Cloud Text-to-Speech API for WordPress Publishers

By ScribeSound editorial team · Updated 2026-11-18

ScribeSound provides a lightweight text-to-speech API designed for WordPress bloggers and content publishers who need reliable audio without complex integrations or monthly fees. Enhance your articles and keep readers engaged by converting your written content into high-quality audio files with a simple API or free online tool.

Access high-quality voices via a straightforward API that works with your existing WordPress setup. Whether you are looking to boost read time, ensure accessibility compliance, or reach a multi-language audience, ScribeSound offers a transparent, pay-per-character pricing model that fits any publishing workflow.

Cloud Text-to-Speech API for WordPress Publishers

Frequently asked questions

Is the text-to-speech really free?

Yes, you get a free trial with $0.50 credit (about 50,000 characters) valid for 7 days when signing in with Google. After that, usage costs $0.01 per 1,000 characters. Failed requests are free, and there are no monthly subscriptions or minimum spending requirements.

How many languages are supported?

We support 23 languages, including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any of these languages. If you do not specify a language, it is guessed from the script, though you should set it explicitly for non-English Latin text.

Can I use the API for my WordPress site?

Absolutely. Our API follows the same request shape as the OpenAI speech endpoint, so you can easily integrate it into your WordPress site. Simply change the base URL to https://api.play55win.com/v1 and use your API key with standard HTTP requests or the OpenAI SDK.

What happens if my request fails?

If synthesis fails, the charge is returned in full. You only pay for successfully generated audio files. This ensures you are never charged for errors, making it safe to implement retry logic in your WordPress plugin or application without worrying about unexpected costs.

Do I need to sign up for a subscription?

No, there are no monthly plans or subscriptions. You pay only for what you use at $10 per million characters. You can top up your balance with USDT on the TRON network, and your balance never expires. There are no seats or minimum spends.

Are the voices realistic for blog content?

Our eight voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They include warm narrators, upbeat speakers, and calm instructional voices. Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring transparency for your readers.

How long does it take to generate audio?

Generation is roughly real-time, processing about 25 characters of text per second of audio. Short phrases take a few seconds, while longer texts may take longer. Requests are processed sequentially, so under heavy load, a request might wait in a queue briefly.

Can I use the generated audio for monetized content?

Yes, you can use the generated audio for monetized content. 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 by us, giving you full control over your content.

What is the character limit per request?

Each request supports up to 4,096 characters of input text. For longer texts, you can split them into parts of this limit and join the resulting audio files. Spaces and punctuation count toward the character total, so plan your splits accordingly for optimal results.

Does the API support different audio formats?

Yes, you can choose from mp3, wav, opus, flac, and pcm formats. This flexibility allows you to optimize file sizes for web delivery or use high-quality formats for podcasts. Simply specify your preferred response_format in the JSON body of your POST request.

Is my text used for training other models?

No, your input text is used only to produce the specific audio file you request. It is not used for training other models. We keep request metadata like time and status for billing purposes, but the actual content remains private and transient.

How do I top up my balance?

You can top up your balance using USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are automatically added within minutes after your transfer is confirmed. We do not accept cards, PayPal, or offer invoices with VAT.

What happens to my API key if I issue a new one?

You have one active key per account. If you issue a new key, the old one stops working immediately. This ensures security; if a key is compromised, you can regenerate it instantly without waiting for a manual review or expiration period.

Can I listen to voice samples before buying?

You can listen to voice samples by visiting the /docs/ page or using the free trial credit. The /v1/voices endpoint also provides details on available voices, languages, and formats. This lets you test the quality and style before committing to larger usage.

First request

curl

curl https://api.play55win.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 Publishers Choose TTS

Sound wave illustration for: Why Publishers Choose TTS

Adding audio to your WordPress articles is a straightforward way to keep readers engaged longer. When visitors can listen to your content while commuting or doing chores, they spend more time with your brand without the effort of reading.

Beyond engagement, audio makes your site accessible to visually impaired users or those with dyslexia. It also helps non-native speakers grasp your message more easily, removing language barriers that often cause visitors to leave quickly.

Boost Read Time

Audio content allows your audience to consume your posts passively. By offering a listen option, you cater to different reading habits and increase the time users spend on your pages, which is a key metric for content success.

  • Encourages passive consumption during commutes
  • Increases average session duration metrics
  • Reduces bounce rates for long-form articles

Accessibility Compliance

Providing audio versions of your text helps meet accessibility standards. It ensures that users with visual impairments or reading difficulties can access your content independently, making your blog more inclusive and compliant with modern web standards.

  • Supports screen readers and audio-only users
  • Assists users with dyslexia or visual impairments
  • Enhances overall user experience

Multi-language Reach

Your content can now reach audiences who prefer listening in their native language. With support for 23 languages, you can easily localize your articles without hiring separate voice actors, expanding your global readership efficiently.

