Transforming Healthcare Communication with AI Voice Technology

By MediVoice editorial team · Updated 2026-11-19

This page explains how SaneReads supports healthcare teams in scaling patient guide production. We are an independent storefront for a cloud text-to-speech API designed for large clinical groups. You will find details on our voice origins, data handling, and technical constraints.

We built these tools to help you turn vast amounts of medical text into clear audio without the overhead of manual recording. Read on to understand our licensing model, privacy standards, and mission to simplify medical content creation for clearer patient communication.

Transforming Healthcare Communication with AI Voice Technology

Frequently asked questions

Who runs the SaneReads?

SaneReads is an independent storefront for a cloud text-to-speech API. We operate as a standalone service designed for healthcare teams, separate from major tech brands. We manage the infrastructure and support directly.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. These recordings provide the foundation for voices like Aria, Nova, and Felix, ensuring high-quality synthetic speech for your patient guides and clinical materials.

Is my data secure?

Input text is used only to produce audio and is not used for training. We keep request metadata like time and status for billing purposes. Generated audio is returned in the response and not stored on our servers, ensuring your clinical data remains private and transient.

Do you store my text?

No. Input text is used solely to generate the audio file and is not stored for training or other purposes. Only request metadata, such as timestamp and character count, is retained for billing accuracy. Your actual medical text content is not kept after generation.

Do you store my audio?

No. Generated audio files are returned directly in the API response and are not stored on our servers. This ensures that your clinical audio outputs remain transient, reducing data retention risks for sensitive patient guide content while keeping your workflow efficient and clean.

How can I contact support?

We offer support exclusively via email. There is no phone number, live chat, or ticketing system. Please reach out through the contact page for any questions regarding your API key, billing, or technical issues.

Do you have an SLA?

No, we do not offer a Service Level Agreement or uptime guarantee. Our service is designed for flexibility rather than enterprise-grade contractual obligations. While we strive for reliability, there is no formal contract ensuring specific availability percentages or financial credits for downtime.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. We simply use the same request shape as the OpenAI speech endpoint, allowing you to use their SDKs by changing the base URL. Our API, voices, and pricing are entirely separate from OpenAI’s products and infrastructure.

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 LibriVox, which uses this license. It allows us to use these public-domain audiobook readings to create our synthetic voice presets, ensuring high-quality audio sources while respecting the original creators' rights.

Do you have a physical office?

We do not have a physical office or on-premise installation option. SaneReads is a cloud-based service accessible via our API. This structure keeps overhead low and allows us to focus on providing a reliable, scalable text-to-speech solution for your healthcare team remotely.

Can I request a specific voice?

You can choose from our eight preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. We do not offer custom voice cloning or uploading your own voice. Each voice is a preset based on licensed recordings, suitable for various clinical and patient guide tones.

Is the team large?

We are an independent storefront. We do not have a large corporate structure or dedicated enterprise account managers. Our focus is on maintaining the API infrastructure and providing direct email support to ensure a responsive experience for our users.

Do you offer refunds?

Yes, failed requests are free. If synthesis fails, the charge is returned in full. We do not offer manual refunds for successful requests, but our billing system automatically credits your account for any errors, ensuring you only pay for successfully generated audio files.

How do I report a bug?

Please report bugs via email using our contact page. Since we do not have a dedicated ticketing system or live chat, email is our primary channel for technical issues. Include details about the API endpoint, request body, and error message for faster resolution.

Who we are

Sound wave illustration for: Who we are

SaneReads is an independent editorial and development team dedicated to building practical tools for healthcare communication. We focus on the specific needs of clinical content creation, ensuring that technical infrastructure supports medical accuracy and clarity.

Independent editorial and dev team

Independent editorial and dev team

Our team operates independently, combining editorial expertise with engineering precision. We build APIs that large healthcare teams can rely on for consistent, high-quality audio generation without external dependencies or corporate overhead.

Focused on medical video needs

Focused on medical video needs

We provide a TTS API that can be used for medical video production. By turning vast amounts of medical text into clear audio, we help teams create patient guides and clinical content at scale, reducing the need for manual recording sessions.

Building tools for large teams

Building tools for large teams

Our infrastructure supports large teams creating content at volume. We provide a reliable, straightforward API that integrates into existing workflows, allowing healthcare organizations to distribute audio materials efficiently while maintaining control over their content pipeline.

Voice licensing and origin

Sound wave illustration for: Voice licensing and origin

Our voice presets are built on licensed recordings from the LibriTTS-R dataset, providing a reliable foundation for medical narration. This approach ensures consistent audio quality across all eight voice presets without the need for continuous manual recording sessions.

Based on LibriTTS-R recordings

Based on LibriTTS-R recordings

We use the LibriTTS-R dataset as our core audio source. This provides a diverse range of vocal characteristics suitable for various clinical contexts, from calm instructional guides to energetic patient updates.

