Frequently asked questions
What is this API?
VoxMedica is a cloud text-to-speech API for healthcare startups. Send text via a POST request to receive an audio file. The endpoint mimics the OpenAI structure, making integration straightforward for developers building patient education tools without enterprise complexity.
How does it compare to Azure TTS?
We offer a simpler integration using the familiar OpenAI endpoint structure. While Azure provides various models, we focus on eight specific presets optimized for clarity. We do not offer SSML or custom voice cloning.
Is it faster than Azure?
Audio generation runs at roughly real-time speed, producing about 25 characters per second. Short phrases take a few seconds to synthesize, while longer texts are processed sequentially. Under load, requests may wait in a queue, so actual latency depends on current server activity. There is no guaranteed SLA or uptime guarantee.
Can I use OpenAI SDKs?
Yes. Our API shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.9a9993.info/v1 and using your VoxMedica key. This allows for easy migration for teams already familiar with OpenAI tools.
What formats are supported?
We support mp3, wav, opus, flac, and pcm formats. Choose the format that best fits your patient education platform. MP3 is recommended for general use due to its balance of quality and file size, ensuring smooth playback on various devices.
Do you support SSML?
No, we do not support SSML. Our API accepts plain text input up to 4096 characters. For precise control, you can adjust the speed between 0.25 and 4.0 or select from our eight voice presets to match the desired tone.
Is there a free trial?
Yes, signing in with Google grants $0.50 of credit, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API before committing to a top-up.
How do I pay?
Payments are made via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes. There are no monthly plans or subscriptions. Your balance does not expire, and you only pay for what you use.
Is credit card accepted?
No, we do not accept credit cards, PayPal, or invoices. All payments are processed exclusively through USDT on the TRON network. This simplifies billing for international startups by avoiding currency conversion fees and traditional payment gateway complexities associated with card processing.
Do you store my patient data?
Input text is used only to produce 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 transparency in your usage costs.
Are the voices synthetic?
Yes, every generated file carries an inaudible watermark marking it as synthetic speech. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.
Can I clone a doctor's voice?
No, we do not offer custom voice cloning or uploading your own voice. We provide eight preset voices, such as Aria and Atlas, designed for clarity. If you need a specific voice, you can select the preset that matches the desired tone.
What happens if the request fails?
Failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successful audio generations. You can retry the request or adjust parameters like speed or voice to resolve any issues with the input text.
Is there an SLA guarantee?
No, we do not offer an SLA, uptime guarantee, or enterprise contract. Our service is designed for startups that need straightforward API access. Requests are processed sequentially, so performance may vary during high traffic periods.
First request
curl
curl https://api.9a9993.info/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Startups Choose This API
Azure’s documentation can feel overwhelming for small healthcare teams, and its enterprise pricing often demands minimum spends that don’t fit startup budgets. We offer a straightforward API that mimics the familiar OpenAI endpoint structure, removing the complexity of negotiating contracts and managing large-scale infrastructure.
Simpler than Azure for small teams
Azure requires navigating extensive documentation and negotiating minimum spends. Our API is designed for developers who need reliable, clear audio outputs for patient education materials without the complexity of enterprise-grade contracts. You get a direct path from text to audio without the overhead.
OpenAI SDK compatibility
If you are already using the OpenAI SDK, you can integrate our voice engine by simply changing the base_url to https://api.9a9993.info/v1. The request shape is identical, so your existing code works with minimal adjustments. This reduces friction for teams familiar with standard TTS workflows.
No enterprise lock-in
There are no monthly plans, no seats, and no minimum spend. You pay only for what you use, starting with a small free trial. This flexibility allows healthcare startups to scale their patient communication tools up or down without being tied to long-term commitments or unused capacity.
Clear Voices for Patient Guides
Patient education materials require clarity above all. Our voices are designed to reduce cognitive load, ensuring that complex medical instructions are easy to follow. Whether explaining a new medication or post-operative care, the audio output is crisp and natural, helping patients feel informed rather than overwhelmed.
We offer distinct vocal profiles tailored to different types of health content. Choose a warm narrator for gentle explanations, a calm voice for instructional steps, or a neutral tone for factual updates. Each voice maintains consistency, building trust with your audience through reliable delivery without the need for expensive voice acting sessions.
