Frequently asked questions
Who runs VerbaLect?
VerbaLect is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Our team focuses on providing consistent, neutral narration for educational workflows, helping teachers and methodologists turn lesson text into clear audio without hiring voice actors.
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. Each generated file carries an inaudible watermark marking it as synthetic speech. The voices include options like Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion.
Is my text data safe?
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. Your content remains secure during processing.
Do you use my data for training?
No. Input text is used solely to generate the audio response. We do not use your text for training models. Generated audio is returned in the response and is not stored long-term. Only request metadata is kept for billing and usage tracking.
Can I contact you by phone?
No, we do not have a phone number. Support is available by email only. We do not offer live chat or phone support. For any questions regarding your API key, billing, or technical issues, please reach out via our contact page or support email.
Do you have a live chat?
No, we do not have a live chat feature. Our support is handled entirely via email. This allows us to provide detailed, written responses to your questions about the API, billing, or voice presets without the need for real-time availability or waiting in a queue.
Are the voices licensed?
Yes, our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain readings from LibriVox. This ensures legal clarity for your educational content.
Can I use the voices commercially?
Yes, you can use the generated audio commercially. Since the source recordings are from LibriVox (public domain) and LibriTTS-R (CC BY 4.0), you can integrate the audio into your educational products, courses, and LMS modules. The API delivers consistent narration suitable for professional educational workflows.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer refunds for successful requests. There are no monthly plans or subscriptions, so you only pay for what you use. Balance does not expire, giving you flexibility.
How is data stored?
Input text is used only to produce audio and is not stored. Generated audio is returned in the response and not stored. We retain request metadata, including time, characters, and status, strictly for billing purposes. Your actual content is not kept in our long-term storage.
Who owns the generated audio?
You own the generated audio files you create. We provide the text-to-speech engine and voices based on licensed sources. The generated files are returned directly in your API response. You can use them in your educational videos, LMS modules, and other commercial or non-commercial projects.
Do you have a physical address?
We do not list a physical address. As an independent API provider, we operate digitally. Support is available by email only. We do not have a physical storefront or office listed for public visits. Our focus is on delivering reliable text-to-speech services via our API.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint and request shape mimic the OpenAI speech endpoint, so their SDKs work by changing the base URL. However, we are an independent storefront. We are not OpenAI, ElevenLabs, Google, Amazon, or Microsoft.
Do you have an SLA?
No, we do not offer an SLA or uptime guarantee. There is no enterprise contract or on-premise install option. We provide a reliable API for teachers and methodologists, but we do not guarantee specific availability percentages or provide certifications like SOC 2 or HIPAA.
Can I get a certificate for GDPR?
No, we do not provide a GDPR certificate. We do not offer certifications such as SOC 2 or HIPAA. We keep request metadata for billing and use input text only for generation. For specific legal requirements, please review our data handling practices or contact us via email.
How do I update my API key?
You can issue a new API key at any time from your account dashboard. When you issue a new key, the old one stops working immediately. This ensures security and allows you to rotate credentials easily. You can manage your keys on the /get-api-key/ page.
Our Mission for Educators
VerbaLect was built to help teachers and methodologists turn lesson text into clear audio for LMS modules without hiring voice actors. Our API delivers consistent, neutral narration that fits any educational video workflow, ensuring your course materials sound professional and uniform.
Simplify audio production
Stop coordinating with external voice talent. Send text to our API and receive an audio file instantly. With a rate limit of 60 requests per minute (10 per minute before the first top-up), you can batch-process entire lessons, though requests are processed sequentially and may wait in a queue under load.
- No studio booking required
- Instant audio delivery via API
- Consistent voice across all modules
Support teachers and methodologists
Our eight voice presets, from the warm narrator Aria to the calm instructor Sage, are designed for clarity. Whether you need energetic promos or neutral news-style delivery, our voices speak 23 languages, allowing you to reach diverse student groups without multiple recordings.
- 8 distinct voice presets
- 23 supported languages
- Neutral, clear narration
Make content creation easy
Integration is straightforward: use the standard OpenAI SDK by changing the base URL. With a simple JSON body, you get audio in mp3, wav, opus, flac, or pcm formats. This simplicity lets you focus on your curriculum, not on technical audio engineering.
