Frequently asked questions
Who runs VoxEase?
VoxEase is an independent storefront for a text-to-speech API. We operate as a standalone service provider, managing the infrastructure so your team can focus on creating accessible materials.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base_url. However, we are a separate entity with our own pricing, voices, and infrastructure, independent of OpenAI’s services.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R, which uses readings from LibriVox public-domain audiobooks. Each generated audio file carries an inaudible watermark to mark it as synthetic speech.
Is the data secure?
We use standard authentication via Bearer tokens for your API key. Request metadata, including time, characters, and status, is kept for billing purposes. We do not use your input text for training models, and we do not store the generated audio files after they are returned in the response.
Do you store my text?
No. Your input text is used only to produce the audio and is not used for training. We retain request metadata for billing and usage tracking, but the actual text content you send to the API is not stored for long-term use or analysis after generation.
Do you store the audio?
No. Generated audio is returned in the response and is not stored on our servers. Once the audio file is delivered to your client or application, we do not keep a copy. This ensures that your specific voice-over content remains ephemeral and under your control.
How can I contact you?
Support is available via email only. We do not offer phone support or live chat. You can reach our team through the contact page on our website. Please include your API key and details about your inquiry to help us assist you with your accessibility projects efficiently.
Is there a live chat?
No, we do not have a live chat feature. All support is handled via email. This allows us to provide detailed, documented responses to your technical or billing questions without the pressure of real-time availability. You can find the email contact link on our /contact/ page.
Do you have an office?
We are a cloud-based service provider and do not have a specific public office location for customer visits. Our team operates remotely to manage the API infrastructure.
Are you certified?
We do not hold specific certifications such as SOC 2, HIPAA, or GDPR certificates. We are an independent storefront providing a standard cloud API. If you require specific compliance documentation for your organization, please contact us via email to discuss your specific data handling needs.
Do you offer SLA?
No, we do not offer a Service Level Agreement (SLA) or uptime guarantee. Our service is provided as-is. While we strive for reliability, we do not contractually guarantee specific availability percentages or compensation for downtime. This approach keeps our pricing simple and transparent for all users.
Can I get a refund?
Failed requests are free, and the charge is returned in full if synthesis fails. Since we do not offer subscriptions or invoices, refunds are handled on a case-by-case basis via email support.
What is the license for the voices?
The voices are based on licensed recordings from LibriTTS-R, which is licensed under CC BY 4.0. The source material comes from LibriVox public-domain audiobook readings.
Do you use AWS or Google Cloud?
We do not specify our underlying cloud provider. We are an independent storefront managing our own API infrastructure. You do not need to know our backend providers to use our service. Our API endpoint is https://api.rk66.info/v1, and we handle all server management for you.
Our Mission
VoxEase was built to ensure that digital content remains accessible to everyone, particularly for teams creating materials for dyslexic and neurodivergent audiences. We provide a reliable text-to-speech API that transforms written text into clear, consistent audio, removing the barrier of dense text for readers who process information differently.
Accessibility First Approach
Our API generates audio from text via a standard REST endpoint, ensuring compatibility with existing workflows. By converting text to speech, we help teams meet accessibility standards without requiring specialized design resources. The generated audio is neutral and clear, designed to aid comprehension rather than distract.
Supporting Neurodivergent Users
Dyslexic readers often benefit from auditory reinforcement to grasp complex information faster. VoxEase’s voices, such as Sage or Luna, offer calm, instructional tones that reduce cognitive load. Our synthetic voices provide consistent pacing and pronunciation, helping users focus on the content itself.
Simplifying Audio Production
Instead of hiring voice actors or recording in studios, teams can generate voice-overs directly from their text. Simply send the text to our API, and receive an audio file. This eliminates the logistical steps of booking talent, scheduling sessions, and editing raw recordings, allowing your team to focus on clear messaging.
Who We Are
We are a small, independent team focused on building reliable infrastructure for accessible content. Our structure is flat, allowing us to prioritize clarity and consistency in every API release without corporate overhead.
Independent Editorial Team
We ensure that the 23 supported languages are accurately represented and that voice descriptions match the actual audio output, avoiding marketing fluff.
Technical Experts
We handle the cloud infrastructure and API compatibility ourselves. By maintaining an OpenAI SDK-compatible endpoint, we ensure that developers can integrate our TTS service into their existing workflows with minimal code changes.
