Frequently asked questions
Who runs BookRead API?
BookRead API is operated by an independent entity providing a cloud text-to-speech API. Accounts are created per site, with support handled exclusively via email. There is no live chat or phone support available. The service is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We focus on delivering reliable synthetic voice generation for audiobook producers and self-publishing professionals without infrastructure overhead.
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 sources ensure clear licensing. Each generated audio file contains an inaudible watermark marking it as synthetic speech. We do not offer custom voice cloning or emotion tags, maintaining a consistent and predictable audio output for your projects.
Do you sell user data?
No, we do not sell user data. Input text is used solely to produce the audio and is not used for training models. Generated audio is returned in the response and is not stored on our servers. We retain request metadata, including time, character count, and status, strictly for billing purposes. Your creative content remains private and secure during processing.
How long is my text stored?
Input text is processed to generate audio and is not stored long-term. We retain request metadata, such as timestamp, character count, and status, for billing verification. Generated audio is returned in the response and is not stored by our infrastructure. This ensures your specific text inputs remain transient, supporting efficient audio production workflows for audiobook and self-publishing projects.
Is there a customer success manager?
No, we do not assign dedicated customer success managers. Support is provided via email only. There is no phone number or live chat available for immediate assistance. This structure keeps our operational costs low, allowing us to offer transparent billing and predictable pricing. Our team handles all inquiries through standard email channels to ensure consistent and documented support for every user.
Can I request a specific voice feature?
We do not offer custom voice features or voice cloning. The API provides eight fixed presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. You cannot upload your own voice or design custom voices. Features like SSML, phoneme dictionaries, and emotion tags are not supported. Requests are processed using these standard presets to maintain reliability and predictable audio quality.
Do you offer bulk discounts?
No, we do not offer bulk discounts or volume-based pricing tiers. The rate is a flat $10 per 1 million characters ($0.01 per 1,000 characters). There are no monthly plans, seats, or minimum spend requirements. Failed requests are free, but volume does not reduce the per-character cost. This transparent model allows you to scale production without negotiating complex discount structures.
Is the API open source?
No, the API is not open source. We do not provide an official SDK of our own; you should use the OpenAI SDK or plain HTTP requests. There are no mobile SDKs, WordPress plugins, or browser extensions. The service is a proprietary cloud API. You interact with it via standard endpoints, changing the base URL to our API domain for integration into your workflows.
What is the company's legal structure?
The specific legal structure is not disclosed. We operate as an independent storefront for the text-to-speech API. Accounts are created per site, and we do not provide enterprise contracts or SLAs. We do not hold specific certifications. Our focus is on providing reliable, transparent billing and high-fidelity synthetic voices for content creators without complex corporate overhead.
Do you have an office?
We do not list a physical office location. Support is handled exclusively via email, with no phone number or live chat. We focus on delivering the API infrastructure rather than maintaining physical premises.
Our Mission
BookRead API delivers a reliable, transparent text-to-speech API tailored for audiobook producers and self-publishing professionals. We enable creators to scale audio production without infrastructure overhead, focusing on clear licensing and predictable billing for synthetic voice generation.
Empowering content creators
Our technology supports independent authors and production studios in converting written content into high-fidelity audio. By providing 23 languages and eight distinct voice presets, we allow creators to maintain consistent quality across diverse projects without managing complex backend systems.
Simplifying audio production
We eliminate the need for specialized hardware or software installations. By sending text via a standard API request, you receive an audio file ready for distribution. This streamlined workflow reduces technical barriers, allowing you to focus on narrative structure and editing rather than audio engineering.
Transparent technology
Pricing is straightforward: $10 per million characters, with failed requests refunded in full. We do not hide fees or impose minimum spends. Our billing structure ensures you only pay for successful synthesis, providing clear visibility into production costs for every audiobook or content piece.
Voice Licensing
BookRead API delivers high-fidelity synthetic voices grounded in transparent, verifiable licensing. Our audio models are derived from the LibriTTS-R dataset, ensuring that every voice preset—whether Aria’s warm narration or Atlas’s neutral tone—originates from licensed source material.
We prioritize legal clarity for audiobook producers and self-publishing professionals. By using openly licensed data, we eliminate ambiguity regarding voice ownership, allowing you to scale audio production with confidence. This approach ensures that the synthetic voices you generate are built on a solid, documented foundation.
LibriTTS-R source
Our voice presets are generated from the LibriTTS-R dataset, which contains high-quality speech recordings. This dataset serves as the source material for our TTS engine, ensuring consistent audio quality across all eight voice models. The data is processed to create distinct vocal characteristics.