- OpenAI SDK compatible
- Multiple audio formats
- Quick integration
Editorial Team
The VerbaLect editorial team is built by teachers and methodologists who understand the daily grind of creating LMS content. We designed this API because we know how time-consuming it is to hire voice actors for every module update. Our goal is to give educators a reliable tool that produces clear, consistent narration without the logistics of traditional recording studios.
VerbaLect editorial team
We are educators first, technologists second. Our team has spent years crafting lesson plans and audio guides, so we know exactly what teachers need: clear enunciation, neutral delivery, and consistent quality across thousands of characters.
Focused on education
Every feature we build serves the classroom. We prioritize voices like Atlas for news-style updates or Sage for instructional guides, ensuring the audio fits seamlessly into your existing course structure. We don’t chase trends; we focus on making your lesson text sound professional and engaging.
- Designed for LMS modules
- Clear, neutral narration styles
- Optimized for lesson text
Expert in TTS technology
Our technology leverages licensed recordings from LibriVox, ensuring high-quality synthetic speech. We handle the complexity of character limits, language detection, and audio formatting so you can focus on your curriculum. With a simple API, you get consistent results every time, without needing technical expertise.
Voice Licensing
VerbaLect’s voice engine is built on high-quality, ethically sourced audio. We use the LibriTTS-R dataset, which is licensed under CC BY 4.0, and recordings from LibriVox.
LibriTTS-R (CC BY 4.0)
The core of our synthesis engine relies on the LibriTTS-R dataset. This collection is publicly available under the Creative Commons Attribution 4.0 International license.
- CC BY 4.0 licensed dataset
- High-fidelity speech samples
- Transparent attribution model
LibriVox public domain
Many of the underlying recordings originate from LibriVox, a platform dedicated to public domain audiobooks. These readings are from the public domain, providing a rich, diverse foundation for our voice presets used in educational modules.
- Public domain source material
- Diverse narrator styles
- Verified audiobook origins
Licensed recordings
We curate and process these recordings to create the eight distinct voice presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). Each voice is engineered for clarity and consistency, ensuring your LMS content sounds professional and uniform.
- Curated voice presets
- Consistent audio quality
- Optimized for narration
Data Policy
When you send text to VerbaLect, we process it exclusively to generate the audio file you receive in the response. The input text is not stored permanently or used for any other purpose.
Text used only for audio
Your lesson content is processed solely to create the speech synthesis. Once the audio is returned, the text is not retained for secondary uses.
No training on input
We do not use your input text to train our models. Your specific lesson texts remain yours and are not part of our training data.
Metadata kept for billing
We keep request metadata, including timestamp, character count, and status, strictly for billing purposes. This ensures accurate charges based on the $0.01 per 1,000 characters rate, where spaces and punctuation count as characters.

Honest Limits
We prioritize stable, batch-based synthesis for LMS modules over real-time streams. If you need live audio for interactive classrooms, our current architecture processes requests sequentially, which may introduce slight delays during high traffic.
No streaming or WebSocket
Our API returns complete audio files (mp3, wav, opus, flac, pcm) upon request completion. We do not offer partial audio chunks or persistent WebSocket connections for real-time playback.
No SSML support
We do not support Speech Synthesis Markup Language (SSML) for fine-grained control over pauses, pitch, or emphasis. Voice characteristics are fixed per preset.
No custom voice cloning
We do not offer voice cloning or custom voice design. You choose from our eight licensed presets, which are based on recorded readings. Each generated file includes an inaudible watermark to mark it as synthetic speech.
Contact Us
We keep communication simple and direct. All support requests go through our email address, where our team reviews your message and responds with specific, actionable answers regarding your API usage or billing.
Email support only
Send us a message anytime. We prioritize clear, written responses that you can reference later.
No phone number
We do not maintain a dedicated phone line. You won’t spend time waiting on hold for a voice prompt.
No live chat
There is no real-time chat widget on this site. If you need immediate assistance during a critical lesson upload, email is the most reliable channel. Our team monitors inboxes regularly and provides detailed, written solutions rather than quick, vague fixes.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. All voices share the same engine, so switching styles does not affect quality or pricing.
23 languages
Any voice speaks any of these languages.