Warm narrator for explanations
The Aria voice offers a warm, clear tone ideal for breaking down complex health concepts. It sounds like a trusted guide walking a patient through their diagnosis or treatment plan. This preset reduces anxiety by delivering information in a soothing, approachable manner.
Use Aria for introductory videos, condition overviews, or wellness tips where empathy matters. The voice remains steady and clear, ensuring that key details are heard without distraction. It works well for patient onboarding materials that need to feel personal and supportive.
- Ideal for condition explanations
- Reduces patient anxiety
- Clear, warm delivery
Calm instructional tone
Sage provides a calm, instructional voice perfect for step-by-step guides. Its steady rhythm helps users follow procedures accurately, from taking medication to performing physical therapy exercises. The tone is authoritative yet gentle, ensuring compliance without sounding robotic.
This preset is particularly effective for instructional content where precision matters. Whether it’s a video guide for using an inhaler or a checklist for pre-surgery preparation, Sage’s voice keeps the user focused on the task. It minimizes errors by maintaining a consistent, easy-to-follow pace.
- Step-by-step clarity
- High comprehension rates
- Steady, reliable pace
Neutral news style for updates
Atlas delivers a neutral, news-style voice suitable for factual updates. It is ideal for hospital announcements, policy changes, or clinical trial results where objectivity is key. The tone is professional and unobtrusive, allowing the information to take center stage.
Use Atlas for regular updates, emergency alerts, or data-driven reports. Its neutral character ensures that the message is perceived as factual rather than emotional. This makes it a reliable choice for communicating important health information that needs to be taken seriously without bias.
- Objective delivery
- Professional tone
- Suitable for alerts
Technical Simplicity
Our API mirrors the OpenAI speech endpoint structure, allowing you to use standard libraries without custom wrappers. By simply adjusting the base URL, your existing code integrates seamlessly with our service, reducing development time for small healthcare teams.
Same request shape as OpenAI
Send a simple POST request with text, voice, and model parameters. The request body matches the familiar OpenAI format, so you can leverage existing SDKs like the official OpenAI client by just pointing it to our endpoint.
- Supports tts-1 and tts-1-hd models
- Standard JSON request body
- Compatible with OpenAI SDKs
Standard audio formats
Receive audio in MP3, WAV, OPUS, FLAC, or PCM formats. These standard codecs ensure compatibility with most electronic health record (EHR) systems and patient-facing web applications without requiring complex conversion steps.
Easy curl integration
Start testing immediately with a single curl command. Our endpoint accepts standard authentication headers, making it easy to verify connectivity and audio quality before building your full integration pipeline.
- Quick validation with curl
- Standard Bearer token auth
- Audio response
Language Support for Global Patients
Healthcare communication extends far beyond English. Our API supports 23 languages, including Spanish, German, Chinese, and Arabic, ensuring patient guides reach diverse populations without needing separate voice vendors. This broad coverage allows startups to localize educational materials efficiently while maintaining consistent audio quality across regions.
23 supported languages
We cover major global markets with Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If a language is not in this list, it is not supported, so check before localizing high-volume content.
Automatic language detection
Set the language field to an ISO code for precise control, or omit it for automatic detection. Text in Latin script defaults to English if no language is specified, so explicitly set the language for non-English Latin-script text to ensure correct pronunciation and intonation.
Clear voice presets
Every voice preset can speak any of the 23 supported languages. You can assign 'aria' for warm patient explanations or 'atlas' for neutral medical updates regardless of the language. This flexibility lets you maintain a consistent brand voice across different linguistic versions of your patient guides.
Transparent Pricing
We charge $0.01 per 1,000 characters, including spaces and punctuation. Your free trial includes $0.50 (approx. 50,000 characters) for 7 days when you sign in with Google.
Failed requests are free, and your balance never expires. You can top up directly with USDT on the TRON network, starting at just $5. There are no monthly plans, subscriptions, or VAT invoices to manage.
Pay per character
Cost is calculated strictly on character count. At $10 per million characters, long patient education guides remain affordable. Short phrases may take a few seconds to generate, but the cost remains proportional to the input size.
No hidden fees
We do not charge for voice selection or speed adjustments. If synthesis fails, the charge is returned in full. There are no minimum spend requirements or per-seat fees, making it easy for small healthcare teams to forecast costs accurately.
