Text to Speech API for Medical Video and Patient Education

By MediVoice editorial team · Updated 2026-11-19

SaneReads provides a reliable TTS API designed for large healthcare teams creating patient guides and clinical content at scale. We turn vast amounts of medical text into clear audio without the overhead of manual recording, ensuring consistent voices across all departments and instant updates when guidelines change.

This page explains how to integrate our API into your workflow for generating medical videos and educational materials. You will find details on supported voices, languages, technical specs, and transparent pricing tailored for high-volume usage in the healthcare industry.

Text to Speech API for Medical Video and Patient Education

Frequently asked questions

What is AI text to speech for medical video?

It is a cloud API that converts text into audio files via a simple POST request. Instead of manual recording, your team sends medical text and receives synthesized speech. This allows large healthcare teams to generate patient guides and clinical content at scale without the overhead of studio sessions or voice actors.

Is the generated voice suitable for patient education?

Yes. The eight voice presets, such as Luna for storytelling or Sage for instructional content, are designed for clarity. They are based on licensed recordings and produce clear, natural-sounding speech suitable for explaining medical procedures or health information to patients in a calm, professional tone.

How many languages are supported?

We support 23 languages, including English, Spanish, German, French, Chinese, and Arabic. Any voice can speak any supported language. If you do not specify the language, the system guesses it from the script, but we recommend setting it explicitly for non-English Latin-script text.

What happens if a request fails?

Failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generation. This ensures you are not billed for errors or processing issues, making the API reliable for high-volume patient guide production workflows.

Are the voices based on real people?

Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Every generated file also carries an inaudible watermark that marks it as synthetic speech, ensuring transparency about the audio source and its synthetic nature.

Can I use the audio for commercial patient guides?

Yes. The API provides a reliable TTS service for creating audio content. Since the source recordings are from LibriVox public-domain readings and licensed under CC BY 4.0, you can use the generated audio for commercial patient guides, training materials, or clinical content without additional licensing fees.

What is the character limit per request?

Each request supports up to 4096 characters of input text. For longer texts, you can split them into parts of this size and join the resulting audio files. This allows you to generate audio for lengthy medical documents or comprehensive patient education guides efficiently.

How long does generation take?

Generation is roughly real-time, producing about 25 characters of text per second of audio. Short phrases may take a few seconds, while longer texts process sequentially. Under load, requests may wait in a queue, but typical speed matches the audio duration for most clinical content.

Do I need special hardware to use the API?

No. SaneReads is a cloud API accessible via standard HTTP requests. You only need an internet connection and a device capable of running code or sending requests. It works with any programming language that can make HTTP calls, integrating easily into your existing tech stack.

Is there a limit on how many teams can use one key?

There is no limit on the number of teams using one key. Each account has one active key, but you can issue a new key at any time, stopping the old one immediately. This allows different team members or departments to use distinct keys for tracking.

What audio formats are available?

You can choose from mp3, wav, opus, flac, and pcm formats. These options allow you to balance file size and quality for different use cases, or high-fidelity archival in medical records (wav or flac), depending on your specific needs.

How is pricing calculated?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free. You pay only for what you use, with no monthly plans, seats, or minimum spend, making it cost-effective for large healthcare teams.

Can I change my API key if it is compromised?

Yes. You can issue a new API key at any time from your account dashboard. When you generate a new key, the old one stops working immediately. This ensures quick security response without downtime, allowing your team to continue generating patient guide audio seamlessly.

Do you store the text I send?

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, such as time, character count, and status, solely for billing purposes and account management.

First request

curl

curl https://api.titan33.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.mp3

Why large medical teams choose API-based TTS

Sound wave illustration for: Why large medical teams choose API-based TTS

API-based text-to-speech removes the bottleneck of manual recording studios, allowing large healthcare teams to generate thousands of patient guides and clinical audio files on demand. This infrastructure supports high-volume content creation without the logistical overhead of scheduling voice talent or managing physical studios.

When medical guidelines shift, you can update the source text and regenerate audio instantly. There is no need to re-record entire sessions or wait for post-production, ensuring your patient education materials remain accurate and current with minimal effort.

Scale patient education without recording studios

Scale patient education without recording studios

Generate audio at scale by sending text via API. Each request processes up to 4,000 characters, with longer texts automatically split and stitched. This allows departments to produce vast libraries of instructional audio without expanding headcount.

