Frequently asked questions
Are you affiliated with OpenAI?
No. MediVoice is an independent storefront. While our API endpoint and request shape match the OpenAI speech endpoint for easy SDK integration, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.
Where do the voices come from?
Our eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech, ensuring clear attribution to our TTS engine.
Do you sell my patient data?
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 (time, characters, status) solely for billing purposes.
Can I use the audio for commercial hospitals?
Yes. MediVoice provides reliable speech synthesis for healthcare teams. You can use the API to convert medical texts, patient guides, and educational scripts into clear audio for commercial use without managing complex voice infrastructure.
Who owns the copyright to the generated audio?
The facts do not specify copyright ownership of the generated audio files. We focus on providing the synthesis engine and infrastructure. The voices themselves are based on CC BY 4.0 licensed recordings from LibriVox.
Is the API hosted in a specific country?
No. We do not offer data-center choice or on-premise installation options. The API is a cloud service accessible via POST requests to our endpoint, with no specific geographic hosting guarantee provided.
Do you have a physical office?
No. We do not have a physical office or a phone number. Support is by email only. There is no live chat, and we do not offer SLAs or enterprise contracts.
Can I request a specific voice modification?
No. We do not offer custom voice cloning, emotion tags, or voice design. You can adjust speed between 0.25–4.0 and choose from eight presets. No SSML or phoneme dictionaries are available for fine-tuning.
Is the editorial team composed of doctors?
Not necessarily. The editorial team is not defined by medical credentials. We are a team focused on providing reliable speech synthesis for healthcare teams, helping them deliver accessible content without managing complex voice infrastructure.
Do you offer refunds for unused credit?
No. We do not offer refunds for unused credit. Balance does not expire. Failed requests are free, and the charge is returned in full if synthesis fails. Balance does not expire.
Can I use the API for voiceovers in medical videos?
Yes. You can send text via POST and receive an audio file. This workflow is ideal for generating voiceovers for medical videos, patient guides, or educational scripts using our eight voice presets.
Is the API GDPR compliant?
We do not hold a GDPR certificate. While we do not store generated audio or use input text for training, we do not offer an SLA or specific compliance guarantees. Support is by email only.
Do you employ human voice actors?
We use recordings from LibriVox, which features human readers. However, we do not employ human voice actors directly for custom cloning or real-time performance. The voices are synthesized from these licensed public-domain recordings.
How do I verify the license of the voices?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. You can verify this through the LibriVox and LibriTTS-R sources. Every file also contains an inaudible synthetic watermark.
Who We Are
We are an independent editorial team building reliable speech synthesis for healthcare teams. We help clinical and administrative groups convert patient guides, medical texts, and educational scripts into clear audio without managing complex voice infrastructure. Our focus is on accessibility for large teams who need consistent, high-quality results.
Independent Editorial Team
MediVoice is not a subsidiary of a major technology conglomerate. We operate as a dedicated group focused solely on delivering a reliable text-to-speech API for medical content. Our team handles everything from voice selection to server maintenance, ensuring the service remains stable for your daily workflows. We do not offer an SLA or uptime guarantee.
Focus on Healthcare Accessibility
We designed our platform to meet the specific needs of healthcare professionals. Whether you are creating audio versions of discharge instructions or training modules for new staff, our API converts text into natural-sounding speech. This helps ensure that critical information is accessible to patients and staff who prefer or require audio formats.
No Affiliation with Major Tech Brands
MediVoice is independent. While our API endpoint mimics the structure of other major providers for ease of integration, we are not affiliated with OpenAI, Google, Amazon, or Microsoft. We use licensed voices and infrastructure, providing a transparent alternative for teams who want to avoid vendor lock-in or brand confusion.
Our Voice Licensing
Our eight voice presets are derived from the LibriTTS-R dataset, which consists of public-domain audiobook recordings from LibriVox. These voices provide a natural, human-like quality suitable for medical patient guides and clinical scripts without requiring complex voice design.
Each generated audio file carries an inaudible watermark that clearly marks it as synthetic speech. This ensures transparency while maintaining the high fidelity needed for clear communication in healthcare settings.
LibriTTS-R Source
The underlying voice data comes from the LibriTTS-R dataset, offering eight distinct presets ranging from warm narrators to calm instructional tones. These voices are optimized for clarity, making them ideal for reading detailed medical texts and patient instructions.
CC BY 4.0 License
The dataset is licensed under CC BY 4.0, allowing us to integrate these voices into our API while respecting the original creators' rights. This license ensures that the audio remains accessible and legally sound for commercial use by your team.