USDT top-up only
We accept USDT on the TRON network (TRC-20) for simplicity. Transfers are credited automatically within minutes. We do not process credit cards or PayPal, eliminating the need for complex billing departments or recurring subscription management.
- Minimum top-up: $5
- Credits never expire
- No VAT invoices

Data Privacy First
Your patient education texts are used solely to generate the audio file for that specific request. We do not ingest your input data to train or improve our underlying models, ensuring your content remains private and distinct from our training corpus.
Text not used for training
The raw text you send via the API is processed exclusively to create the audio output. It is not stored long-term or used to refine our voice engines, keeping your specific medical explanations and patient guides secure.
No audio storage
Generated audio files are returned directly in the response and are not persisted on our servers after delivery. Once you receive the file, we do not retain copies, meaning your patient audio assets exist only where you store them.
Metadata kept for billing
We retain minimal request metadata—including timestamp, character count, and status—strictly to calculate charges and verify usage for your account. This data supports transparent billing but is not used for marketing or model training.
Performance You Can Trust
Generation typically matches real-time speed, processing roughly 25 characters of text per second. Short phrases may take a few seconds to synthesize, while longer texts generate efficiently as they are split into 4096-character chunks and joined seamlessly.
Real-time generation speed
For standard use cases, your audio is generated in real time. This predictable latency allows you to build responsive patient education interfaces without long loading waits, ensuring a smooth user experience even for detailed medical guides.
Queue handling under load
Requests are processed sequentially. If many developers are generating audio simultaneously, your request may wait briefly in a queue before processing begins. This simple approach ensures stable, consistent output without complex infrastructure overhead.
Failed requests are free
If synthesis fails for any reason, the charge is returned in full. You only pay for successfully generated audio files, reducing financial risk when integrating the API into your critical care workflows.
Getting Started
Start your integration by visiting our key management page to create an account via Google or email. You will receive a single active API key immediately, allowing you to begin sending synthesis requests without waiting for approval or signing enterprise contracts.
Get your API key
Once signed up, your dashboard displays your unique key, current balance, and a ready-to-use cURL example. This key authenticates every request to the API base URL, ensuring secure access to the synthesis engine.
- Support Google or email/password sign-up
- Instant key generation and dashboard access
- Single active key per account
Try the free trial
Google sign-ups include $0.50 of credit, covering approximately 50,000 characters for seven days. This allows you to test voice quality and integration speed without immediate payment commitment. Email-only accounts start without trial credit.
- $0.50 credit for Google sign-ups
- Approx. 50,000 characters included
- Valid for 7 days
Read the documentation
Consult the developer docs to understand the request structure, supported voices, and rate limits. The API mimics the OpenAI speech endpoint, so you can often use existing OpenAI SDKs by simply adjusting the base URL.
- Endpoint structure details
- Voice and format options
- Rate limit guidelines
Common Questions
Startups often ask if this API mimics Azure’s behavior or just its interface. We align with the OpenAI endpoint structure, which many healthcare developers already know, but we are not affiliated with Azure, Microsoft, or OpenAI. Our engine is distinct, built for straightforward integration without enterprise complexity.
Is it really like Azure?
We match the request shape of the OpenAI speech endpoint, allowing you to use standard SDKs by simply changing the base URL. This reduces boilerplate code, but the underlying engine and voice models are independent. We do not replicate Azure’s specific neural features or SSML support.
- Same JSON structure as OpenAI
- Independent voice engine
- No SSML support
Can I use it for HIPAA?
We do not offer a HIPAA Business Associate Agreement (BAA) or specific healthcare certifications. While input text is not used for training and audio is not stored, we provide no uptime guarantees or compliance warranties. Small startups often use us for internal prototypes or non-PHI educational materials, but verify your specific risk tolerance.
- No BAA included
- No stored audio
- Not certified for PHI
How do I switch?
Update your API base URL to https://api.9a9993.info/v1 and use your new key. Since we support standard formats like mp3 and wav, most existing audio players require no changes. If you are using the OpenAI SDK, just point it to our endpoint and swap the model ID to 'tts-1'.
- Update base URL
- Swap API key
- Keep existing audio formats
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This consistency helps you predict costs for large volumes of patient guides or appointment reminders without tracking tiered usage.
23 languages
Any voice speaks any of these languages.
