About Clinical Audio: Independent Medical TTS API Storefront

By Clinical Audio editorial team · Updated 2026-11-18

Clinical Audio is an independent storefront providing a reliable text-to-speech API designed specifically for healthcare teams. This page explains our mission to make medical information accessible, details our voice licensing from LibriVox, and clarifies our data privacy commitments. We handle the volume and language diversity required for global medical communication without compromising on clarity.

If you are building large-scale audio patient guides or internal training materials, you will find our technical infrastructure, pricing structure, and support options here. We are not affiliated with major tech brands, ensuring a direct relationship and transparent operations for your clinical audio needs.

About Clinical Audio: Independent Medical TTS API Storefront

Frequently asked questions

What is Clinical Audio?

Clinical Audio is an independent storefront for a cloud text-to-speech API. We provide a reliable endpoint for healthcare teams to generate audio patient guides and training materials. The API accepts JSON requests and returns audio files, supporting multiple languages and voices without requiring complex infrastructure management.

Who owns the voices 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 use these licensed sources to create the eight voice presets available in the API, ensuring clear legal grounding for the synthetic speech generated for your medical content.

Are the voices based on real people?

Yes, the voices are synthesized from licensed recordings of real people. These recordings originate from LibriVox public-domain audiobook readings. Each generated audio file carries an inaudible watermark to mark it as synthetic speech, distinguishing it from original human recordings while maintaining high clarity for medical contexts.

Is my data used for training?

No. 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 like time and characters for billing purposes, ensuring your medical content remains private and secure during processing.

Is Clinical Audio affiliated with OpenAI?

No. Clinical Audio is an independent storefront. While our API endpoint shape matches the OpenAI speech endpoint for compatibility, we are not affiliated with OpenAI. We use our own engine and pricing model, clearly distinct from OpenAI’s services, ensuring you understand the specific provider of your TTS solution.

How do I contact support?

Support is available by email only. We do not offer live chat or phone support. For technical issues or billing questions regarding your Clinical Audio API usage, please send an email to our support address. We aim to respond to your inquiries promptly via this dedicated channel.

Is there a phone number for support?

No. Clinical Audio does not provide a phone number for support. All communication is handled via email. This approach allows us to maintain clear records of your requests and ensures that your technical or billing queries are addressed by our support team through written correspondence.

Do you have a physical office?

What is the CC BY 4.0 license?

CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on recordings under this license, allowing us to use and adapt the source material. This ensures that the underlying voice data is legally sourced from public-domain and licensed audiobook readings, providing a solid foundation for our API.

Where do the voice recordings come from?

The voice recordings come from LibriVox public-domain audiobook readings. These are licensed under CC BY 4.0. We use these specific sources to create the eight voice presets, ensuring that the synthetic voices are derived from real human recordings available in the public domain for broad usage.

Is the API hosted in a specific data center?

We do not offer data-center choice or specify a single physical location. Clinical Audio is a cloud API service. The infrastructure is managed to ensure reliability, but we do not provide details on specific data centers or offer on-premise installation options for your healthcare team’s internal networks.

Do you offer an SLA?

No. Clinical Audio does not offer a Service Level Agreement (SLA) or an uptime guarantee. We provide a reliable API for medical audio generation, but we do not contractually guarantee specific availability percentages. This allows us to maintain flexibility in our infrastructure management for independent storefront operations.

Are you HIPAA certified?

No. Clinical Audio does not offer certifications such as HIPAA or SOC 2.

Can I get a VAT invoice?

No. We do not provide invoices with VAT. Payments are made via USDT on the TRON network. We do not offer traditional billing methods like credit cards or PayPal, so VAT invoices are not generated. Your payment history and balance are visible in your account dashboard for transparency.

Do you have a WordPress plugin?

No. Clinical Audio does not offer a WordPress plugin. We provide a standard REST API endpoint compatible with the OpenAI SDK format. You can integrate our TTS service into your WordPress site using custom code or any HTTP client that supports JSON requests, without needing a dedicated plugin.

Is there a mobile app?

No. There is no official mobile app for Clinical Audio. We provide a web-based API and a storefront website. You can access your API key, balance, and usage statistics via your browser. Integration into mobile applications is done by calling our API directly from your app’s backend or client.

Can I clone my own voice?

No. We do not offer custom voice cloning for customers. You cannot upload your own voice to create a unique preset. You must choose from the eight available voice presets (e.g., Aria, Nova, Felix). This ensures consistent quality and licensing clarity for all generated medical audio content.

Do you support SSML?

