Cloud TTS API for Medical & Biblical Audio Generation

By MediVoice editorial team · Updated 2026-11-18

MediVoice provides a reliable cloud TTS API designed for healthcare teams who need to convert medical texts, patient guides, and educational scripts into clear audio. This page outlines how our infrastructure supports large clinical and administrative groups in delivering accessible content without managing complex voice systems.

You will find specific details on our voice presets, multilingual support, and straightforward pricing. Discover how to integrate the official OpenAI SDK (by changing the base URL) into your existing workflows, understand our data privacy standards, and start generating audio files immediately with a simple API key.

Cloud TTS API for Medical & Biblical Audio Generation

Frequently asked questions

What does 'Bible read aloud' mean in the context of a TTS API?

It means converting written scripture text into audio files using our TTS endpoint. You send the text via JSON, and we return an audio file. This allows you to distribute readable audio versions of biblical texts without hiring voice actors, ensuring consistent narration across your digital platforms.

Can the API read long medical texts or patient guides?

Yes. Each request handles up to 4096 characters. For longer texts, split the input into parts and join the resulting audio files. This workflow allows you to generate complete patient guides or medical scripts efficiently, keeping each API call within the supported character limit for reliable synthesis.

Which voices are best for patient education?

We recommend Luna for soft storytelling or Sage for calm, instructional content. Aria offers a warm narrator tone suitable for general health information. These voices provide clear, accessible audio that helps patients understand medical instructions without distraction, supporting better comprehension in educational materials and patient guides.

Do you support languages other than English?

Yes, we support 23 languages including Spanish, French, German, Chinese, and Arabic. Any voice can speak any of these languages. If you do not set the language parameter, it guesses from the script, but we recommend explicitly setting it for non-English Latin-script text to ensure accuracy.

Is the audio generated from real human recordings?

The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. However, the generated audio is synthesized, not a direct recording. Every file carries an inaudible watermark that marks it as synthetic speech, distinguishing it from original human recordings while maintaining high quality.

How is the cost calculated for large teams?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. There are no monthly plans, seats, or minimum spends. You only pay for the characters you process, making it scalable for large clinical teams with varying usage needs.

What happens if a synthesis request fails?

Failed requests are free. If synthesis fails, the charge is returned in full. You are not billed for characters that do not result in successful audio generation. This ensures your team only pays for usable audio outputs, protecting your budget during high-volume processing or network issues.

Is the API suitable for commercial patient apps?

Yes, the API is designed for general use and integrates easily into applications. You receive audio files via the endpoint, which you can store or play in your app. There are no restrictions on commercial use, and the consistent pricing model supports scalable deployment in patient-facing software.

Do I need to pay for each individual user?

No. There are no seats or per-user fees. You manage one active API key per account. Whether one person or a large clinical team uses the generated audio, the cost depends only on the total characters processed. This simplifies billing for organizations with many end-users.

Can I adjust the speed of the narration?

Yes, you can set the speed between 0.25 and 4.0. This allows you to tailor the narration pace for different audiences, such as slower speeds for elderly patients or faster speeds for quick updates. Adjusting speed helps optimize comprehension and fits various educational contexts effectively.

Are there any hidden fees for using the API?

No. Pricing is strictly $10 per million characters. Failed requests are free. Top-ups via USDT on the TRON network (TRC-20) are credited automatically. There are no subscriptions, invoices, or VAT charges. You know exactly what you pay based on character count, with no surprise costs for features or support.

How do I integrate this with my existing medical software?

Send a POST request to the speech endpoint with JSON body containing text, voice, and format. Use the official OpenAI SDK by changing the base URL, or use plain HTTP. This standard approach allows easy integration into existing workflows without needing a custom SDK or complex middleware.

Is the synthetic audio detectable as AI-generated?

Yes, every generated file carries an inaudible watermark that marks it as synthetic speech. This watermark identifies the audio as AI-generated without affecting the listening experience. It provides transparency about the content source, which is useful for compliance and clarity in patient communications and educational materials.

