Frequently asked questions
Who runs the CursVoice API?
CursVoice is an independent storefront for a cloud text-to-speech API. It operates as a distinct entity, not affiliated with OpenAI, ElevenLabs, or other major brands. The API provides a reliable endpoint for converting text into audio files, serving educational content creators directly without intermediary brand association.
Where do the voices come from?
The eight voice presets are based on licensed recordings from LibriTTS-R, which derives from LibriVox public-domain audiobook readings. These recordings form the foundation of the synthetic voices available for your text-to-speech generation, ensuring a consistent and recognizable audio style across all generated content.
Are the voices licensed recordings?
Yes, the voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated audio file carries an inaudible watermark that marks it as synthetic speech, confirming its origin from these specific licensed and public-domain source materials.
How is my text data used?
Input text is used solely to produce the requested audio file. It is not stored after generation and is not used for training models. Only request metadata, including time, character count, and status, is retained for billing purposes and account management.
Is my data used for training models?
No. 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. Request metadata is kept strictly for billing purposes, ensuring your educational content remains private and unused for model development.
How long is request metadata kept?
Request metadata, including time, characters, and status, is kept for billing purposes. This data allows us to accurately track usage and charges against your account balance. No other text or audio data is retained beyond the immediate generation and response delivery.
Do you offer phone support?
No, we do not offer phone support. All customer support is handled via email only. There is no live chat or phone number available for inquiries. You can reach our team by contacting us through the email address provided on our contact page.
How can I contact the editorial team?
Support is provided by email only. There is no phone number or live chat available. You can contact us by sending an email to the address listed on our contact page.
Is CursVoice affiliated with OpenAI?
No, CursVoice is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. While our API endpoint shape matches the OpenAI speech endpoint for SDK compatibility, we are an independent entity providing our own text-to-speech technology and infrastructure.
Are there any certifications for the API?
No, we do not offer certifications such as SOC 2, HIPAA, or GDPR certificates. We provide a reliable API for educational content but do not maintain specific enterprise-grade compliance certifications. Data is used only for generation and billing, but formal certification is not provided.
Do you have an SLA?
No, we do not offer an SLA or uptime guarantee. Requests are processed sequentially, and under load, a request may wait in a queue. Typical speed is roughly real time, but we do not guarantee specific latency or availability percentages for any service tier.
What is the data retention policy?
Input text is used only to produce the audio and is not stored. Generated audio is returned in the response and not stored. Request metadata (time, characters, status) is kept for billing. No other data is retained, ensuring minimal footprint for your educational content.
Can I request a specific voice?
Yes, you can select from eight voice presets: aria, nova, luna, sage, felix, milo, atlas, and orion. Each voice has a distinct tone, such as warm, bright, or deep. You specify the desired voice in the voice field of your API request for synthesis.
How do I verify the license of the voices?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech.
Who We Are
CursVoice is an independent provider of a text-to-speech API designed for instructional designers and teachers. We focus on converting textbooks and course materials into accessible audio files without requiring manual recording.
Our engineering team understands the technical constraints of learning management systems and ensures reliable integration for long-form educational content processing.
Editorial Team
We are engineers and instructional designers who build tools specifically for educational workflows. Our team combines technical expertise with pedagogical understanding to ensure our API meets the needs of course creators.
Mission Statement
Our goal is to provide a reliable, straightforward API that allows educators to convert large volumes of text into audio efficiently. We aim to reduce the barrier to creating accessible course materials by automating voice synthesis.
Independence
CursVoice operates as an independent storefront, not affiliated with OpenAI, ElevenLabs, or other major brands. We use the OpenAI SDK structure for compatibility but maintain our own infrastructure, pricing, and key management system.
Voice Licensing
We use licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox. All eight voice presets—including Aria, Nova, and Atlas—are derived from these sources. This approach ensures consistent, high-quality synthetic speech suitable for educational materials without requiring manual recording sessions for every course module.
LibriTTS-R Source
Our voice models are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0). This dataset provides clean, high-quality speech data optimized for text-to-speech synthesis, ensuring clarity and natural pacing for instructional content.
