Independent Text-to-Speech API for Audiobooks

By ReadCast editorial team · Updated 2026-11-19

ReadCast API is an independent text-to-speech service built for independent authors and audiobook narrators who need consistent quality without enterprise contracts. This page explains our mission to simplify the production pipeline from manuscript to audio file using open standards and predictable character-based pricing.

We provide a reliable cloud API that works with standard protocols, ensuring you retain full control over your audio assets. Read on to learn about our voice licensing, data privacy practices, and how our support structure is designed to serve content creators effectively.

Independent Text-to-Speech API for Audiobooks

Frequently asked questions

Who runs ReadCast API?

ReadCast API is an independent storefront for a cloud text-to-speech API. We operate as a standalone service tailored for independent authors and audiobook narrators. Our infrastructure is separate from major tech brands, providing a direct, character-based billing model without enterprise contracts or complex subscription tiers.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These sources include public-domain audiobook readings from LibriVox. The voices cover diverse styles, from warm narrators to energetic promo styles, ensuring consistent quality for your content creation needs.

Do you use my text for training?

No. Input text is used exclusively to produce the requested audio file. We do not use your submitted text for model training or improving future algorithms. Once the audio is generated and returned in the response, the input text is not retained for training purposes.

How is my data stored?

Generated audio is returned in the response and not stored on our servers. We retain request metadata, including time, character count, and status, strictly for billing and usage tracking. This ensures accurate invoicing based on your consumption of the API service without keeping your content.

Is this site affiliated with OpenAI?

No. ReadCast API is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We simply use a request shape similar to the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL. Our pricing and voice engine are entirely separate.

How can I contact support?

Support is available via email only. We do not offer a phone number, live chat, or SLA guarantees. For issues regarding your account, billing, or API usage, please send an email to our support address. We aim to respond to your inquiries directly and efficiently.

Do you have a physical office?

We do not provide on-premise installation options. ReadCast API is a cloud-based service accessible via our API endpoints. Our infrastructure is distributed, allowing you to generate audio from anywhere without needing to manage local servers or physical hardware locations.

Are the voices licensed for commercial use?

Yes. The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. This licensing structure supports commercial use for your generated audio files. You can use the synthesized speech in audiobooks, podcasts, or other commercial projects without additional licensing fees for the voice itself.

Our Mission

Sound wave illustration for: Our Mission

ReadCast API delivers reliable, character-based text-to-speech designed for independent authors and audiobook narrators. We prioritize consistent quality and predictable costs, eliminating the need for complex enterprise contracts. Our goal is to support creators who value transparency and control over their audio production pipeline.

We simplify the journey from manuscript to final audio file by using open standards and straightforward pricing. By focusing on the specific needs of self-publishing professionals, we ensure that every generated voice file meets professional standards without hidden fees or unexpected usage spikes.

Empowering Creators

Empowering Creators

Independent narrators often face high barriers to entry for studio-quality audio. ReadCast API lowers this barrier by providing an accessible cloud API that anyone can integrate. You retain full ownership of the generated audio, allowing you to distribute audiobooks across any platform.

  • Full ownership of generated audio files
  • No platform-specific lock-in
  • Direct integration with self-publishing workflows

Simplifying Production

Simplifying Production

Our API handles the technical complexity of synthesis, letting you focus on content. With a simple POST request, you receive high-quality audio in formats like MP3, WAV, or FLAC. The system automatically handles character limits and queue management, processing requests one after another.

  • Standard JSON API compatible with OpenAI SDKs
  • Support for 8 distinct voice presets
  • Automatic handling of long-text segmentation

Transparent Pricing

Transparent Pricing

We charge $0.01 per 1,000 characters, with no monthly plans or minimum spend. Failed requests are free, and your balance never expires. This model allows you to scale your audiobook production exactly according to your output, paying only for what you use.

  • $10 per 1 million characters
  • No hidden fees or VAT invoices
  • Top-ups via USDT (TRC-20)

The Technology

Sound wave illustration for: The Technology

ReadCast API delivers cloud-based text-to-speech synthesis, allowing you to send text and receive audio files without managing local infrastructure. The system handles character splitting into parts of up to 4096 characters and joins the audio files.

Cloud-Based TTS

Cloud-Based TTS

Your input text is processed remotely and returned as an audio file. Failed requests incur no charge, and typical generation speed is roughly real-time, averaging 25 characters of text per second of audio.

OpenAI Compatible

The API endpoint POST https://api.link02.info/v1/audio/speech mirrors the OpenAI speech endpoint structure. You can use official OpenAI SDKs by simply changing the base_url to https://api.link02.info/v1 and swapping in your ReadCast key.

