About the Independent Text-to-Speech API Service

By ScribeRead editorial team · Updated 2026-11-18

ScribeRead operates as an independent storefront for the ScribeRead text-to-speech API, designed specifically for self-publishers and no-code developers who need to convert large PDF documents into high-quality audio files. This page outlines our operational structure, data handling policies, and the technical foundation that supports reliable audiobook production without manual formatting overhead.

You will find details on our voice licensing sources, including the LibriTTS-R dataset and CC BY 4.0 terms, alongside our strict data privacy stance. We explain our cloud infrastructure, support model, and why we remain independent from major tech brands. This information is provided for teams evaluating the API for long-form content creation and character-based billing needs.

About the Independent Text-to-Speech API Service

Frequently asked questions

Who owns the voices used in the API?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We do not claim ownership of the original recordings, but we provide the synthetic audio generation service based on these licensed assets.

Do you sell user data?

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. We do not sell this data or use it for other commercial purposes.

How can I contact you?

Support is available by email only. We do not offer a phone number or live chat. You can reach our team via the contact page or by emailing us directly. Response times may vary depending on current support volume, but we aim to address all inquiries efficiently.

Are you affiliated with OpenAI?

We are not affiliated with OpenAI. Our API endpoint structure matches the OpenAI speech endpoint format, allowing you to use official OpenAI SDKs by changing the base URL. However, we are an independent provider using our own engine and pricing model, distinct from OpenAI’s services and infrastructure.

Where is your server located?

We do not provide specific details about our server locations or data-center choices. Our cloud API is accessible globally via standard HTTP requests. We do not offer on-premise installations or allow customers to choose specific geographic regions for data storage or processing within our current service offering.

Do you have a physical office?

We do not list a physical office address. As an independent API provider, we operate primarily through our web platform and email support. We do not have a public-facing office for visitors, and our team manages all operations remotely through our digital infrastructure and communication channels.

Are your voices based on real people?

Yes, every voice is based on licensed recordings from LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech. While the source material comes from real human readers, the output is processed through our TTS engine to create distinct, synthetic voice presets.

Our Mission

Sound wave illustration for: Our Mission

ScribeRead provides a character-based text-to-speech API designed for self-publishers and no-code developers. We enable the conversion of large PDF documents into high-quality audio files without manual formatting, handling the volume and complexity of long-form content creation.

Democratizing audiobook production

Democratizing audiobook production

Our API allows creators to generate professional audio from text inputs up to 4096 characters. By supporting 23 languages and eight distinct voice presets, we provide the infrastructure needed for diverse audiobook production without requiring specialized technical teams.

Supporting no-code creators

Supporting no-code creators

We offer a straightforward REST API compatible with standard OpenAI SDKs. This allows users to integrate TTS capabilities directly into their workflows via simple HTTP requests, eliminating the need for custom software development or complex coding environments.

Providing reliable API infrastructure

Providing reliable API infrastructure

The service processes requests sequentially with a queue management system to handle load. With a rate limit of 60 requests per minute, the API ensures consistent delivery of audio files, maintaining stability for automated publishing pipelines.

Voice Licensing and Sources

Sound wave illustration for: Voice Licensing and Sources

ScribeRead utilizes voice presets derived from the LibriTTS-R dataset, which comprises recordings from LibriVox public domain audiobooks. This foundation ensures high-quality, natural-sounding speech for our eight distinct voice presets used in text-to-speech generation.

Each voice is based on licensed recordings that adhere to specific copyright standards, allowing us to provide consistent audio output for self-publishers and developers without complex licensing negotiations for individual tracks.

LibriTTS-R dataset details

LibriTTS-R dataset details

The LibriTTS-R dataset provides the raw audio material for our voice models. These recordings are sourced from LibriVox, offering a diverse range of vocal styles suitable for narrations, documentaries, and instructional content.

CC BY 4.0 licensing terms

Our voice assets are built upon the CC BY 4.0 license. This permits commercial use and modification, provided appropriate credit is given to the original authors and sources. This framework supports our character-based API model by ensuring clear legal standing for generated audio files.

LibriVox public domain sources

Many underlying recordings originate from the public domain via LibriVox, where volunteers read copyright-free books. This combination of public domain material and CC BY 4.0 licensed data allows us to maintain a stable, reliable voice library for long-form content creation.

Data Privacy Policy

Sound wave illustration for: Data Privacy Policy

ScribeRead processes your input text exclusively to generate the requested audio file. Once the synthesis is complete, the generated audio is returned in the response and is not stored on our servers. This ensures that your narrative content remains transient and secure during the creation process.

