Frequently asked questions
Who runs FableSays?
FableSays is an independent storefront for the same text-to-speech API used across our network. We are not affiliated with OpenAI, ElevenLabs, or any other major brand. We focus on providing reliable text-to-speech capabilities for teachers and methodologists, ensuring simple integration and clear voices for educational content.
Are the voices licensed?
Yes, our eight voice presets are based on licensed recordings from LibriTTS-R, which is available under the CC BY 4.0 license. These voices originate from LibriVox public-domain audiobook readings. Each generated audio file also carries an inaudible watermark to mark it as synthetic speech, ensuring transparency in usage.
Do you use my data for training?
No. 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, character count, and status, solely for billing purposes and do not retain the actual content.
How can I contact support?
Support is available by email only. We do not offer live chat or phone support. You can reach our team via the contact page or by emailing us directly. Please include your API key and details about your issue to help us assist you efficiently.
Is there a phone number?
No, there is no phone number for FableSays. All support is handled via email. We do not provide live chat or voice support channels. For urgent matters, please email us directly. We aim to respond to all inquiries promptly through our written support channel.
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. Our service is provided as-is, without certifications like SOC 2 or HIPAA. We focus on delivering reliable API access for teachers and methodologists without complex service level commitments.
Are you affiliated with OpenAI?
No, FableSays is not affiliated with OpenAI. We simply use a request shape similar to the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base URL to our API endpoint. We are an independent provider of a text-to-speech API for education.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on recordings from LibriTTS-R, which uses this license. This allows us to offer clear, licensed voices for your educational texts.
Who We Are
FableSays is an independent storefront dedicated to providing reliable text-to-speech capabilities for educational settings. We prioritize clarity and accessibility, ensuring that teachers and methodologists have the tools they need to bring texts to life for their students without unnecessary complexity.
Independent Editorial Team
We operate independently, focusing solely on delivering a robust API tailored for classroom use.
- Focused on educational workflows
- No corporate bloat
- Direct developer support
Focus on Education
Our primary audience includes teachers and methodologists who require clear, accurate audio for children's stories and fairy tales. We design our voice presets to be clear and easy to understand, supporting Japanese and other supported languages in a classroom environment.
Teacher-First Approach
We simplify integration so you can spend time teaching, not debugging. By offering straightforward pricing and clear documentation, we ensure that schools and individual educators can access high-quality synthetic speech without navigating complex enterprise contracts or hidden fees.
Voice Licensing
Our voices are derived from the LibriTTS-R dataset, ensuring a foundation built on established, high-quality speech recordings. This approach guarantees consistent, clear audio suitable for educational contexts without relying on proprietary, black-box models.
We provide transparency regarding the origin of our synthetic voices, allowing educators to understand exactly where the audio data comes from and how it is licensed for classroom use.
LibriTTS-R Dataset
The core of our voice engine is the LibriTTS-R dataset, which provides the raw audio material for our eight preset voices.
Using established datasets ensures that our voices maintain consistent quality and natural intonation, which is critical for keeping students engaged during lesson planning and accessibility reading.
- Based on established speech recordings
- Curated for high-fidelity synthesis
- Supports eight distinct voice presets
CC BY 4.0 License
The LibriTTS-R dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows us to legally use these recordings as the basis for our TTS engine.
Users of our API receive generated audio files that carry an inaudible watermark identifying them as synthetic speech, maintaining clarity about the audio's origin.
Public Domain Source
The underlying recordings in LibriTTS-R originate from LibriVox, which hosts public-domain audiobook readings.
This licensing structure supports our mission to provide accessible, reliable tools for teachers without restrictive proprietary constraints on the voice data itself.
Data Policy
When you send text to FableSays, our system processes it solely to generate the requested audio file. The input is not stored permanently and is used exclusively for that immediate synthesis task. This ensures that your lesson plans and teaching materials remain private during processing.