  • Supports 23 languages including Spanish, German, and Japanese
  • No need for separate voice actors
  • Expand global audience reach

How It Works

Sound wave illustration for: How It Works

Generate audio from your blog content in three straightforward steps. This workflow is designed for WordPress publishers who need to integrate speech without complex infrastructure or monthly fees.

Paste Your Text

Copy the text from your WordPress editor and send it to the API endpoint. You can process up to 4,096 characters per request. For longer articles, split the text into parts and join the resulting audio files.

Choose a Voice

Select from eight distinct presets to match your content's tone. Options range from warm narrators like Aria to energetic promo voices like Felix. Each voice supports 23 languages, ensuring your audience hears clear, consistent speech.

  • Female voices: Aria, Nova, Luna, Sage
  • Male voices: Felix, Milo, Atlas, Orion

Get Audio

Receive your audio file via the API response. You can download MP3, WAV, OPUS, FLAC, or PCM formats and embed them directly into your WordPress posts to keep readers engaged.

How It Works

Available Voices

Sound wave illustration for: Available Voices

ScribeSound offers eight distinct voice presets, each engineered for clarity and natural pacing to keep blog readers engaged. Whether you are narrating a personal story or summarizing technical content, there is a voice that matches your tone.

Female Voices

Our female voices range from warm narrators to upbeat conversationalists. Aria provides a clear, professional narration style ideal for standard articles. Nova brings a bright, energetic tone perfect for lifestyle blogs and quick updates. Luna offers a soft, storytelling cadence that works well for longer reads, while Sage delivers a calm, instructional voice suitable for guides and tutorials.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Male Voices

Male voices are designed for specific content types, from promotional updates to deep-dive documentaries. Felix adds energy to promo content, while Milo offers a friendly, conversational tone for everyday posts. Atlas provides a neutral, news-like delivery for factual content, and Orion delivers a deep, documentary-style voice for serious topics.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Neutral Narrators

The selection includes voices that avoid strong emotional bias, making them versatile for a wide range of publishers. All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Each generated file includes an inaudible watermark to identify it as synthetic speech.

Supported Languages

Sound wave illustration for: Supported Languages

ScribeSound supports 23 languages, allowing you to reach global audiences without hiring multiple voice actors. Our API handles text in various scripts, ensuring your content sounds natural whether your readers are in Berlin, Tokyo, or Cairo.

You can specify a language code for precise control, or let the system guess based on the text. If you use Latin script for non-English languages, always set the language parameter to avoid defaulting to English.

Major European Languages

We support the most widely spoken languages in Europe, including English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Swedish, Danish, Norwegian, Finnish, Greek, and Turkish. This covers the vast majority of Western and Central European markets.

  • English, German, French, Spanish, Italian, Portuguese
  • Dutch, Polish, Russian, Swedish, Danish, Norwegian
  • Finnish, Greek, Turkish

Asian Languages

Expand your reach into Asia with support for Chinese, Japanese, Korean, and Hindi. These languages use distinct scripts, and our API detects them automatically. For mixed scripts, setting the language code ensures accurate pronunciation.

  • Chinese, Japanese, Korean, Hindi

Middle Eastern Languages

We support Arabic and Hebrew, allowing you to publish content for Middle Eastern audiences. The voices adapt to the script's direction and phonetics, providing a natural listening experience for readers in these regions.

  • Arabic, Hebrew

Pricing for Publishers

Sound wave illustration for: Pricing for Publishers

ScribeSound charges only for what you use: $10 per million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. If a request fails, you are not charged, ensuring you pay only for successful audio generation.

Pay Per Character

Calculate your exact costs before publishing. With a typical real-time generation speed, you can estimate usage based on article length. There are no hidden fees for format selection or voice choice.

  • $10 per 1,000,000 characters
  • $0.01 per 1,000 characters
  • Spaces and punctuation count
  • Failed requests are free

No Monthly Fees

Unlike many TTS providers, there are no monthly subscriptions or minimum spend requirements. You can scale from a few articles to thousands without worrying about overage charges or plan limits. Your balance never expires.

  • No monthly subscriptions
  • No minimum spend
  • No seats or limits
  • Balance does not expire

Free Trial Credit

Sign in with Google to receive $0.50 in free credit, valid for 7 days. This allows you to generate approximately 50,000 characters of audio to test voice quality and integration. Email-based accounts start without this trial credit.

  • $0.50 free credit
  • Google sign-in required
  • Valid for 7 days
  • Approx. 50,000 characters
Pricing for Publishers

API Integration

Sound wave illustration for: API Integration

ScribeSound uses the same request shape as the OpenAI Speech endpoint, meaning you can use the official OpenAI SDKs with just a base_url change. This compatibility simplifies integration for WordPress developers already familiar with standard TTS workflows.