No. Clinical Audio does not support SSML (Speech Synthesis Markup Language). You send plain text input, and the API controls pacing via the speed parameter. We do not offer phoneme dictionaries or custom pronunciation lexicons, keeping the integration simple for healthcare teams generating large-scale audio guides.

How do I report a bug?

You can report bugs by contacting our support team via email. Since we offer email-only support, please include details about the issue, your API key, and the request ID if available. Our team will review the report and assist you with any technical problems encountered during audio synthesis.

What is the editorial team's role?

Our mission in healthcare audio

Sound wave illustration for: Our mission in healthcare audio

Clinical Audio delivers a reliable text-to-speech API designed for healthcare teams creating large-scale audio patient guides and internal training materials. We handle the volume and language diversity required for global medical communication without compromising on clarity or data privacy.

Our platform transforms static medical text into clear, synthetic speech using licensed voice recordings, ensuring that complex clinical information reaches diverse patient populations effectively.

Making medical information accessible

Making medical information accessible

We convert text into audio files, enabling patients to listen to discharge instructions or medication guides. This reduces reading barriers for individuals with visual impairments or low literacy levels, ensuring critical health data is consumed accurately.

  • Converts up to 4096 characters of text per request into audio.
  • Supports 23 languages, including Spanish, French, and German, for global patient reach.
  • Generates realistic speech without requiring human voice actors for every update.

Supporting diverse patient populations

Supporting diverse patient populations

Healthcare teams often serve multilingual communities. Our API supports 23 languages, allowing you to produce patient guides in Arabic, Chinese, Hindi, and more using the same engine. This ensures consistent quality across diverse linguistic groups without hiring multiple voice talent pools.

  • 23 supported languages for global patient communication.
  • Automatic language detection or explicit ISO code setting for accuracy.
  • Consistent voice quality across all supported languages.

Empowering healthcare teams with tools

Our API integrates into your existing workflows. Teams can generate audio for training materials or patient education at scale. With a rate limit of 60 requests per minute (10 per minute before the first top-up), you can batch-process large volumes of medical text efficiently.

  • Standard JSON API compatible with OpenAI SDKs.
  • Simple pricing: $10 per 1 million characters.
  • No minimum spend or monthly subscriptions required.

Voice licensing and origins

Sound wave illustration for: Voice licensing and origins

Clinical Audio’s eight voice presets are derived from licensed recordings within the LibriTTS-R dataset. These voices provide the clear, distinct vocal profiles necessary for effective medical communication and patient education materials.

We ensure full transparency regarding our audio sources. Every generated file carries an inaudible watermark identifying it as synthetic speech, maintaining integrity in clinical communications.

Voices based on LibriTTS-R recordings

The eight available voices—aria, nova, luna, sage, felix, milo, atlas, and orion—are built directly from the LibriTTS-R dataset. This foundation ensures consistent acoustic quality across all language and voice combinations.

Licensed under CC BY 4.0

The voice recordings are based on the LibriTTS-R dataset, licensed under Creative Commons Attribution 4.0 International. This license allows us to use these recordings in our API.

Source: LibriVox public domain audiobooks

The underlying audio originates from LibriVox, a community of volunteers reading public domain books. By leveraging these public domain recordings, we provide synthetic voices without the complexity of proprietary voice cloning or custom recording sessions.

Voice licensing and origins

Data privacy and usage

Sound wave illustration for: Data privacy and usage

Clinical Audio is built for healthcare teams that need reliable, privacy-conscious audio generation. Our API processes text strictly to produce speech, ensuring that your patient guides and training materials remain secure throughout the workflow.

Input text used only for generation

When you send text to our API, it is processed solely to create the audio file. The input is used only to produce the audio and is not used for training.

No training on your data

We do not use your input text to train our models. Your specific medical terminology and patient narratives remain yours, preserving the uniqueness of your institutional knowledge without contributing to broader model datasets.

Generated audio not stored

Once the audio file is returned in the response, we do not store it. We keep request metadata—such as time, character count, and status—strictly for billing accuracy and service verification.

Technical infrastructure

Sound wave illustration for: Technical infrastructure

Clinical Audio operates as a cloud-based API endpoint, delivering synthesized audio directly via HTTP requests. This architecture allows healthcare teams to integrate TTS capabilities into existing electronic health record systems or patient education platforms without managing local infrastructure.

The system relies on a standard JSON request format, ensuring predictable and reliable data exchange. By adhering to established web standards, the API simplifies integration for engineering teams building large-scale audio workflows for global medical communication.

Cloud-based API endpoint

The core infrastructure is a cloud-based API endpoint. Teams can send text and receive audio files without maintaining dedicated servers, scaling effortlessly as patient guide volumes increase.