Do I need a developer to use this service?

A developer helps with integration, but you can use the API directly. The endpoint accepts standard JSON, compatible with OpenAI SDKs. For non-technical users, you can use the provided curl examples and documentation. However, custom workflows or app integration typically require basic programming knowledge to automate requests.

First request

curl

curl https://api.playabc999.com/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.mp3

Why Healthcare Teams Choose Our API

Sound wave illustration for: Why Healthcare Teams Choose Our API

Healthcare teams often need to convert lengthy patient guides and educational scripts into audio for accessibility compliance. Our API processes medical texts up to 4,096 characters per request, ensuring clear, consistent narration without the overhead of managing complex voice infrastructure.

This solution allows large clinical teams to generate scalable audio content efficiently. You retain control over tone and clarity, ensuring patient materials are delivered with professional quality.

Accessible Patient Guides

Accessible Patient Guides

Convert written instructions into clear audio files for patients with visual impairments or reading difficulties. Send text via a simple JSON request and receive standard formats like MP3 or WAV, ready for integration into patient portals or waiting room systems.

  • Supports complex medical terminology
  • Generates audio in seconds
  • Standard file formats for easy playback

Clear Educational Content

Ensure training materials and clinical scripts are heard clearly. Voices like Sage provide a calm, instructional style ideal for procedural explanations, while Aria offers a warm narrator tone for patient education. Each request is processed individually, maintaining consistent audio quality.

  • Calm instructional voice options
  • Warm narrator tones available
  • Consistent audio output

Scalable for Large Teams

Large organizations can generate hundreds of audio files without hiring voice actors. With 60 requests per minute allowed per key, teams can batch-process content efficiently. Failed requests incur no charge, protecting your budget during high-volume testing.

  • 60 requests per minute limit
  • No minimum spend required
  • Free failed requests

Natural Voices for Clinical and Spiritual Texts

Sound wave illustration for: Natural Voices for Clinical and Spiritual Texts

MediVoice offers distinct voice presets tailored for clinical clarity and biblical texts.

Warm Narrator Tone (Aria)

Aria provides a warm, clear narration ideal for patient guides and educational scripts. Her tone is accessible, helping patients understand complex medical information without feeling overwhelmed.

Calm Instructional Style (Sage)

Sage delivers a calm, instructional style perfect for procedural explanations or step-by-step clinical instructions. Her steady pace ensures listeners can follow along easily, reducing cognitive load.

Deep Documentary Voice (Orion)

Orion offers a deep, documentary-style voice suitable for biblical texts or serious medical overviews. His deep tone is suitable for serious medical overviews or biblical texts.

Support for Multilingual Patient Populations

Sound wave illustration for: Support for Multilingual Patient Populations

MediVoice supports 23 languages, covering major global dialects including Arabic, Chinese, French, Hindi, Spanish, and more. This range allows healthcare teams to distribute patient guides and educational scripts to diverse populations without needing separate voice infrastructure for each region.

Automatic language detection simplifies deployment. If the language field is omitted, the API guesses the language from the text script, defaulting to English for Latin characters. This reduces configuration overhead for standard English medical texts.

23 Supported Languages

We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, ensuring consistent audio quality across different linguistic contexts.

Automatic Language Detection

For most workflows, you do not need to specify the language manually. The API analyzes the input text script to determine the appropriate language model. This automatic detection works for both Latin and non-Latin scripts, streamlining the integration process for development teams.

Precise ISO Language Codes

For non-English text using the Latin alphabet, we recommend explicitly setting the language parameter. Without this hint, Latin-script text defaults to English, which may affect pronunciation accuracy. Providing the correct ISO code ensures precise synthesis for multilingual patient populations.

Simple Integration for Existing Workflows

Sound wave illustration for: Simple Integration for Existing Workflows

MediVoice integrates seamlessly into your existing clinical content pipelines using standard HTTP requests. By adjusting the base URL to our API endpoint, you can leverage the official OpenAI SDKs without rewriting your integration logic. This ensures that your current codebase for text-to-speech workflows remains stable and familiar.