The API handles the heavy lifting, delivering files in formats like MP3, WAV, Opus, FLAC, or PCM. Teams can integrate this directly into existing patient portals or mobile apps, distributing clear audio guidance to thousands of users simultaneously.

  • No studio booking or equipment maintenance required
  • Process up to 4,000 characters per request
  • Automated splitting for longer clinical documents

Update content instantly when guidelines change

Medical protocols evolve frequently. With an API, you update the text in your system and regenerate the audio in minutes. This eliminates the delay of re-recording voiceovers and ensures patients always hear the latest recommendations.

Failed requests incur no charge, so you can regenerate content freely until it meets quality standards. This flexibility supports rapid iteration during clinical trials or guideline updates.

Consistent voice across all departments

Use preset voices like Atlas for neutral news or Sage for calm instructions. Each voice maintains a consistent tone across all generated files, regardless of which department creates them. This uniformity builds patient trust and reduces cognitive load.

Since voices are based on licensed recordings, the audio quality remains professional and uniform. Teams can assign specific voices to specific content types, ensuring clear distinction between emergency updates and routine care instructions.

Voices for different medical contexts

Sound wave illustration for: Voices for different medical contexts

Choosing the right voice ensures medical information is received with the appropriate tone. Our eight presets cover the spectrum from urgent updates to gentle guidance, allowing teams to match the audio to the clinical context without hiring multiple voice actors.

Each voice is based on licensed recordings, ensuring high quality and consistency across your entire patient education library. You can swap voices instantly if guidelines change, keeping your content fresh and engaging.

Atlas for neutral, news-style delivery

Atlas provides a clear, neutral tone ideal for broadcasting clinical updates, hospital announcements, or regulatory changes. Its straightforward delivery ensures critical information is understood quickly without emotional bias.

Use Atlas for daily health bulletins or standardized protocol updates where clarity and neutrality are prioritized over character.

  • Neutral, news-style delivery
  • Ideal for clinical updates
  • High clarity for regulatory info

Sage for calm instructional guides

Sage offers a calm, instructional voice perfect for step-by-step patient guides. Her steady pace helps users follow complex medical instructions without feeling rushed, reducing anxiety during post-operative or treatment phases.

Sage is optimized for educational content where listeners need to process detailed information at a comfortable speed.

  • Calm, instructional tone
  • Step-by-step guidance
  • Reduces listener anxiety

Luna for soft storytelling and empathy

Luna brings a soft, storytelling quality that adds empathy to patient journeys. She is well-suited for explaining chronic conditions or recovery stories, making medical text feel more human and relatable.

Use Luna for patient testimonials, chronic disease management, or empathetic care instructions where emotional connection enhances understanding.

  • Soft, storytelling quality
  • Adds empathy to content
  • Great for chronic care

Languages for diverse patient populations

Sound wave illustration for: Languages for diverse patient populations

Delivering clear patient education across diverse communities requires more than just accurate translation; it demands voices that sound natural in the patient's native tongue. Our API supports 23 major languages, ensuring your clinical content reaches a wider audience without the logistical overhead of hiring voice actors for every region.

This linguistic breadth allows healthcare teams to standardize patient guides globally while maintaining local relevance. Whether you are creating instructions for Spanish-speaking patients or Mandarin-speaking elders, the audio remains professional, clear, and easy to understand, reducing confusion and improving health literacy across your entire patient population.

Support for 23 major languages

We currently 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. This selection covers the majority of global patient demographics, allowing you to serve diverse communities effectively without managing multiple external vendors.

Each voice is optimized for natural intonation within its specific language, ensuring that medical terminology and instructions are delivered with clarity. This consistency helps build trust with patients who may otherwise struggle with unfamiliar accents or robotic delivery in their native language.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Automatic language detection or explicit setting

The API automatically detects the language from the script, defaulting to English for Latin-script text. For non-English Latin-script content, explicitly setting the language parameter ensures accurate pronunciation and prevents misinterpretation.

This flexibility allows you to maintain a single workflow for all your content. You do not need to manually tag every file; the system handles the heavy lifting, ensuring that your patient guides sound natural regardless of the source language.

Consistent quality across all supported regions

Every voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring a consistent, professional tone across all 23 languages. This uniformity helps maintain your brand identity across different patient groups.

