Text to Speech API for SaaS Notifications and Interfaces

By Readly API editorial team · Updated 2026-11-18

This page introduces the Readly API, a straightforward text-to-speech solution built specifically for indie developers who need reliable audio for SaaS notifications and interfaces. We provide a simple JSON API that integrates easily into your existing workflows, allowing you to convert text into audio files without managing complex infrastructure or enterprise contracts.

You will find concrete details on our eight natural voices, 23 supported languages, and developer-friendly features like OpenAI SDK compatibility. We also cover our transparent pricing, data privacy guarantees, and quick start guide so you can generate your first audio file in minutes using your $0.50 free trial credit.

Text to Speech API for SaaS Notifications and Interfaces

Frequently asked questions

Is the text to speech mp3 free tier available?

Yes, signing in with Google provides a $0.50 trial credit valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without this trial credit. After the trial expires or is used, you must top up your balance to continue generating audio files.

Which voices are available for SaaS notifications?

We offer eight presets suitable for various tones: aria, nova, luna, and sage (female); felix, milo, atlas, and orion (male). For SaaS notifications, milo offers a friendly conversational tone, while atlas provides a neutral news style. All voices support 23 languages and can be adjusted for speed between 0.25 and 4.0.

How many languages does the API support?

The API supports 23 languages: 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, and the system guesses the language from the script if not explicitly set.

Can I use the OpenAI SDK with this API?

Yes, our endpoint matches the OpenAI speech endpoint shape. You can use the official OpenAI SDKs by changing the base_url to https://api.playpx9.com/v1 and using your Readly API key. This allows indie developers to integrate high-quality TTS into their existing workflows without learning a new library structure.

What happens if a request fails?

If synthesis fails, the charge is returned in full, so you are not billed for errors. Failed requests are free. This ensures predictable costs for your SaaS notifications. You only pay for successfully generated audio files, making our pricing model honest and transparent for indie developers managing their budgets.

Is there a rate limit on the API?

Yes, the limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. If you exceed this, requests may wait in a queue. For longer texts, split them into parts of up to 4096 characters and join the resulting audio files.

Do you support streaming audio?

No, we do not support streaming, WebSocket, or real-time partial audio. You send text via POST and receive the complete audio file. This synchronous approach simplifies integration for indie developers who prefer predictable, file-based responses over managing complex streaming connections or partial data buffers.

Can I clone my own voice?

No, we do not offer custom voice cloning or uploading your own voice. Our eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. If you need a specific voice, you must choose from our available presets.

Is SSML supported for voice control?

No, SSML is not supported. You cannot use phoneme dictionaries or custom pronunciation lexicons. Control is limited to the voice preset, speed (0.25–4.0), and language code. This simplicity reduces integration complexity for indie developers who want straightforward text-to-speech without managing complex markup structures for every edge case.

How are characters counted for billing?

Billing is based on character count, including spaces and punctuation. The rate is $10 per 1 million characters, or $0.01 per 1,000 characters. Each request handles up to 4096 characters. Failed requests are free, so you only pay for the characters in successfully generated audio files.

What audio formats can I receive?

You can receive audio in mp3, wav, opus, flac, or pcm formats. Specify the desired format in the response_format field of your JSON request. All formats are generated from the same engine, ensuring consistent quality regardless of your choice. This flexibility allows you to optimize for file size or compatibility.

Is my input text used for training models?

No, your 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 like time and status for billing purposes, ensuring your data remains private and dedicated solely to generating your audio files.

How do I top up my balance?

Top up using USDT on the TRON network (TRC-20) only. The minimum amount is $5, and credits are automatically added within minutes after your transfer. We do not accept cards, PayPal, or subscriptions. Your balance does not expire, and you can issue a new API key anytime if needed.

Do you offer phone support?

No, we do not offer phone support or live chat. Support is provided via email only. We focus on building a simple, predictable API for indie developers rather than maintaining enterprise-level support infrastructure. This keeps our overhead low and our pricing competitive for small teams and individual developers.

First request

curl

curl https://api.playpx9.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 Indie Developers Choose Our TTS API

Sound wave illustration for: Why Indie Developers Choose Our TTS API

Indie developers need reliable text-to-speech without enterprise overhead. Our API delivers a straightforward JSON endpoint compatible with the official OpenAI SDKs, requiring only a base_url change. You get predictable integration for SaaS notifications and interfaces without learning a new proprietary protocol.

Simple JSON API compatible with OpenAI SDKs

Simple JSON API compatible with OpenAI SDKs

Send text via a standard POST request and receive audio files directly. The request shape mirrors OpenAI’s speech endpoint, allowing you to use familiar libraries like openai-python by simply pointing to our base URL. This reduces boilerplate code and accelerates development cycles.