CC BY 4.0 License
The LibriTTS-R recordings are licensed under Creative Commons Attribution 4.0. We include this attribution in our documentation, ensuring that our usage of these voice assets remains transparent and compliant with open licensing standards for educational distribution.
Public Domain Recordings
All voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and readings from LibriVox public-domain audiobook recordings. This combination allows us to offer diverse vocal tones, from warm narrators to neutral news readers, using legally clear source material.
Data Policy
CursVoice processes your input text exclusively to generate the requested audio file. We do not use your educational content, textbooks, or course materials for model training or to improve our voice synthesis engines. Your data remains isolated to the specific generation request.
Input Data Usage
Text sent to the API is used solely for the immediate production of the audio file. Once the synthesis is complete, the input text is not retained for training purposes or future model development.
Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery.
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 based on the $0.01 per 1,000 characters rate.
Technical Limits
CursVoice is engineered for reliability, not infinite scale. Understanding these constraints ensures your educational audio pipelines run smoothly without unexpected interruptions or delays during peak usage.
Rate Limits
Each API key is capped at 60 requests per minute. If you have never topped up your account, this limit is stricter at 10 requests per minute. This ensures fair usage for all independent educational creators.
Character Limits
Each API request accepts up to 4,096 characters of input text. For longer textbooks or course modules, you must split the text into chunks and concatenate the resulting audio files. Spaces and punctuation count toward this limit.
- Maximum input: 4,096 characters per request
Processing Speed
Generation speed is approximately real-time (25 characters per second) for long texts. Short phrases may take a few seconds to process. Requests are processed sequentially, so high load may introduce queuing delays.

Support Channels
Support is handled via email only. We do not offer phone lines, live chat, or dedicated account managers, keeping our structure lean and cost-effective for educational institutions.
Email Support
Send inquiries regarding API integration, billing discrepancies, or voice selection to our support team. This single channel ensures your request is logged and tracked without the noise of multiple communication streams.
No Phone Support
There is no phone number or real-time voice support. For complex technical issues, detailed context provided via email allows our engineers to diagnose and resolve problems more accurately than a brief call.
Response Time
Response times vary based on current volume. We aim to address all technical and billing inquiries promptly during business hours. Please check your spam folder if you do not receive a reply within 24 hours.
Contact Information
Email Address
All communication regarding CursVoice is handled exclusively via email. We do not maintain a phone line or live chat support, ensuring that every query is logged and can be referenced later. Send your messages to [email protected].
Address
CursVoice operates as a cloud-based API service and does not publish a specific physical mailing address. Our infrastructure is distributed, and business correspondence is managed digitally through our support channels.
Queries
Whether you have technical questions about character limits, billing inquiries, or details about our educational use cases, please include your account details and a clear description of the issue in your email. Our engineering-focused team reviews all incoming messages to provide precise answers without unnecessary delay.
Affiliations and Certifications
CursVoice is an independent storefront for the TTS API, not affiliated with OpenAI, Google, Amazon, or Microsoft. We operate separately and do not claim endorsement from any major tech brand.
Unlike enterprise providers, we do not hold specific certifications such as SOC 2, HIPAA, or GDPR certificates. Our infrastructure is designed for simplicity and direct API access rather than regulated compliance frameworks.
OpenAI Affiliation
We are not affiliated with OpenAI. Although our API endpoint and request shape mirror the OpenAI speech endpoint, allowing you to use the official OpenAI SDKs by simply changing the base_url, we are a separate entity with our own keys, pricing, and voice models.
Certifications
We do not maintain external certifications like SOC 2, HIPAA, or specific GDPR certificates. Our data policy is transparent: input text is used only for synthesis and not for training, and generated audio is returned in the response without long-term storage.
SLA Status
There is no formal Service Level Agreement (SLA) or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. We aim for reliability but do not promise specific availability percentages or enterprise contracts.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The request shape is identical to industry standards, meaning minimal code changes are needed to switch or integrate.
23 languages
Any voice speaks any of these languages.