Standard Protocols

We use standard JSON bodies and HTTP headers. Authentication requires a Bearer token, and requests support standard formats like MP3, WAV, OPUS, FLAC, and PCM, ensuring easy integration into your existing publishing pipeline.

Voice Licensing

Sound wave illustration for: Voice Licensing

ReadCast API voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. These voices are not custom-designed for our platform but are selected for their natural cadence and clarity, providing a consistent baseline for audiobook narration.

LibriTTS-R Source

The dataset provides high-quality, clean audio samples that form the foundation of our eight voice presets. By using established speech data, we ensure that each voice maintains a stable tonal quality across different languages and speeds without requiring complex proprietary synthesis models.

CC BY 4.0 License

All voice data is licensed under Creative Commons Attribution 4.0. This allows you to use the generated audio commercially. You can use the generated audio commercially.

LibriVox Origins

The recordings originate from LibriVox, a platform dedicated to public domain audiobooks. This heritage ensures that the voices are rooted in public domain literature, offering a neutral and professional sound ideal for narrating classic and modern texts alike.

Data Privacy

Sound wave illustration for: Data Privacy

ReadCast API treats your manuscript as a transactional asset, not a training resource. When you submit text for synthesis, that input is used exclusively to generate the audio file returned in the response. We do not ingest your unique narrative content into our model’s training dataset, ensuring that your unpublished works remain distinct from the underlying voice engine.

No Training Data

Your input text is processed solely for the purpose of producing the requested audio output. Unlike many modern AI services, we do not use your submitted narratives to fine-tune or improve our voice models. This ensures that your specific creative works remain proprietary and are not reused to train future iterations of our synthesis engine.

Metadata Retention

Request metadata, including timestamp, character count, and status, is retained for billing accuracy. This data allows us to verify usage against your balance and ensure accurate invoicing for the characters consumed. This information is kept only as long as necessary to resolve billing inquiries or audit your account history.

Audio Storage

Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Generated audio is returned in the response and not stored. You retain full ownership of the output, and we hold no copy of your final audiobook files.

Data Privacy

Contact and Support

Sound wave illustration for: Contact and Support

ReadCast API relies on email for all customer inquiries. We do not maintain a live chat widget or a direct phone line, ensuring that every question is logged and addressed with care rather than rushed through a queue.

This approach suits independent authors and narrators who prefer asynchronous communication. You can reach us at [email protected] for technical issues, billing questions, or general inquiries.

Email Support

Our email support is the single point of contact for all users. Whether you need help with your API key or have questions about voice selection, our team handles every ticket directly.

No Live Chat

We do not offer live chat or instant messaging services. This decision keeps our operational costs low and passes those savings on to you through predictable, character-based pricing without hidden service fees.

Response Times

We aim to respond to all emails within one business day. During high-volume periods, responses may take slightly longer, but every message receives a thorough and accurate reply.

Independence and Affiliations

Sound wave illustration for: Independence and Affiliations

ReadCast API operates as an independent storefront, distinct from the major technology providers often cited in comparisons. While our API endpoint structure mirrors the OpenAI speech format for ease of integration, we are not owned by, affiliated with, or endorsed by OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in industry comparisons.

Our infrastructure is self-managed, ensuring that our pricing, voice models, and service terms remain solely under our control. This independence allows us to offer a straightforward, character-based pricing model without the complexity of enterprise contracts or tiered feature locks found in larger platforms.

Not Affiliated with OpenAI

Although our API request shape matches the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply changing the base_url to https://api.link02.info/v1, we are a separate entity. Our models, voices, and infrastructure are entirely our own.

Independent Storefront

This site is an independent storefront for the ReadCast API. We handle billing, key issuance, and voice management directly. Our pricing is transparent and character-based, without hidden fees or tiered limitations. We do not impose minimum spends or require monthly subscriptions, keeping our focus on serving independent authors and content creators.

No Vendor Lock-in

Because we use standard HTTP protocols and JSON bodies compatible with widely used SDKs, switching away from ReadCast API is straightforward. Your integration code relies on common standards, not proprietary protocols. You retain full ownership of your generated audio files, which are returned directly in the response and not stored by us for long-term retention.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The ability to specify language codes ensures accurate pronunciation for non-native speakers, enhancing accessibility for diverse student demographics.

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. curl documentation
  3. openai-python on GitHub
  4. ISO 639 language codes
  5. Tether (USDT)
  6. LibriTTS-R corpus (OpenSLR 141)
  7. IETF RFC 7845: Ogg Opus
  8. Node.js documentation
  9. TRON developer hub: TRC-20
  10. Creative Commons Attribution 4.0
  11. openai-node on GitHub
  12. FFmpeg documentation

More on this site