A Reliable TTS API Key for Medical Patient Guides

By MediSpeak editorial team · Updated 2026-11-19

MediSpeak delivers a reliable text-to-speech API designed specifically for healthcare product teams generating patient education materials. We replace complex voice configurations and unpredictable billing with a straightforward, character-based pricing model. This ensures predictable costs for your medical guides without hidden fees or minimum commitments.

This page outlines the technical specifications, supported voices, and compliance features that make our API suitable for clinical use cases. You will find concrete integration details, pricing transparency, and data privacy guarantees tailored to teams who need clear, compliant audio output for patient-facing applications.

A Reliable TTS API Key for Medical Patient Guides

Frequently asked questions

Is this Google Cloud TTS?

No. MediSpeak is an independent API, not affiliated with Google. It uses a compatible endpoint structure similar to OpenAI, allowing you to use standard SDKs by changing the base URL. We are a separate entity offering a straightforward alternative for healthcare product teams without proprietary lock-in or brand confusion.

What is the character limit per request?

Each request supports up to 4096 characters. For longer patient education materials, split the text into chunks of this size and join the resulting audio files. This ensures consistent processing and avoids payload limits while maintaining the integrity of your medical documentation delivery workflow.

How many languages are supported?

We support 23 languages, including English, Spanish, Chinese, Arabic, and German. Any voice can speak any of these languages. If you do not specify a language, the system guesses it from the script, defaulting to English for Latin text. Vietnamese and Thai are not supported.

Can I clone my own voice?

No. We do not offer custom voice cloning, voice uploading, or voice design. You must choose from our eight preset voices (e.g., Aria, Felix, Atlas). These are based on licensed recordings from LibriTTS-R and LibriVox, providing consistent, high-quality synthetic speech without the complexity of custom model training.

What is the pricing model?

Pricing is $10 per 1 million characters ($0.01 per 1,000 characters). Failed requests are free. We do not offer monthly plans, seats, or minimum spends. Payment is via USDT on TRON. Balance does not expire, and spaces/punctuation count toward the character limit for accurate billing.

Do I need an SLA for production?

We do not provide an SLA, uptime guarantee, or enterprise contract. Requests are processed sequentially, so under load, synthesis may queue. Typical speed is roughly real-time. This model suits most patient guide integrations but lacks the formal guarantees required by some high-availability clinical systems.

Is there a free trial available?

Yes. Signing in with Google provides $0.50 credit (approx. 50,000 characters) valid for 7 days. Email/password accounts start without trial credit. You can top up via USDT (TRC-20) for continued use. This allows testing integration with healthcare data formats before committing to a paid USDT balance.

How do I set the language?

Include the optional language field in your JSON request with an ISO code. If omitted, the system guesses the language from the script, defaulting to English for Latin text. Explicitly setting the language ensures accuracy for non-English Latin-script texts, such as Spanish or German medical terms.

What audio formats are available?

You can request audio in mp3, wav, opus, flac, or pcm formats. These are standard formats suitable for web players, EHR systems, and archival storage. The API returns the audio file directly in the response, allowing immediate playback or storage in your healthcare content management system.

Can I use this for commercial patient guides?

Yes. The voices are based on licensed recordings (LibriTTS-R CC BY 4.0 and LibriVox public domain). Generated files include an inaudible watermark marking them as synthetic. Input text is not used for training, making this suitable for commercial patient education materials without additional licensing complexity.

How are voices licensed?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This provides clear licensing for commercial use. Each generated file carries an inaudible watermark indicating synthetic origin, which helps maintain transparency with patients regarding the nature of the audio content.

Is there a rate limit?

Yes, 60 requests per minute per key (10 per minute before the first top-up). Requests are processed sequentially, so under load, a request may wait in a queue. Plan your patient guide generation batches accordingly to avoid delays, especially during peak usage hours for your application.

Do you support SSML?

No. We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control prosody via the speed parameter (0.25–4.0). This simplifies integration for product teams who do not need fine-grained phonetic control but require reliable, consistent synthetic speech for medical documentation and patient guides.

How do I get support?

Support is by email only. We do not offer phone support, live chat, or SLAs. For technical issues with your API key or billing, send an email. This streamlined support model keeps costs low and aligns with the straightforward, engineering-focused nature of our API offering.

First request

curl

curl https://api.pj88.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 switch from Google Cloud TTS?

Sound wave illustration for: Why switch from Google Cloud TTS?