Accessibility Advocates
Our core audience includes teams creating materials for dyslexic and neurodivergent users. We design our pricing and voice options with consistency in mind, ensuring that audio outputs remain clear and predictable for assistive technologies.
Voice Licensing and Sources
VoxEase derives its eight voice presets from the LibriTTS-R dataset, which consists of recordings from LibriVox public-domain audiobooks. This foundation allows us to provide diverse synthetic voices without relying on proprietary training data or celebrity likenesses.
LibriTTS-R Dataset
The voices are based on licensed recordings from the LibriTTS-R dataset, sourced directly from LibriVox public-domain audiobook readings. This ensures that our audio engine rests on a robust, legally clear foundation of spoken language data.
CC BY 4.0 License
The underlying dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This standard license permits commercial use and modification, provided appropriate credit is given, allowing us to integrate these voices into our API services efficiently.
Public Domain Recordings
The source audio comes from public-domain readings, meaning the original recordings are free of restrictive copyright claims. This transparency helps teams creating accessible content for neurodivergent audiences understand exactly where their audio originates, ensuring compliance and clarity in content production workflows.
Data Privacy Policy
We process your input text solely to generate the audio file returned in the response. This text is not used for training our models or improving the engine, ensuring your content remains proprietary.
Generated audio files are delivered directly in the response and are not stored on our servers. Once you receive the file, our role in data custody ends, keeping your voice assets secure.
No Text Training
Your input text is used exclusively for the synthesis task. We do not retain it for model training, preserving your intellectual property and ensuring that your specific phrasing or scripts do not influence future voice generations.
No Audio Storage
The audio output is returned to you in the API response and is not persisted in our storage systems. This means your final voice-over files are not kept on our infrastructure after delivery, reducing long-term data exposure.
Metadata Retention
We retain request metadata, including timestamp, character count, and status, strictly for billing and usage verification. This data allows us to accurately charge your account and troubleshoot any synthesis issues without storing the actual content.

Technical Infrastructure
VoxEase operates as a cloud-based text-to-speech API, handling the infrastructure so your team can focus on creating accessible content. We manage the servers, scaling, and delivery, ensuring consistent performance for teams producing materials for dyslexic and neurodivergent audiences.
Cloud-Based API
Our service is entirely cloud-hosted, requiring no on-premise installation or data-center choice. You send text via a standard HTTP request and receive an audio file. This eliminates the need for complex local setups, allowing immediate integration into your existing workflows for generating voice-overs at scale.
OpenAI SDK Compatible
The API follows the same request shape as the OpenAI speech endpoint. By changing the base_url to https://api.rk66.info/v1 and using your VoxEase key, you can use the official OpenAI SDKs directly. This reduces integration time for developers already familiar with common TTS libraries.
- Same request shape as OpenAI
- Use official OpenAI SDKs with adjusted
base_url - No proprietary SDK required
Standard REST Endpoints
We use standard REST endpoints for all operations. You interact with POST /v1/audio/speech for generation, GET /v1/voices for metadata, and GET /v1/models for model info. This simplicity ensures reliability and ease of debugging, critical for teams maintaining consistent audio output across large volumes of content.
Contact and Support
We provide straightforward support via email for all technical and billing inquiries. There is no phone number or live chat available, keeping our operations lean and focused on the API itself. This allows us to maintain clear records of every request and resolution.
Our team consists of technical experts and accessibility advocates who understand the specific needs of neurodivergent audiences. We prioritize accurate, documented answers over quick, unrecorded conversations.
Email Only Support
Send your questions to our dedicated support address. We handle everything from API key issues to voice selection advice via this single channel.
This approach ensures that every query is logged and can be referenced later if you need to check the status of your request or billing adjustments.
- All inquiries are handled via email
- No voicemail or call queues
- Written records for every interaction
No Phone Number
We do not offer a phone number for customer support. If you prefer asynchronous communication, email is the most reliable way to reach us.
This avoids the delays of holding lines and ensures your specific question is answered by the right expert without general routing.
Response Time Expectations
Due to our lean team structure, complex technical questions may take slightly longer.
For urgent billing issues related to TRC-20 top-ups, please include your transaction hash in your email to speed up verification.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This combination supports better retention of information in video content.
23 languages
Any voice speaks any of these languages.