OpenAI SDK Compatibility

Our API mirrors the structure of the OpenAI speech endpoint. You can simply update your client’s base_url to https://api.playabc999.com/v1 and use your MediVoice API key. This allows teams already using OpenAI SDKs in their applications to switch providers with minimal code changes.

  • Use official OpenAI SDKs with a simple base URL change.
  • Compatible with existing TTS integration patterns.
  • No proprietary client libraries required; use the official OpenAI SDK or plain HTTP.

Standard JSON Requests

Send your medical texts via a simple POST request to /v1/audio/speech. The JSON body accepts standard fields like model, input, voice, and language. This standard format makes it easy to trigger audio generation from any backend service, whether it’s a patient portal or an internal education platform.

  • POST request to https://api.playabc999.com/v1/audio/speech.
  • JSON body with model, input, voice, and optional language.
  • Supports text up to 4096 characters per request.

Multiple Audio Formats

Choose the output format that best fits your delivery method. We support MP3, WAV, OPUS, FLAC, and PCM. This flexibility allows you to optimize file sizes for web delivery or preserve high fidelity for archival purposes, ensuring your patient guides and educational scripts play clearly across all devices.

  • MP3, WAV, OPUS, FLAC, and PCM formats.
  • Optimize for web delivery or high-fidelity archival.
  • No need for post-processing conversion.

Transparent Pricing for Medical Volumes

Sound wave illustration for: Transparent Pricing for Medical Volumes

MediVoice charges $10 per 1 million characters, equivalent to $0.01 per 1,000 characters. This model ensures you pay only for what you generate, making it easy to budget for large-scale patient guide distributions or educational script libraries.

Spatial and punctuation characters count toward the total, providing predictable cost calculation for clinical texts. With no monthly minimums or subscription commitments, your expenses scale directly with your audio production volume.

Pay Per Character

Every character in your input text, including spaces and punctuation, contributes to the usage count. At $0.01 per 1,000 characters, generating a 4,000-character patient guide costs just $0.04. This precise metering allows healthcare administrators to forecast audio production costs accurately for bulk content creation.

  • Cost: $0.01 per 1,000 characters
  • Includes spaces and punctuation in count
  • Ideal for high-volume educational scripts

No Monthly Minimums

There are no fixed monthly plans or seat licenses. You can top up with USDT on the TRON network (TRC-20) whenever needed, with a minimum top-up of $5. Your balance never expires, allowing you to pause usage during low-demand periods without losing credit.

Free Failed Requests

If a synthesis request fails for any reason, the charge is returned in full. This ensures that technical glitches or network issues do not result in unnecessary costs. You only pay for successfully generated audio files, protecting your budget for critical patient communications.

Transparent Pricing for Medical Volumes

How It Works: From Text to Audio

Sound wave illustration for: How It Works: From Text to Audio

Convert your medical scripts or patient guides into audio by sending a simple POST request to the speech endpoint. The API accepts text up to 4,096 characters, allowing you to integrate speech synthesis directly into your existing clinical workflows without managing complex infrastructure.

Send Text via API

Include your text, selected voice, and desired format in a standard JSON body. Use the OpenAI SDK or plain HTTP with your Bearer token for authentication. The system processes requests sequentially, ensuring consistent delivery even under load.

  • Support for tts-1 and tts-1-hd models
  • Compatible with standard OpenAI SDKs
  • JSON-based request structure

Receive Audio File

Once synthesis completes, you receive the audio file in your chosen format (MP3, WAV, OPUS, FLAC, or PCM). Failed requests incur no charge, ensuring you only pay for successful audio generation.

  • Multiple output formats available
  • No charge for failed requests
  • Direct file response

Handle Long Texts Automatically

For scripts exceeding 4,096 characters, split the text into smaller parts and join the resulting audio files. This approach ensures high-quality synthesis for lengthy patient guides or educational materials without losing context.