CC BY 4.0 license

The underlying recordings are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This allows us to distribute clear, high-quality synthetic speech for your healthcare teams while maintaining transparency about the audio origins.

Public domain audiobook sources

Many of the base recordings come from LibriVox public-domain audiobook readings. This heritage ensures that our voices are natural, well-articulated, and proven for long-form content delivery.

Data privacy and storage

Sound wave illustration for: Data privacy and storage

We prioritize data integrity for clinical teams. Our infrastructure ensures that the medical text you submit is processed solely to generate the audio file you receive. This input is never repurposed or used to train our underlying models, keeping your specific patient guides and clinical notes private to your immediate use case.

Input text not used for training

Your source text remains transient. We do not ingest your submissions into our training datasets, ensuring your proprietary medical content stays distinct from our model's general knowledge base.

Audio not stored after generation

Once the synthesis is complete and the audio file is returned in the response, we do not retain the generated audio on our servers. The file exists only in your local environment or downstream systems.

Metadata kept for billing only

We retain minimal request metadata, such as timestamps, character counts, and status codes. This data is stored exclusively for accurate billing and usage tracking, not for analytics or training purposes.

Technical limitations

Sound wave illustration for: Technical limitations

Our API is designed for batch processing rather than real-time interaction. You send a request and receive the final audio file, which is ideal for pre-generating patient guides or clinical content libraries before they are needed.

The system processes requests sequentially, meaning high-volume teams may experience brief queueing during peak times. This ensures fair resource distribution but requires planning for large-scale audio generation jobs.

No streaming or WebSocket

We do not support streaming audio chunks or WebSocket connections. The entire audio file is returned only after synthesis completes. This approach simplifies integration for teams using standard HTTP libraries and avoids the complexity of managing partial audio streams for pre-recorded medical content.

No SSML support

The API does not support Speech Synthesis Markup Language (SSML). You cannot use tags to control pauses, pronunciation, or emphasis manually. The voices interpret the text naturally based on the selected preset, which is sufficient for most clinical narration needs without complex markup.

Standard API latency

Generation speed is roughly real-time on long texts (about 25 characters of text per second of generation); short phrases take a few seconds. Short phrases may take a few seconds to process, while longer documents are split into parts and joined. Requests are processed one after another, so under heavy load, a request may wait in a queue before synthesis begins.

  • Approx. 25 characters of text per second of audio
  • Requests processed sequentially, not in parallel
  • Queuing possible during high demand periods
Technical limitations

Support and contact

Sound wave illustration for: Support and contact

We handle support via email only, ensuring detailed attention to your technical or billing questions without the noise of live queues. This approach suits healthcare teams who prefer documented, asynchronous communication for complex API integration issues or billing inquiries regarding TRC-20 top-ups.

Email support only

Send your queries to our support address. We prioritize clear, written responses that you can reference later during development or team training sessions.

  • No ticketing system overhead
  • Written record of all communications

No live chat or phone

We do not offer live chat widgets or phone numbers. This keeps our overhead low and ensures you get a thoughtful, complete answer rather than a quick, potentially incomplete verbal reply.

Response times vary

Response times depend on current request volume. During peak integration periods, responses may take longer than usual. We aim to address all medical and technical queries thoroughly, even if it takes extra time.

Our mission

Sound wave illustration for: Our mission

We build tools that let healthcare teams turn patient guides and clinical text into audio quickly. Our API handles the conversion so your staff can focus on care, not recording studios.

By automating voice generation, we help large teams produce consistent medical content at scale. This ensures patients receive clear, accurate information without the delay of manual narration.

Simplify medical content creation

Convert vast amounts of medical text into clear audio without manual recording overhead. Our API integrates directly into your workflow, allowing developers to generate speech from clinical notes or patient instructions with a simple request.

  • No complex equipment needed
  • Instant generation from text
  • Consistent voice quality

Enable scalable video production

Large healthcare teams often need to produce hundreds of videos. With our TTS API, you can generate audio files rapidly, supporting high-volume production without hiring additional voice actors or booking studio time.

  • Supports large teams
  • High character limits
  • Automated workflows

Ensure clear patient communication

Clear audio helps patients understand instructions better. Our voices are designed for clarity, reducing cognitive load for patients listening to medical information. We prioritize straightforward, neutral tones that convey information accurately.

  • Clear narration
  • Multiple languages
  • Adjustable speed

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Their upbeat, rapid cadence can obscure important medical details, especially for those with hearing impairments.

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. LibriTTS-R paper (arXiv 2305.18802)
  3. openai-python on GitHub
  4. openai-node on GitHub
  5. curl documentation
  6. ISO 639 language codes
  7. LibriVox public-domain audiobooks
  8. Creative Commons Attribution 4.0
  9. MDN: Web Speech API
  10. W3C WAI: making audio and video accessible
  11. IETF RFC 7845: Ogg Opus
  12. Node.js documentation

More on this site