available via email only. We do not offer a phone number, live chat, or SLA guarantees. For LMS teams needing assistance with API integration or billing issues, please reach out through the contact page. We handle all support inquiries through email to maintain clear records and efficient communication for your team.
Do you offer refunds?
Yes, but only for failed requests. If synthesis fails, the charge is returned in full. Successful requests are not refundable. We do not offer invoices with VAT or subscriptions, so refunds are processed automatically for errors. Your balance does not expire, and you can top up with USDT on the TRON network at any time.
Are the voices human or AI?
The voices are synthetic speech generated from licensed human recordings. They are not direct human voices but are based on LibriVox readings. Every generated file carries an inaudible watermark marking it as synthetic. We do not offer custom voice cloning, so you cannot upload your own voice or create a unique human-like variant for your brand.
Can I use the voices commercially?
Yes. The underlying recordings are from LibriVox public-domain audiobook readings, licensed under CC BY 4.0. You can use the generated audio for your online courses, LMS workflows, and commercial projects. There are no restrictions on commercial use, and we do not claim ownership over the final audio files you generate via our API.
Do you have a physical office?
We do not list a physical office or provide a phone number. As an independent API provider, we operate remotely. All support and communication are handled via email. This structure allows us to keep overhead low and pass those savings on to you with our predictable, per-character pricing model for large teams.
Who reads the content?
Our eight voice presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) read your content. These voices are based on licensed recordings from LibriTTS-R and LibriVox. They are not specific real people but synthetic voices trained on these licensed datasets. You can select any voice for any language supported by our API, regardless of the voice's original language.
Is the API open source?
No. We do not provide an official SDK of our own, nor is our API code open source. You can use the official OpenAI SDKs by changing the base_url to our endpoint, or use plain HTTP requests. We do not offer mobile SDKs, WordPress plugins, or browser extensions, keeping the integration simple and lightweight.
Who We Are
We are an independent storefront for a text-to-speech API designed specifically for large online course teams. Our goal is to simplify the conversion of educational text into audio files, allowing LMS workflows to scale without complex infrastructure.
Independent Editorial Team
Our service focuses on delivering a reliable API that integrates directly with your existing learning management systems. We prioritize simplicity and predictable pricing, ensuring your team can generate voiceovers for courses without managing intricate technical details or complex infrastructure.
Focus on LMS Integration
We built Lectera to handle the specific needs of educational content creation. By providing a straightforward API endpoint, we enable teams to convert up to 4,096 characters per request, making it easy to batch-process lesson scripts and integrate audio directly into your course modules.
No Affiliation with Major Brands
Lectera operates as an independent storefront for the same underlying TTS API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Our service offers a distinct set of eight voices and specific pricing structures tailored for high-volume educational teams.
Voice Licensing and Sources
Lectera’s voice models are derived from the LibriTTS-R dataset, which consists of read audiobooks from the LibriVox project. This foundation ensures that our synthetic voices are rooted in verified, high-quality human recordings.
LibriTTS-R Dataset
The core of our eight voice presets comes from the LibriTTS-R dataset. This collection provides the acoustic data necessary to train our text-to-speech engine, ensuring consistent quality across all languages and voices offered to LMS teams.
CC BY 4.0 License
We utilize the Creative Commons Attribution 4.0 International license for the source material. This allows us to legally incorporate these recordings into our API service while maintaining transparency about our data origins.
Public Domain Readings
The recordings originate from LibriVox, a volunteer effort providing public domain audiobooks. Because the source readings are in the public domain, we can offer these voices at scale without complex royalty negotiations, keeping your costs predictable for large course volumes.

Data Privacy Policy
Lectera processes your course scripts to generate audio files. We use your input text strictly for the purpose of synthesis and do not retain it for training our models or improving the voice engine.
Text Not Used for Training
Unlike many consumer AI services, we do not use your input text to train our TTS models. Your course scripts are processed solely to generate the requested audio file.
Audio Not Stored
The generated audio files are returned directly in the API response and are not permanently stored on our servers. Once you receive the file, it is not kept by Lectera for any other purpose.
Metadata Retention
We retain request metadata, including the timestamp, character count, and status, specifically for billing accuracy. This data ensures you are charged correctly for the characters processed and helps us manage your 60 requests per minute limit.
Technical Limitations
Lectera’s API delivers complete audio files via standard HTTP responses. We do not support WebSocket streams or real-time partial audio generation, so you receive the full synthesized speech only after processing completes. This design simplifies integration with most LMS platforms but requires waiting for the final output.
No Streaming Support
Audio is returned as a single response body in formats like MP3, WAV, or FLAC. For texts under 4096 characters, latency is typically a few seconds, scaling with length. Longer texts are split internally and joined before return.
No SSML Support
Our endpoint accepts plain text strings only. We do not parse SSML tags for pauses, emphasis, or custom pronunciation lexicons. Voice characteristics are controlled via the voice parameter (e.g., aria, nova, atlas) and the speed multiplier (0.25–4.0).
No Custom Cloning
We offer eight preset voices derived from the LibriTTS-R dataset. Customers cannot upload their own voice samples for cloning or design custom voice profiles. All generated files include an inaudible watermark indicating synthetic origin.

Support Contact Information
Lectera is an independent editorial team built for LMS workflows. We focus on delivering a reliable text-to-speech API that integrates smoothly with your course production pipeline, without the overhead of complex infrastructure or enterprise sales teams.
Our support structure is designed to be straightforward and transparent, ensuring that your team can resolve issues efficiently without navigating multiple channels or waiting on hold for generic answers.
Email Support Only
All support requests are handled exclusively via email. This ensures that your queries are documented, searchable, and can be addressed by engineers who understand the API’s specific behavior and limitations.
We do not maintain a public help desk or ticketing portal; simply send your message to our support address with your account details and a clear description of the issue.
No Phone or Chat
We do not offer phone numbers, live chat, or instant messaging support. This deliberate choice allows our small team to focus on deep technical problem-solving rather than real-time availability.
By avoiding real-time channels, we ensure that every request receives a thorough, written response that you can reference later in your team’s documentation or workflow.
Response Expectations
High-volume periods may extend this window slightly, but we prioritize clear, actionable solutions.
For urgent integration issues, including your API key and error logs in your initial email will significantly speed up the resolution process.

Mission and Values
Lectera exists to remove friction from audio production for large educational teams. We built a straightforward API that fits directly into your LMS workflow, allowing you to convert text to speech at scale without managing complex infrastructure or hiring specialized voice talent.
Simplicity First
Our tool is designed for speed and ease of use. Send text via a simple POST request and receive audio files immediately. We prioritize clear documentation and predictable behavior so your development team can integrate Lectera into course creation pipelines without steep learning curves.
Transparent Pricing
- $0.01 per 1,000 characters
- No minimum spend
- Balance does not expire
Team-Focused Design
- Single active key per account
- Easy key rotation
- Supports large volume handling
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Our scalable platform streamlines employee onboarding and continuous learning across your entire global workforce.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriTTS-R corpus (OpenSLR 141)
- curl documentation
- openai-node on GitHub
- Node.js documentation
- FFmpeg documentation
- LibriTTS-R paper (arXiv 2305.18802)
- LibriVox public-domain audiobooks
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- openai-python on GitHub
- TRON developer hub: TRC-20