Technical Specifications for Developers

Sound wave illustration for: Technical Specifications for Developers

MediVoice’s TTS API is built for reliability and ease of integration. Healthcare engineering teams can adopt standard HTTP requests or use the OpenAI SDK with a simple base_url change to https://api.playabc999.com/v1. This ensures your existing infrastructure handles medical audio generation without complex custom wrappers.

Rate Limits and Quotas

Each API key supports 60 requests per minute (10 per minute before the first top-up). New accounts start with a limit of 10 requests per minute until the first top-up is processed. This ensures stable performance for batch processing patient guides without overwhelming the service during peak hours.

Authentication Methods

Access is secured via a single active Bearer token sent in the Authorization header. You can generate a new key at any time from your dashboard; the previous key becomes invalid immediately, ensuring tight security for sensitive clinical data workflows.

Supported Formats

Audio is returned in standard formats: mp3, wav, opus, flac, or pcm. Choose mp3 for efficient storage or wav for high-fidelity archival. All outputs include an inaudible synthetic watermark for content identification.

Data Privacy and Usage

Sound wave illustration for: Data Privacy and Usage

Input text is used solely for audio synthesis and is never retained for training. Generated audio files are returned in the response and not stored on our servers, ensuring your patient guides and educational scripts remain private during processing.

Request metadata, including timestamp, character count, and status, is kept for billing accuracy. This data helps us provide transparent usage records without storing the actual content of your medical or biblical texts.

No Training on Input Text

Your medical texts and patient guides are processed exclusively to generate the requested audio file. We do not use your input data to train our models, ensuring that your specific clinical terminology and narratives remain yours.

Metadata Retention

We retain request metadata such as time, character count, and status for billing purposes. This minimal data allows us to accurately track usage and ensure fair billing without storing the actual text content you send.

Synthetic Watermarking

Every generated audio file includes an inaudible watermark that identifies it as synthetic speech. This helps distinguish AI-generated medical audio from human-recorded content while remaining transparent to patients and listeners.

Get Started with Your First Audio File

Sound wave illustration for: Get Started with Your First Audio File

Begin by visiting the /get-api-key/ page to create your account using Google or email. This simple step opens your dashboard where you can manage your credentials and monitor usage.

Once registered, you receive a unique API key instantly. Your account starts with a $0.50 free trial (valid for 7 days), giving you approximately 50,000 characters to test the service without any commitment.

Sign Up for an Account

Navigate to the sign-up page and choose your preferred authentication method. Accounts are specific to this site, ensuring your credentials are secure and isolated within your workflow.

If you use Google, you receive immediate trial credit. Email-based accounts start with a zero balance but can be topped up easily via USTRC20.

  • Google or email + password authentication
  • Instant trial credit for Google sign-ins
  • No credit card required to start

Obtain Your API Key

Your dashboard displays your active API key alongside your current balance and character usage. You can issue a new key at any time, which immediately invalidates the old one.

Keep this key secure in your environment variables. It is the single credential needed to authenticate all your text-to-speech requests.

  • One active key per account
  • Instant revocation on key renewal
  • Visible in the dashboard

Test with a Sample Script

Use the provided curl example to send a POST request to the speech endpoint. Start with a short patient guide or educational snippet to verify voice quality and response format.

Remember that requests are processed sequentially. For longer texts, split the input into chunks of 4,096 characters and join the resulting audio files.

  • POST https://api.playabc999.com/v1/audio/speech
  • Supports mp3, wav, opus, flac, pcm
  • Max 4,096 characters per request

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.

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. curl documentation
  3. LibriTTS-R corpus (OpenSLR 141)
  4. OpenAI API reference: create speech
  5. ISO 639 language codes
  6. Python documentation
  7. openai-node on GitHub
  8. IETF RFC 7845: Ogg Opus
  9. Creative Commons Attribution 4.0
  10. FFmpeg documentation
  11. openai-python on GitHub
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site