Input text usage for generation only

Your text is used solely for the immediate production of the audio file. We do not retain your raw text after the audio is delivered, ensuring that your manuscript content remains private and is not archived for other purposes.

No training on user data

We do not use your input text or generated audio for machine learning training. Your data is processed in real-time to fulfill your specific request and is not added to our training datasets, preserving the uniqueness of your content.

Metadata retention for billing

We retain request metadata, including timestamp, character count, and status, strictly for billing and usage verification. This data is used to calculate charges based on the $0.01 per 1,000 characters rate and to verify service delivery.

Technical Infrastructure

Sound wave illustration for: Technical Infrastructure

ScribeRead operates as an independent storefront for the same text-to-speech API, ensuring that our infrastructure is dedicated solely to reliable audio generation for self-publishers and no-code developers. We provide a consistent cloud-based environment that handles the volume and complexity of long-form content creation without relying on third-party platforms.

Cloud-based processing

Our API endpoints are hosted on cloud servers, allowing you to send text and receive audio files. The system processes requests sequentially, ensuring that each synthesis is completed accurately before moving to the next. This architecture supports the standard request shape used by official OpenAI SDKs, making integration straightforward for developers.

  • Cloud-hosted API endpoints
  • Standard JSON request processing
  • OpenAI SDK compatibility

Queue management system

Requests are processed one after another, meaning that under heavy load, a request may wait in a queue before generation begins. This sequential processing ensures stability but means that longer texts may take time to complete, typically roughly real-time (25 characters per second). Short phrases usually take a few seconds to generate.

  • Sequential request processing
  • Load-based queuing
  • Real-time generation speed

Audio generation standards

We generate audio files in multiple formats, including mp3, wav, opus, flac, and pcm. Each generated file carries an inaudible watermark that marks it as synthetic speech. For texts exceeding 4096 characters, the system splits the input into parts and joins the resulting audio files to deliver a complete, high-quality audio file.

  • Multiple output formats
  • Inaudible synthetic watermark
  • Automatic text splitting
Technical Infrastructure

Contact and Support

Sound wave illustration for: Contact and Support

ScribeRead operates as an independent API provider, maintaining a lean support structure designed for clarity and efficiency. We prioritize direct, asynchronous communication to ensure every inquiry is handled with precision, avoiding the delays often associated with larger, multi-tiered support teams.

Email support only

All support requests are managed exclusively via email. This channel allows our team to thoroughly review technical details, API usage patterns, and billing questions without interruption. Email support is the single point of contact for all issues, from integration bugs to account queries.

  • Primary method for all technical and billing inquiries
  • Detailed context provided for efficient troubleshooting
  • No phone or live chat available

No phone or live chat

We do not offer phone numbers or live chat widgets. This decision reduces overhead and ensures that support interactions are documented and searchable. You will not encounter hold times or be routed through automated menus. Every message is received and processed by a human specialist.

Response time expectations

High-volume periods may extend this time slightly. You will receive a confirmation that your message has been received, ensuring no query is lost in transit.

Company Structure

Sound wave illustration for: Company Structure

ScribeRead operates as an independent storefront, functioning as a direct vendor for the ScribeRead TTS API. This structure ensures that pricing, account management, and service terms are defined solely by our operational requirements without intermediary markup or third-party platform restrictions.

Independent storefront operation

Our independent model allows for transparent character-based billing and direct API access. Customers interact directly with the infrastructure, ensuring clear accountability for service delivery and data handling without the complexity of multi-tiered platform agreements.

No affiliation with major tech brands

We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Although our API endpoint mimics the OpenAI request shape for ease of integration, we are a distinct entity providing our own licensed audio engine.

Editorial team oversight

This oversight guarantees that pricing, voice descriptions, and usage limits remain precise and up-to-date for self-publishers and no-code developers relying on our infrastructure.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. His style keeps long-form non-fiction engaging without sacrificing clarity.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. FFmpeg documentation
  3. W3C WAI: making audio and video accessible
  4. IETF RFC 7845: Ogg Opus
  5. LibriTTS-R corpus (OpenSLR 141)
  6. Python documentation
  7. Node.js documentation
  8. openai-node on GitHub
  9. Creative Commons Attribution 4.0
  10. ISO 639 language codes
  11. MDN: Web Speech API
  12. Tether (USDT)

More on this site