Frequently asked questions
Who runs the MediVoice API?
MediVoice API is an independent storefront providing a cloud text-to-speech service. We operate as a standalone entity, not a subsidiary of a larger tech conglomerate.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide clear, accessible narration suitable for clinical instructions. Each generated audio file includes an inaudible watermark to identify it as synthetic speech, ensuring transparency in medical communications.
Is the API affiliated with OpenAI?
No. While our API endpoint shape matches the OpenAI speech endpoint for easy SDK integration, we are not affiliated with OpenAI. We are an independent provider. Our models, voices, and infrastructure are distinct. Developers use the OpenAI SDK by simply changing the base URL to our API domain.
How is my data used?
Input text is used solely to produce the audio response and is not used for training our models. Generated audio is returned in the response and not stored. We retain request metadata, such as time, character count, and status, strictly for billing purposes. Your medical content remains private and secure.
Do I own the generated audio?
Yes. You receive the generated audio directly in the API response. We do not store the generated files, so you retain full control over the output.
Is there a physical office?
Our presence is defined by our API endpoints and documentation rather than a single physical location, allowing for flexible and scalable service delivery.
How do I contact support?
Support is available via email only. We do not offer phone numbers, live chat, or SLAs. You can reach us through the contact page or by emailing the support address provided in your account dashboard. We aim to respond to technical and billing inquiries efficiently via written correspondence.
Are there any certifications?
We do not hold specific certifications such as SOC 2, HIPAA, or GDPR certificates. While we do not use your text for training, we do not provide formal compliance documentation. Healthcare startups should verify our data handling practices against their own internal requirements or consult their legal teams for specific regulatory needs.
Our Editorial Team
MediVoice API operates as an independent storefront for a cloud text-to-speech API, providing expert reviews tailored for healthcare startups.
Expert Review Approach
We evaluate the API’s technical specifications, pricing structure, and voice quality specifically for clinical instruction and patient guide generation. Our analysis focuses on clarity, language support, and reliability for medical content.
Focus on Healthcare
Our team understands the unique needs of medical communications. We assess how well the eight voice presets handle technical terminology and whether the API’s speed and character limits suit long-form patient education materials.
Independent Testing
Reviews are based on direct API usage and factual data, not vendor-provided marketing materials. We test character limits, language accuracy, and audio generation times to ensure our recommendations reflect actual performance for startup developers.
Voice Licensing and Source
MediVoice API voices are built on the LibriTTS-R dataset, providing a robust foundation for medical and patient guide audio.
LibriTTS-R Dataset
The underlying engine uses LibriTTS-R, a curated collection of speech data designed for text-to-speech research.
CC BY 4.0 License
We utilize the Creative Commons Attribution 4.0 International license for the source material.
Public Domain Readings
Many voices are derived from LibriVox public-domain audiobook readings.
Data Privacy Policy
MediVoice API processes your input text solely to generate the corresponding audio file. We do not use the content of your medical texts, patient guides, or clinical instructions to train or improve our underlying speech models.
No Training on Input
The text you send via the API is used exclusively for synthesis.
No Audio Storage
Generated audio files are returned directly in the API response and are not permanently stored on our servers.
Metadata Retention
We retain request metadata, including timestamps, character counts, and status codes, primarily for billing accuracy and usage tracking.
Technical Limitations
The API prioritizes simplicity and reliability over complex markup.
No SSML Support
We do not support SSML, so you cannot control prosody, pauses, or pronunciation dictionaries via markup.
No Voice Cloning
The service uses eight fixed presets derived from licensed recordings; it does not offer custom voice cloning or upload-your-own-voice features. Each generated file carries an inaudible watermark marking it as synthetic speech, which aids in identifying AI-generated audio in medical communications.
Fixed Voice Presets
You must choose from our eight curated voices (e.g., aria, nova, atlas). There are no emotion tags or real-time style adjustments.

Contact and Support
We handle all inquiries via email. There is no phone support or live chat available, ensuring every message is documented and traceable for accountability.
Email Support Only
Send your questions to our support address. We do not use automated bots to route your tickets; human reviewers assess each request based on technical context.
No Phone Number
We do not provide a direct phone line. This reduces overhead costs, keeping pricing transparent for healthcare startups without hidden support premiums.
Response Expectations
Responses are typically sent within 24 hours during business days. For urgent integration issues, email is the most reliable channel for detailed technical exchange.
- Standard business day response time
- Email-only communication channel
- Human-led ticket review
Company Mission
MediVoice API was built to help healthcare startups deliver clear, multilingual patient guides and clinical instructions.
Accessible Healthcare
Startup-Friendly Pricing
We charge $0.01 per 1,000 characters with no monthly plans or minimum spend.
Transparent Operations
All billing is handled via USDT (TRC-20) with automatic crediting. We do not hide fees or use complex tier structures. Your input text is used only for synthesis and never for training, ensuring patient data remains private.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Email-based accounts start without trial credit, requiring immediate top-up to begin generation.
23 languages
Any voice speaks any of these languages.