The audio quality remains high regardless of the language, with clear articulation suitable for complex medical instructions. This consistency is crucial for patient safety, ensuring that critical information is never lost due to poor audio clarity.

Technical integration for development teams

Sound wave illustration for: Technical integration for development teams

Integration is straightforward: send a POST request to https://api.titan33.info/v1/audio/speech with your JSON payload. By setting the base_url in the official OpenAI SDKs, you can reuse existing code with minimal changes.

The API accepts standard fields like model, input, voice, and response_format, ensuring a familiar workflow for developers already accustomed to modern TTS services.

Simple REST API compatible with OpenAI SDKs

Use the standard OpenAI SDKs by simply changing the base_url to https://api.titan33.info/v1. Authenticate with your Bearer token and call the speech endpoint just like any other OpenAI-compatible service.

This approach eliminates the need for custom client libraries or complex authentication logic, allowing your team to focus on building features rather than managing API infrastructure.

  • Compatible with official OpenAI SDKs
  • Standard JSON request body
  • Bearer token authentication

Multiple audio formats: MP3, WAV, Opus, FLAC, PCM

Choose from MP3, WAV, Opus, FLAC, or PCM based on your application’s needs. MP3 offers small file sizes for web delivery, while WAV and FLAC provide lossless quality for archival or high-fidelity playback.

PCM is available for raw audio processing, and Opus provides efficient compression suitable for low-bandwidth environments.

  • MP3, WAV, Opus, FLAC, PCM
  • Optimize for file size or quality
  • No format conversion required

Fast processing with predictable real-time speeds

Generation is roughly real-time on long texts, processing about 25 characters of text per second of audio. Short phrases may take a few seconds due to queue processing.

Requests are processed sequentially, so under heavy load, wait times may increase slightly, but performance remains consistent and predictable for planning purposes.

  • ~25 chars/sec processing speed
  • Sequential request processing
  • Predictable latency

Transparent pricing for high-volume usage

Sound wave illustration for: Transparent pricing for high-volume usage

SaneReads uses a straightforward per-character model for medical content generation. You pay $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful audio synthesis.

Pay only for characters generated

Costs are directly proportional to text length. This makes it easy to predict expenses for large patient guide libraries or high-volume clinical documentation projects without guessing usage volumes.

  • $10 per 1 million characters
  • $0.01 per 1,000 characters
  • Spaces and punctuation count as characters

No monthly fees or minimum spends

There are no monthly plans, seats, or minimum spending requirements. You can scale up during peak periods and scale down without penalty. Balance does not expire, allowing you to carry over credits indefinitely.

  • No monthly fees
  • No minimum spend
  • No subscriptions

Free trial credit for immediate testing

Sign up with Google to receive $0.50 of trial credit, valid for 7 days. This allows your team to test the API with real medical texts before committing to larger volumes. Email-based accounts start without this credit.

Transparent pricing for high-volume usage

Compliance and data handling

Sound wave illustration for: Compliance and data handling

Your clinical content stays private. We use input text solely to generate the audio response, ensuring patient guide drafts remain confidential. The generated audio is returned directly in the API response and is not stored on our servers, reducing your data retention burden.

We retain only request metadata—such as timestamp, character count, and status—strictly for accurate billing. This minimal data keeps your compliance footprint light without sacrificing transparency.

Input text not used for training

Input text is used only to produce the audio and is not used for training. Your clinical content remains yours, ensuring that sensitive patient guide language or internal protocol text isn’t repurposed for improving our engine.

This distinction matters for healthcare teams managing proprietary or regulated content, as it eliminates the risk of your specific phrasing appearing in future public outputs.

Audio returned in response, not stored

The audio files generated from your text are transmitted back to you in the API response and are not persisted on our infrastructure. This means we hold no copy of your final patient education materials after delivery.

By not storing the audio, we simplify your data governance, as you maintain full control over where and how long the audio files reside within your own systems.

Metadata kept only for billing accuracy

We keep minimal metadata—specifically the time of request, character count, and status code—solely to ensure accurate billing and to help you track usage patterns.

This data does not include the content of your text or audio, keeping your privacy high while providing the transparency needed for large-scale team budgeting.

How it works: From text to audio

Sound wave illustration for: How it works: From text to audio

The API transforms your clinical text into clear audio files through a straightforward POST request. By sending your content to the designated endpoint, you trigger the synthesis engine, which processes the input and returns the generated audio file in your preferred format, ready for immediate integration into patient guides or video overlays.