Google Cloud TTS requires manual voice selection, regional configuration, and complex project setup. MediSpeak offers a single API key with eight curated voices, removing the need to manage multiple voice IDs or regional endpoints. You send text and receive audio without negotiating custom voice parameters.

Simplified character-based billing

Simplified character-based billing

Google bills by character but often includes hidden costs for streaming or specific features. We charge strictly $10 per 1 million characters, with spaces and punctuation counted. Failed requests are free, ensuring you only pay for successful synthesis.

  • No minimum spend or monthly commitments
  • Simple per-character calculation
  • Instant refunds for failed requests

No complex voice configuration

You do not need to configure SSML or select regional variants. Choose from eight presets like Aria for narration or Sage for instruction. The API handles language detection or accepts an explicit ISO code, simplifying integration for patient guides.

  • Eight pre-configured voices
  • Automatic or explicit language setting
  • No SSML required

Predictable costs for patient guides

Healthcare content often involves long texts split into 4096-character chunks. Our pricing remains linear and transparent. With a $0.50 trial credit, you can test volume without upfront investment. No enterprise contracts or usage spikes affect your budget.

  • Linear pricing model
  • $0.50 trial credit
  • No volume-based surprises

How it works

Sound wave illustration for: How it works

To integrate MediSpeak, send a POST request to the speech endpoint with your text and desired parameters. The API returns the generated audio file directly in the response body, allowing you to save the output immediately.

Send text, receive audio

Submit up to 4096 characters per request using standard JSON formatting. The service processes the input and returns the audio file in your chosen format, ensuring a straightforward data flow for your application.

OpenAI SDK compatibility

Use the official OpenAI SDKs by updating the base URL to https://api.pj88.info/v1. This allows you to leverage existing client libraries and code structures without rewriting integration logic for our specific API shape.

Instant API key generation

Sign up via Google or email to receive your API key immediately. The key is active for requests upon creation, enabling you to start testing and generating audio files immediately.

Clinical Voices for Patient Education

Sound wave illustration for: Clinical Voices for Patient Education

For patient education, clarity is non-negotiable. Aria provides a warm, clear narrator voice ideal for reading detailed medical explanations or consent forms. Her tone ensures complex instructions remain accessible without sounding robotic.

Clear narration with Aria

Aria’s steady pacing reduces cognitive load for patients reviewing post-op care or medication schedules. Her voice is consistent across multiple sentences.

Calm instruction with Sage

Sage offers a calm, instructional tone perfect for step-by-step procedural guides. Her neutral delivery prevents misinterpretation of critical health advice, making her suitable for both digital apps and printed QR code audio.

Engaging storytelling with Luna

Luna brings a soft, storytelling quality to patient journeys or disease awareness campaigns. Her expressive yet gentle tone helps humanize clinical data.

Supported Languages for Global Health

Sound wave illustration for: Supported Languages for Global Health

MediSpeak supports 23 languages for global patient education, including Spanish, French, German, Arabic, and Chinese. This allows product teams to distribute standardized medical guides across diverse populations without managing multiple voice providers or complex localization pipelines.

23 languages including Spanish and French

We cover the primary languages required for broad healthcare accessibility. The supported list includes Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.

Automatic language detection

If the language field is omitted, the API infers the language from the text script. Latin script defaults to English. This reduces payload size for simple English patient guides.

Explicit language setting for Latin scripts

For non-English Latin-script text (e.g., Spanish or Portuguese), set the language parameter explicitly. This ensures accurate pronunciation and prevents the engine from defaulting to English. Unsupported languages like Vietnamese or Thai are not available.

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

Technical Specifications

Sound wave illustration for: Technical Specifications

The API returns audio in MP3, WAV, OPUS, FLAC, or PCM formats, allowing seamless integration with existing healthcare media players and EHR systems. Requests are processed sequentially, with generation speed averaging real-time for long texts, though short phrases may require a few seconds.

MP3, WAV, OPUS, FLAC formats

Choose the format that best fits your delivery channel. MP3 offers efficient compression for web playback, while WAV and FLAC provide lossless quality. PCM is available for raw audio processing.

Speed control from 0.25x to 4.0x

Adjust speech rate between 0.25 and 4.0 to accommodate different patient needs. Slower speeds (e.g., 0.75x) may improve comprehension, while faster speeds suit quick reference guides.

4096 character limit per request

Each API call accepts up to 4096 characters, including spaces and punctuation. For longer patient guides, split the text into chunks and join the resulting audio files. Requests are queued under load, so plan for slight delays during peak usage.