LibriVox Public Domain Recordings
The source recordings are public domain reads from LibriVox, donated by volunteer narrators. This foundation provides a rich variety of speech patterns that we have refined into our eight preset voices, ensuring consistent quality across all generated audio files.
Data Privacy and Usage
MediVoice processes your medical texts strictly to generate audio. We do not use your input text for training our models, ensuring that patient guides and clinical scripts remain proprietary to your organization.
Input Text Not Used for Training
Your text is sent to the API, converted to speech, and returned in the response. It is not retained for model improvement, keeping your educational scripts and patient data secure.
Audio Not Stored
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once you receive the file, it lives entirely on your infrastructure.
Metadata Kept for Billing
We retain request metadata—specifically the time, character count, and status—to calculate your usage accurately. This ensures you are charged correctly for each synthesis attempt.
Our Honest Limits
MediVoice is built by an independent editorial team, not a large corporation. We prioritize transparency over complex corporate structures. Our infrastructure is designed for reliability, but we do not promise specific uptime percentages or financial compensation if service varies.
We offer a straightforward API without the overhead of enterprise agreements. This keeps our pricing simple and accessible for healthcare teams of all sizes.
No SLA or Uptime Guarantee
We do not provide a Service Level Agreement (SLA) or guarantee 99.9% uptime. Our infrastructure is robust, but unexpected delays can occur, especially during peak usage. Requests are processed sequentially, so longer texts may take time to generate.
If you require a strict financial guarantee for downtime, MediVoice may not be the right fit for your critical infrastructure needs.
No Enterprise Contracts
We do not offer custom enterprise contracts, dedicated support lines, or volume-based pricing tiers. We do not offer phone support. Our model is transparent: you pay per character used, with no minimum spend or monthly commitments.
This approach allows large clinical teams to scale usage up or down without negotiating complex agreements or waiting for invoice approvals.
No On-Premise Installation
MediVoice is a cloud-only API. We do not offer on-premise installation or data-center choice. All text processing happens on our servers.
Your input text is used only to produce audio and is not stored after the response is delivered, except for request metadata kept for billing purposes.

Contact and Support
MediVoice support is handled entirely through email. We believe this allows for thoughtful, detailed responses tailored to your specific integration or billing question, rather than the rushed exchanges common in live chat. There are no complex menus or automated bots to navigate; you speak directly to our team.
This approach keeps our operational costs low, allowing us to maintain our simple, transparent pricing model without hidden support fees. It also ensures that every query receives full attention from a human who understands the technical nuances of our TTS API.
Email Only Support
Send your questions to [email protected]. Whether it is about voice selection, character limits, or billing discrepancies, our team reviews every message personally.
We do not use ticketing systems that obscure your message in a queue. Your email goes directly to our support engineers who can assist with API specifics.
No Live Chat or Phone
We do not offer live chat widgets or phone lines. This decision reduces overhead and keeps our focus on building a reliable API rather than managing call centers.
If you need immediate assistance during a critical release, email remains the most reliable way to document the issue for later reference.
Response Times
We aim to respond to all support emails within 24 hours on business days. During peak periods, responses may take slightly longer, but we prioritize clarity over speed.
For urgent billing issues, please include your account email and transaction details to help us locate your account quickly.
- Business days: Monday–Friday
- Average response: <24 hours
- No weekend guarantee
Why We Built This API
We built MediVoice to help healthcare teams convert patient guides and educational scripts into clear audio without complex infrastructure. By leveraging the open LibriTTS-R dataset, we provide accessible speech synthesis tailored for medical contexts, ensuring large clinical teams can deliver consistent, understandable content to patients and staff.
Democratizing Audio for Medicine
Our goal is to make high-quality text-to-speech accessible to every healthcare provider, regardless of technical resources. We focus on delivering reliable audio for medical texts, ensuring that critical information reaches patients in an accessible format without requiring expensive voice design or custom cloning services. We do not offer custom voice cloning.
- Accessible audio for patient guides
- Reliable synthesis for clinical scripts
- No custom voice cloning needed
Simplifying Integration
We use the same request shape as the OpenAI speech endpoint, allowing you to integrate with existing tools by simply changing the base URL. With straightforward endpoints for voices and models, your team can start generating audio quickly without learning a proprietary SDK or managing complex infrastructure.
Transparent Pricing Model
Our pricing is simple: $0.01 per 1,000 characters, with no monthly plans or hidden fees. Failed requests are free, and you can top up with USDT on TRON. This model ensures predictable costs for large teams processing extensive medical texts, with no minimum spend or subscription locks.
- $0.01 per 1,000 characters
- No monthly plans
- Free failed requests
- USDT top-ups
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Note any specific words or phrases that were difficult to catch.
23 languages
Any voice speaks any of these languages.