Send text via POST request

Initiate synthesis by sending a JSON body to the speech endpoint. Include your model choice (tts-1 or tts-1-hd), the input text, and the desired voice preset. Authentication is handled via a Bearer token in the Authorization header, ensuring secure access to the generation engine.

  • Use POST https://api.titan33.info/v1/audio/speech
  • Include model, input, voice, and response_format in JSON
  • Authenticate with your unique API key

Receive audio file in your chosen format

The system returns the synthesized audio directly in the response, supporting formats like MP3, WAV, Opus, FLAC, and PCM. You can select the format that best fits your delivery platform, whether it’s a web patient portal or a downloadable PDF guide.

Handle long texts with automatic splitting

Medical texts often exceed the 4096-character limit per request. The API handles this by splitting longer inputs into manageable parts, generating individual audio segments, and joining them into a single continuous file. This ensures seamless playback for detailed post-operative instructions or comprehensive drug interaction explanations without manual chunking.

Common medical use cases

Sound wave illustration for: Common medical use cases

Medical teams often struggle to keep patient education materials current. When clinical guidelines shift, rewriting scripts for manual recording is slow and expensive. Our API allows you to update audio content instantly by simply changing the source text, ensuring every patient hears the most recent advice.

Consistency is key for trust. Using the same voice for post-op instructions, drug explanations, and triage guides creates a recognizable, calming brand experience across all digital touchpoints without managing multiple voice actors.

Post-operative care instructions

Generate clear, step-by-step audio guides for discharge instructions. Use Atlas for neutral, easy-to-follow updates or Luna for a softer, empathetic tone that helps reduce patient anxiety. Update the script instantly if hospital protocols change, ensuring every patient receives accurate care steps.

You can distribute these via patient portals or QR codes in recovery rooms. The API handles long texts by splitting them into seamless audio segments, perfect for detailed recovery protocols.

  • Instant updates when protocols change
  • Consistent tone across all departments
  • Support for detailed, long-form instructions

Drug interaction explanations

Explain complex pharmacology in simple terms. Sage’s calm, instructional voice works well for explaining side effects and dosage schedules. Generate distinct audio clips for different medications, allowing patients to listen to specific drug information on demand.

Since characters are billed per 1,000, short, precise explanations are cost-effective. You can easily regenerate audio if dosage instructions or warnings change in the pharmaceutical label.

  • Clear, calm instructional tone
  • Easy to regenerate for label changes
  • Cost-effective for short clips

Symptom checkers and triage guides

Integrate TTS into your symptom checker tools. Provide immediate audio feedback for triage recommendations, helping users who may have difficulty reading or want a second confirmation. The API supports 23 languages, making it easy to serve diverse patient populations without separate recordings.

Use Nova for upbeat, engaging prompts or Orion for serious, documentary-style warnings. Requests are processed one after another, so under load a request may wait in a queue.

  • Support for 23 languages
  • Fast processing for real-time apps
  • Flexible voice selection for tone

Get started with the API

Sound wave illustration for: Get started with the API

SaneReads is built for healthcare teams who need reliable audio generation without manual recording overhead. Our API integrates directly with your existing content workflows, allowing you to turn patient guides and clinical texts into clear audio files instantly.

Create your account in seconds

Sign up on our /get-api-key/ page using your Google account or email. Accounts are created per site, ensuring your team’s access is managed independently and securely.

Get your API key instantly

Once registered, you receive a single active Bearer key. You can issue a new key at any time, and the old one stops immediately, keeping your integrations simple and secure.

Start generating with $0.50 free credit

Google sign-ups include $0.50 of free trial credit, valid for 7 days. This covers approximately 50,000 characters, allowing you to test voice quality and API performance before committing to paid usage.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Their upbeat, rapid cadence can obscure important medical details, especially for those with hearing impairments.

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-python on GitHub
  3. FFmpeg documentation
  4. Tether (USDT)
  5. openai-node on GitHub
  6. LibriTTS-R corpus (OpenSLR 141)
  7. Creative Commons Attribution 4.0
  8. OpenAI API reference: create speech
  9. curl documentation
  10. LibriVox public-domain audiobooks
  11. Python documentation
  12. Node.js documentation

More on this site