Technical Specifications

Pricing Transparency

Sound wave illustration for: Pricing Transparency

MediSpeak uses straightforward character-based billing at $10 per 1 million characters. Spaces and punctuation count toward the total, ensuring predictable costs for patient education materials. You pay only for what you process, with no hidden fees or complex tiered structures.

If a synthesis request fails, the charge is returned in full. This eliminates risk for batch processing large medical guides.

$10 per 1 million characters

The rate is $0.01 per 1,000 characters. This linear pricing model scales directly with your volume, making it easy to forecast monthly spend for high-volume patient onboarding workflows.

Free failed requests

Synthesis failures result in a full refund of the character cost. You are never charged for audio that does not successfully generate, protecting your budget during integration testing or edge-case handling.

No monthly minimums

There are no required minimum spends or recurring subscription fees. You can top up with USDT (TRC-20) starting at $5, and the balance never expires. This structure suits teams with variable usage patterns.

Integration for Product Teams

Sound wave illustration for: Integration for Product Teams

Integrate MediSpeak into your healthcare product workflow with minimal overhead. Our API follows standard patterns, allowing your team to generate patient education audio using familiar tools and existing infrastructure.

We provide clear documentation and direct code examples to accelerate your integration sprint. Start with a simple request and scale as your content library grows.

Easy curl example

Generate your first audio file immediately. Use the following command to send a text request and receive an MP3 file.

curl -X POST "https://api.pj88.info/v1/audio/speech" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Please take this medication with food.", "voice": "aria", "response_format": "mp3"}'

JSON body structure

The request body accepts standard parameters. You can specify the model, voice, and speed. The input text is limited to 4096 characters per request.

You can also set the language explicitly to ensure accurate pronunciation for Latin-script texts that are not English.

  • model: "tts-1" or "tts-1-hd"
  • voice: e.g., "aria", "sage", "nova"
  • input: string, max 4096 chars
  • response_format: mp3, wav, opus, flac, pcm
  • speed: 0.25–4.0
  • language: optional ISO code

Standard base_url configuration

Use the official OpenAI SDKs by setting the base URL to our endpoint. This allows you to reuse existing client code with minimal changes.

Set the base URL to "https://api.pj88.info/v1" and use your API key for authentication. This approach simplifies integration for teams already familiar with standard TTS clients.

  • Base URL: https://api.pj88.info/v1
  • Auth: Bearer token
  • Compatible with OpenAI SDKs

Data Privacy and Compliance

Sound wave illustration for: Data Privacy and Compliance

Data handling is designed for clarity and minimal footprint. Your input text is processed solely to generate the audio response and is not used for model training, ensuring that patient education content remains distinct from your dataset improvements.

Input not used for training

We use your input text exclusively for synthesis. It is not ingested into our training data, preserving the integrity of your specific medical narratives and guides.

No storage of generated audio

Generated audio files are returned directly in the response and are not stored on our servers after delivery. This reduces data retention risk for sensitive patient materials.

Metadata kept for billing only

We retain request metadata—such as timestamp, character count, and status—strictly for accurate billing and usage tracking. This data is not used for product development or analytics beyond invoicing purposes.

Get Started Today

Sound wave illustration for: Get Started Today

Create your MediSpeak account on /get-api-key/ using your Google credentials for instant access. Unlike email-based accounts, Google sign-ups immediately include a $0.50 free trial credit, sufficient for approximately 50,000 characters of patient education audio.

Sign up with Google

Visit the registration page and select the Google sign-in option. This method instantly provisions your account with initial trial credit, valid for seven days, allowing immediate testing without a credit card or top-up.

Receive your API key

Your dashboard displays a single active Bearer token (tts-...) ready for use. You can generate a new key at any time; the previous key stops working immediately, ensuring secure access for your product team.

Start generating audio

Use the provided curl example or OpenAI SDK with the base URL https://api.pj88.info/v1. Send text to POST /v1/audio/speech and receive an audio file directly, beginning your compliance-friendly TTS integration.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Medical product teams need predictable budgets for patient education materials.

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. openai-node on GitHub
  4. OpenAI API reference: create speech
  5. LibriTTS-R corpus (OpenSLR 141)
  6. ISO 639 language codes
  7. TRON developer hub: TRC-20
  8. curl documentation
  9. Creative Commons Attribution 4.0
  10. IETF RFC 7845: Ogg Opus
  11. LibriVox public-domain audiobooks
  12. FFmpeg documentation

More on this site