- High-quality speech recordings as the core training material
- Processed to ensure distinct vocal characteristics
- Maintains natural prosody and clarity
CC BY 4.0 license
The LibriTTS-R dataset is licensed under Creative Commons Attribution 4.0 International. This means the source recordings are freely available for use and modification, provided appropriate credit is given. We leverage this open license to provide you with a reliable, legally sound voice API without hidden licensing fees for the underlying voice models.
Public domain recordings
Many of the voices in our dataset are based on recordings from LibriVox, which are in the public domain. These recordings feature readers narrating classic texts, providing a rich variety of vocal styles. By building on these public domain sources, we offer a diverse range of voices—from the soft storytelling of Luna to the energetic promo style of Felix—without the need for expensive exclusive voice contracts.
- Based on LibriVox public domain readings
- Diverse range of vocal styles
- No expensive exclusive voice contracts
Data Policy
BookRead API processes input text strictly to generate the requested audio file. The service does not retain your source text after synthesis is complete, ensuring that your narrative content remains private and is not repurposed for other uses.
Input text usage
Your text is transmitted to the synthesis engine solely for the purpose of creating the audio output. Once the audio file is generated and returned in the response, the input text is not stored for long-term retention.
No training data retention
We do not use your input text or generated audio to train our models or improve the voice engine. Your content remains yours, with no risk of it being incorporated into our training datasets or used to create derivative voices.
Metadata retention for billing
We retain request metadata, including timestamp, character count, and status, exclusively for billing and usage tracking purposes. This data ensures accurate invoicing based on the 4,096-character request limits and supports account management without storing the actual audio or text content.
Technical Infrastructure
BookRead API operates as a cloud-based service, eliminating the need for clients to manage underlying infrastructure or server scaling. This architecture allows audiobook producers and self-publishing professionals to integrate voice synthesis directly into their production pipelines without hardware overhead.
Cloud-based API
The service processes requests through a standardized cloud endpoint. By offloading computational requirements to our servers, teams can focus on content creation rather than server maintenance.
OpenAI SDK compatibility
The API endpoint structure mirrors the OpenAI speech endpoint specification. This design allows developers to use official OpenAI SDKs by simply adjusting the base URL to https://api.regal33.info/v1. This compatibility reduces integration time for existing workflows.
Rate limit management
Requests are processed sequentially, meaning performance depends on current server load. New accounts start with a limit of 10 requests per minute, increasing to 60 requests per minute after the first top-up. This structure ensures fair resource distribution during peak production periods.

Support and Contact
BookRead API provides email-only support for all inquiries regarding API usage, billing, or technical issues. There is no telephone support number available for direct calls. All communication is handled asynchronously through our dedicated support email address to ensure clear documentation of your request.
Email-only support
We do not offer live chat or phone support. This approach allows us to maintain detailed records of each interaction and provide thorough, written responses that you can reference later. Please include your API key and a clear description of the issue when emailing us.
No live chat
Our support model relies entirely on email correspondence. We avoid real-time chat to ensure that complex technical questions are answered with precise, documented solutions rather than quick, potentially vague verbal assurances. This method suits audiobook producers who prefer asynchronous communication.
Response time expectations
Support responses are typically provided within 24 hours during standard business days. During high-volume periods, response times may vary slightly. We prioritize technical and billing inquiries to minimize disruption to your audio production workflow. For urgent API key issues, please specify this in the subject line.
Limitations and Honesty
We prioritize transparency regarding our technical boundaries. Our API processes requests sequentially, which means under load, synthesis may queue. Long texts are split into 4,096-character segments and joined, taking roughly real-time duration. Short phrases require a few seconds regardless of length.
No streaming support
We do not offer WebSocket or real-time partial audio streaming. You receive the complete audio file after synthesis finishes. This ensures reliable delivery for audiobook production workflows where file integrity matters more than instant playback.
No SSML support
Our interface does not parse SSML tags for pronunciation or prosody control. You control pacing via the speed parameter (0.25–4.0) and select from eight distinct voice presets. Custom pronunciation dictionaries or phoneme-level adjustments are not available.
No custom voice cloning
We do not offer voice cloning or upload-your-own-voice features. All outputs use our eight licensed presets derived from LibriTTS-R recordings. We do not provide bespoke voice design services.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. A mismatch between the voice’s inherent tone and the listener’s age or preference can reduce engagement, regardless of audio fidelity.
23 languages
Any voice speaks any of these languages.