We do not use your input text to train or improve our models. Your data is transient, existing only long enough to produce the audio response. Once the audio is generated and returned, the text is not retained for future model improvement, keeping your educational content distinct from our training data.
Input Text Usage
Text is processed strictly to create audio. Input text is not stored permanently; it is used only to produce the audio and is not stored.
Your lesson content remains yours; we do not claim rights to it for other uses.
No Training on Data
Input text is not used for model training. Generated audio is not stored. This keeps your specific educational materials separate from our voice engine’s learning process.
You retain full control over your content without contributing it to our dataset.
Metadata Retention
We keep request metadata, including timestamp, character count, and status, solely for billing and usage tracking. This ensures accurate charges for your API key.
No personal identifiers are linked to the text content itself in these records.
- Timestamp of request
- Character count processed
- Request status (success/failure)
Technical Limits
The API delivers complete audio files rather than streaming partial chunks in real time. Requests are processed sequentially, so under load a request may wait in a queue. Typical generation speed is roughly real time, producing about 25 characters of text per second for long texts, while short phrases take a few seconds to render.
The service does not support SSML tags for granular control over pronunciation or pacing. You cannot insert pauses or emphasize specific words via markup. The API also limits accounts to a single active API key at any given time; you can issue a new key anytime, but the old one stops immediately.
No Streaming Support
The API delivers complete audio files rather than streaming partial chunks in real time. Requests are processed sequentially, so under load a request may wait in a queue. Typical generation speed is roughly real time, producing about 25 characters of text per second for long texts, while short phrases take a few seconds to render.
No SSML
Unlike some competitors, the service does not support SSML tags for granular control over pronunciation or pacing. You cannot insert pauses or emphasize specific words via markup.
Single Key Per Account
The API also limits accounts to a single active API key at any given time; you can issue a new key anytime, but the old one stops immediately.

Contact and Support
For technical questions, billing inquiries, or integration support, our team is available via email. We handle all communications centrally to ensure consistent, documented responses for educators and developers alike.
Email Support Only
We do not offer phone lines or interactive voice response systems. All requests are managed through our dedicated support email address, allowing for clear written records of your specific TTS integration issues.
No Live Chat
Unlike many SaaS platforms, we do not maintain live chat widgets on our site. This reduces noise and ensures that every query receives a thoughtful, detailed response from a human specialist rather than a bot.
Response Times
During peak periods or holidays, response times may extend slightly, but we prioritize resolving integration blockers for teachers quickly.
- Standard response: within 24 hours
- No 24/7 guarantee
- Priority support for billing issues
Mission and Values
FableSays exists to ensure educational texts are accessible to all students, regardless of reading ability or visual needs. We provide a reliable text-to-speech API that supports lesson planning and classroom accessibility with clear voices.
Our mission is rooted in practicality: helping teachers and methodologists save time on reading aloud while maintaining high-quality audio standards for educational materials.
Accessibility First
We prioritize clear, natural-sounding voices that support diverse learning needs. Our API enables educators to convert lesson texts into audio, making content available to students with visual impairments or reading difficulties.
- Supports 23 languages, including Japanese
- Ideal for lesson planning and accessibility
Transparency in Pricing
We charge $0.01 per 1,000 characters, with no hidden fees or subscriptions. Failed requests are free, and your balance never expires. You only pay for what you use, making it easy to budget for classroom audio needs.
- $10 per 1 million characters
- No monthly plans or minimum spend
Simplicity in Integration
Our API follows a familiar format, allowing you to use standard HTTP requests or the OpenAI SDK with a simple base URL change. We provide clear documentation and a ready-to-use curl example to get started quickly.
No complex setup, no custom SDKs to manage—just send text and receive audio.
- Standard JSON body
- Works with OpenAI SDKs
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. It works well for young adult fiction or modern stories where a traditional fairy tale voice might feel too juvenile.
23 languages
Any voice speaks any of these languages.