  • Standard JSON request body with model, input, and voice parameters
  • Compatible with official OpenAI SDKs via simple base_url configuration
  • Supports both tts-1 and tts-1-hd models

No monthly plans or minimum spend required

Start using the API immediately without committing to a recurring subscription. There are no seats to manage and no minimum monthly fees to worry about. You maintain full control over your infrastructure costs, scaling up or down based on actual usage demands.

  • No monthly subscription plans
  • No minimum spend requirements
  • No per-seat licensing fees

Pay only for characters you actually use

Your billing is directly tied to character count, not request volume. Each character, including spaces and punctuation, counts toward your usage. Failed requests are free, ensuring you only pay for successfully generated audio. This transparent model prevents unexpected costs during high-traffic periods.

  • $10 per 1 million characters
  • Failed requests are free
  • Spaces and punctuation count as characters

8 Realistic Voices, 23 Languages

Sound wave illustration for: 8 Realistic Voices, 23 Languages

Choose from eight distinct voices designed for clarity and tone, ranging from warm narration to energetic promo styles. Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. You can pick the perfect tone for your SaaS notifications or interface elements with these eight presets.

Female voices: Aria, Nova, Luna, Sage

Aria offers a warm, clear narrator style ideal for explanatory content. Nova provides a bright, upbeat tone for engaging updates. Luna brings a soft, storytelling quality for narrative-driven interfaces. Sage delivers a calm, instructional voice perfect for guides and tutorials.

Male voices: Felix, Milo, Atlas, Orion

Felix is energetic and great for promotional announcements. Milo sounds friendly and conversational, suitable for user interactions. Atlas provides a neutral, news-style delivery for factual updates. Orion offers a deep, documentary tone for serious or immersive content.

Any voice speaks any supported language

All eight voices support 23 languages, including English, Spanish, German, French, Japanese, and Chinese. You are not restricted to matching voice gender to language. If the language is not specified, the system guesses from the script, but setting it explicitly ensures accuracy.

Supported Audio Formats

Sound wave illustration for: Supported Audio Formats

We support five standard audio formats to fit your workflow. Choose MP3 for universal web compatibility or WAV and FLAC when you need uncompressed, high-fidelity audio for professional interfaces.

MP3 for web compatibility

MP3 is the default choice for most web applications. It offers compression suitable for web delivery, ensuring fast loading times across all browsers and devices.

WAV and FLAC for high fidelity

Select WAV for lossless, uncompressed audio or FLAC for lossless compression with smaller file sizes. These formats are ideal when you need lossless audio for notifications or archival purposes.

OPUS and PCM for efficient processing

OPUS provides efficient compression suitable for low-bandwidth environments, while PCM offers raw, uncompressed audio data. Use these formats when you need precise audio handling or are processing streams directly.

How It Works

Sound wave illustration for: How It Works

You integrate the Readly API by sending a simple POST request to the speech endpoint. The JSON body follows the familiar OpenAI shape, requiring only the model, input text, voice selection, and desired response format. This standard structure means you can reuse existing TTS logic with minimal code changes.

Once submitted, the API processes your text and returns the generated audio file directly in the response. You receive the audio in your chosen format—MP3, WAV, OPUS, FLAC, or PCM—ready to play in your SaaS interface or trigger notifications without additional processing steps.

Send text via POST request

Use the POST https://api.playpx9.com/v1/audio/speech endpoint with a JSON payload. Specify the model (tts-1 or tts-1-hd), your input text (up to 4096 characters), and the voice preset. You can also set response_format and speed (0.25–4.0). Authentication is handled via the Authorization: Bearer header with your unique API key.

  • Endpoint: POST https://api.playpx9.com/v1/audio/speech
  • Auth: Authorization: Bearer tts-...
  • Body: JSON with model, input, voice, response_format

Receive audio file in response

The API returns the synthesized audio file immediately upon completion. The response contains the binary audio data in your selected format, allowing you to save it for later use. For texts exceeding 4096 characters, split the input and join the resulting audio files sequentially.

Handle errors and retries easily

If synthesis fails, the request is processed but no charge is applied, ensuring you only pay for successful generations. Standard HTTP status codes indicate success or failure, making it easy to implement retry logic. Use the official OpenAI SDKs by changing the base_url to https://api.playpx9.com/v1 for familiar error handling.

  • Failed requests are free
  • Standard HTTP status codes
  • Compatible with OpenAI SDK error handling

Speed and Performance

Sound wave illustration for: Speed and Performance

Generation speed scales with text length. Long texts process at roughly real-time speed, consuming about 25 characters per second. Short phrases may take a few seconds to synthesize completely, as the engine processes requests sequentially.

Real-time generation for long texts

Efficiency shines with longer content. For extended texts, the API generates audio at roughly real-time speed, handling up to 4096 characters per request. This makes it ideal for SaaS notifications or interface updates where immediate delivery matters.