You can also use plain HTTP or a simple curl command to send text and receive audio files directly, ensuring your publishing stack remains lightweight and flexible.

OpenAI Compatible

The API endpoint https://api.play55win.com/v1 accepts standard JSON bodies. By setting the base URL in the OpenAI SDK, you can leverage existing libraries without rewriting your integration logic.

This approach supports both tts-1 and tts-1-hd models, giving you control over quality and speed while maintaining a familiar developer experience.

  • Supports official OpenAI SDKs
  • Same request shape as OpenAI
  • Uses base_url configuration

Simple Curl Example

For quick testing or custom scripts, use a standard POST request. Send your text, select a voice, and receive the audio file immediately.

This method is ideal for WordPress plugins or background jobs that need to generate audio on the fly without heavy dependencies.

  • POST to /v1/audio/speech
  • JSON body with text and voice
  • Returns audio file directly

WordPress Ready

The lightweight nature of the API makes it perfect for WordPress environments. Generate audio files for blog posts, podcasts, or accessibility features with minimal overhead.

You can integrate the API into your theme or plugin to automatically create audio versions of your articles, enhancing reader engagement without complex setups.

  • Easy WordPress integration
  • Minimal code requirements
  • Perfect for blog audio

Quality & Format

Sound wave illustration for: Quality & Format

ScribeSound delivers clear, natural-sounding audio optimized for web consumption. You can choose between MP3 for efficient storage, or WAV for high-fidelity archival needs. Other formats include OPUS, FLAC, and PCM. The synthesis engine preserves natural intonation and pacing, making long-form articles and blog posts engaging to listen to without sounding robotic.

MP3 and WAV Support

Select the format that best fits your WordPress workflow. MP3 offers smaller file sizes for faster page loads, while WAV provides uncompressed audio quality. Other formats like OPUS and FLAC are also available.

Realistic Synthesis

Voices are based on licensed recordings from LibriVox, ensuring a human-like cadence. Each generated file includes an inaudible watermark to identify it as synthetic speech, maintaining transparency for your readers.

Fast Generation

Generation speed is roughly real-time, processing about 25 characters per second. Short phrases take just a few seconds to synthesize, keeping your content pipeline moving smoothly even during high traffic.

Technical Limits

Sound wave illustration for: Technical Limits

ScribeSound is built for reliability, but certain technical boundaries ensure consistent performance for your WordPress content. Understanding these limits helps you structure articles and manage API traffic effectively without unexpected interruptions.

4096 Character Limit

Each API request accepts a maximum of 4,096 characters. If your article excerpt or blog post section exceeds this length, you must split the text into smaller chunks and join the resulting audio files sequentially.

Rate Limits

You are allowed 60 requests per minute per API key. If you are processing long articles via script, this queue ensures fair usage. New accounts start with a limit of 10 requests per minute until the first top-up.

Voice Consistency

Voices are preset and do not change dynamically. While the engine maintains consistent tone and quality, you cannot adjust emotion, pitch, or pronunciation in real-time. Each generated file includes an inaudible watermark to identify it as synthetic speech.

Technical Limits

Get Started

Sound wave illustration for: Get Started

Start by signing up with your Google account on the /get-api-key/ page. This instant method grants you a $0.50 trial credit, valid for 7 days, letting you test the API without entering payment details first.

Sign Up with Google

Click the sign-up button and authorize access. Your account is created immediately, and the trial credit is applied automatically. Note that accounts created with email and password do not receive this initial trial credit.

  • Instant account creation
  • $0.50 trial credit included
  • Valid for 7 days

Get Your API Key

Once logged in, navigate to your dashboard to find your unique API key. This key authenticates your requests to the API endpoint. You can generate a new key at any time, which instantly invalidates the previous one.

  • One active key per account
  • Instant key rotation
  • Bearer token format

Try the Demo

Use the provided curl example on your dashboard to send your first request. Paste any text up to 4096 characters, choose a voice, and receive an audio file. This confirms your integration works before you build your WordPress plugin.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Streamline your publishing workflow by integrating reliable hosting solutions with powerful content management systems for seamless performance.

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. LibriVox public-domain audiobooks
  3. OpenAI API reference: create speech
  4. Creative Commons Attribution 4.0
  5. LibriTTS-R paper (arXiv 2305.18802)
  6. curl documentation
  7. Python documentation
  8. openai-node on GitHub
  9. FFmpeg documentation
  10. W3C WAI: making audio and video accessible
  11. MDN: Web Speech API
  12. Tether (USDT)

More on this site