  • Hosted on scalable cloud infrastructure
  • No local server maintenance required
  • Designed for high-volume batch processing

Standard JSON request format

Requests follow a consistent JSON structure, making it easy to parse responses and handle errors. The endpoint accepts parameters for model, voice, language, and output format, allowing precise control over the generated audio characteristics.

  • Consistent JSON request structure
  • Supports all 8 voice presets
  • Handles up to 4096 characters per request

Compatible with OpenAI SDKs

The API endpoint shape matches the OpenAI speech endpoint, allowing developers to use official OpenAI SDKs by simply changing the base URL. This compatibility reduces development time for teams already familiar with standard TTS integration patterns.

  • Compatible with OpenAI SDKs
  • Base URL: https://api.play79z.com/v1
  • Standard POST request method
Technical infrastructure

Independent storefront structure

Sound wave illustration for: Independent storefront structure

Clinical Audio operates as an independent storefront for the shared text-to-speech API. Each site in this network functions as a distinct commercial entity, providing direct access to the same underlying synthesis engine without centralised branding. This structure ensures that your integration remains stable and transparent, regardless of which storefront you initially choose.

As an independent operator, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We do not resell their infrastructure nor claim to be their official provider. Our identity is strictly tied to the Clinical Audio brand, offering a clear, unbranded technical relationship focused solely on healthcare audio generation.

Independent storefront for the same API

Every site in this network is an independent storefront for the same text-to-speech API. You interact with the identical api.play79z.com endpoints, using the same request shapes and voice models, regardless of the storefront domain. This ensures consistent performance and pricing across all independent partners.

Our architecture is simple: you send text, we return audio. There are no intermediary layers or proprietary wrappers. This direct connection allows you to use standard OpenAI SDKs by simply adjusting the base_url, ensuring your code remains portable and easy to maintain.

  • Same API endpoints and voice models across all storefronts
  • Standard JSON request format compatible with OpenAI SDKs
  • Consistent pricing and rate limits (60 requests/minute)

Not affiliated with major tech brands

Clinical Audio is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We do not use their branding, nor are we an official partner or reseller. Our voice models are based on licensed recordings from LibriTTS-R and LibriVox, distinct from the major tech ecosystems.

We maintain our own independent identity. When you sign up, you create an account with Clinical Audio, not with a larger tech conglomerate. This clarity helps healthcare teams understand exactly who holds their API keys and billing data, reducing confusion in enterprise procurement processes.

  • No affiliation with OpenAI, Google, Amazon, or Microsoft
  • Independent voice licensing from LibriVox and LibriTTS-R
  • Clear distinction from major tech ecosystem providers

Direct customer relationship

You have a direct relationship with Clinical Audio. Your API key, balance, and usage data are managed solely through our independent storefront. There are no third-party resellers or opaque billing layers. If you need to issue a new key or check your balance, you do it directly with us.

Support is by email only. We do not offer phone lines or live chat, keeping overhead low and allowing us to focus on reliability. Your account is per site, meaning each storefront maintains its own distinct customer records, ensuring a clean and direct line of communication for your team.

  • Direct API key management and billing
  • Email-only support for focused assistance
  • No third-party resellers or opaque billing layers
Independent storefront structure

Contact and support

Sound wave illustration for: Contact and support

Support for Clinical Audio is handled exclusively through email. This direct line ensures that technical questions regarding API integration, billing inquiries, or general account issues are addressed by a dedicated team without the noise of automated queues.

Email support only

We maintain a single, efficient channel for all customer communications. By focusing on email, we ensure that every query receives a thoughtful, written response that you can reference later. This approach minimizes miscommunication and provides a clear audit trail for your support interactions.

No phone or live chat

We do not offer phone support or live chat widgets. This decision reflects our operational model as an independent storefront for a high-volume API service. Without the overhead of call centers, we can keep our infrastructure lean and our focus on technical reliability and clear documentation.

Email address for inquiries

Send your questions to [email protected]. Whether you need help with your API key, have questions about character usage, or require clarification on voice licensing, our team monitors this inbox regularly. Please include your account details and specific technical context to help us assist you faster.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Our patient guides simplify complex medical information for large teams to deliver clear and compassionate care.

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. openai-node on GitHub
  3. IETF RFC 7845: Ogg Opus
  4. OpenAI API reference: create speech
  5. W3C WAI: making audio and video accessible
  6. openai-python on GitHub
  7. FFmpeg documentation
  8. Creative Commons Attribution 4.0
  9. MDN: Web Speech API
  10. TRON developer hub: TRC-20
  11. Node.js documentation
  12. curl documentation

More on this site