Adjustable speed from 0.25x to 4.0x

Control the pacing to fit your interface. The speed parameter accepts values from 0.25 to 4.0, allowing you to slow down instructional content or speed up brief alerts. This flexibility ensures the audio matches your app’s tone without post-processing.

Queue processing under load

Requests are processed sequentially. Under high load, a request may wait in a queue before synthesis begins. While this ensures consistent quality, it means generation time can exceed real-time during peak usage periods. Plan your integrations accordingly.

Speed and Performance

Developer Friendly Features

Sound wave illustration for: Developer Friendly Features

Integrate high-quality TTS into your SaaS notifications with minimal code. Our endpoint mirrors the OpenAI speech structure, meaning you can switch providers without rewriting your client logic. Just update the base URL and keep using the official OpenAI SDKs you already know.

Debugging is straightforward. We provide clear, standard error codes so you can handle failures gracefully. Your dashboard includes ready-to-use cURL examples, letting you test the API immediately without building a UI first.

Use official OpenAI SDKs with base_url change

Leverage existing infrastructure by pointing your OpenAI SDK to https://api.playpx9.com/v1. The request shape is identical, so migration is a one-line change. This compatibility extends to all major SDKs, ensuring a smooth developer experience.

bullets

Clear error codes for debugging

We return standard HTTP status codes and descriptive error messages. If a request fails due to rate limits or invalid parameters, you get immediate feedback. This clarity helps you resolve issues quickly without guessing.

bullets

Ready curl examples on dashboard

Your account dashboard at /get-api-key/ displays pre-configured cURL commands. Use these to verify your key and test voice synthesis instantly. Copy, paste, and get an audio file in seconds.

bullets

Pricing Transparency

Sound wave illustration for: Pricing Transparency

Predictable billing is essential for indie developers building scalable SaaS products. Readly API charges a flat rate of $10 per 1 million characters, ensuring you only pay for the text you actually process. Spaces and punctuation count as characters, making cost estimation straightforward without hidden surprises.

$10 per 1 million characters

The cost is exactly $0.01 per 1,000 characters. This simple formula applies to all models, including tts-1 and tts-1-hd, which share the same engine and price. You can easily calculate your budget based on expected notification volumes or interface usage.

Failed requests are free

If synthesis fails for any reason, the charge is returned in full. You are not billed for incomplete or errored audio generations, protecting your balance during debugging or unexpected API issues.

No hidden fees or subscriptions

There are no monthly plans, seats, or minimum spends. Balance does not expire. You top up with USDT (TRC-20) as needed, with a minimum of $5. Accounts start with a $0.50 free trial credit when signing in with Google, valid for 7 days.

Data Privacy and Licensing

Sound wave illustration for: Data Privacy and Licensing

Your input text is used exclusively to generate the audio file and is never added to our training data. Once the synthesis completes, the generated audio is returned in the response and is not stored on our servers, ensuring your content remains yours.

Input text not used for training

We process your text solely for the immediate purpose of creating the audio file. Unlike many consumer AI services, we do not harvest your input data to improve our models, keeping your proprietary content private and secure.

Audio not stored after response

The resulting audio file is transmitted directly to your application and is not retained in long-term storage. We keep only the necessary request metadata—such as timestamp, character count, and status—for accurate billing and debugging purposes.

Voices from licensed LibriTTS-R and LibriVox

Our eight voice presets are built upon licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures high-quality synthetic speech while respecting the original creators' licensing terms.

Get Started Today

Sound wave illustration for: Get Started Today

Head over to our /get-api-key/ page to create your account. You can sign in securely using your Google account or set up a traditional email and password combination. This quick setup ensures you are ready to start integrating text-to-speech into your SaaS notifications or interfaces without delay.

Sign up with Google or email

Creating an account takes less than a minute. We keep the process straightforward so you can focus on building your product rather than navigating complex enterprise onboarding flows.

Get your API key instantly

Once registered, you receive a unique API key immediately. The dashboard displays your key, current balance, and a ready-to-use cURL example, making integration into your codebase seamless from day one.

  • One active key per account
  • Replace old keys instantly if needed
  • Compatible with standard OpenAI SDKs

Test with $0.50 free trial credit

Google sign-ups include a $0.50 free trial credit, valid for 7 days. This covers approximately 50,000 characters, allowing you to verify voice quality and latency before committing to top-ups.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

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 API reference: create speech
  3. ISO 639 language codes
  4. Node.js documentation
  5. TRON developer hub: TRC-20
  6. LibriTTS-R corpus (OpenSLR 141)
  7. FFmpeg documentation
  8. LibriVox public-domain audiobooks
  9. MDN: Web Speech API
  10. Python documentation
  11. Tether (USDT)
  12. W3C WAI: making audio and video accessible

More on this site