Frequently asked questions
What is an AI voice maker API?
It is a cloud text-to-speech service where you send text via a POST request and receive an audio file. ScribbleVoice provides a simple endpoint that converts your written content into audio files, allowing indie developers and bloggers to integrate text-to-speech directly into their applications without managing complex infrastructure.
How does text-to-speech work for WordPress?
You send your blog post text to our API endpoint and receive an audio file. You can then embed this file directly into your WordPress posts or pages. The API handles the synthesis, returning formats like MP3 or WAV that are compatible with standard WordPress media players and embed codes.
Can I use this API with the OpenAI SDK?
Yes. Our API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base_url to https://api.play67bd.com/v1 and using your ScribbleVoice key. This allows you to leverage familiar SDK methods for generating audio from your WordPress or other applications.
What formats can I download the audio in?
You can choose from five response formats: mp3, wav, opus, flac, and pcm. Select the format that best fits your WordPress theme or application needs. MP3 and WAV are widely supported for web embedding, while FLAC and Opus offer lossless or efficient compression.
How many languages are supported?
We support 23 languages, including English, Spanish, French, German, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. If you do not specify a language, the system guesses it from the script, but setting it explicitly ensures accuracy for non-English Latin-script text.
Is there a free trial available?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can test the API immediately to see how the voices sound with your specific content.
How do I pay for the API?
We accept USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and credits are added automatically within minutes. There are no monthly plans, no subscriptions, and no credit cards. Your balance does not expire, and you only pay for the characters you use.
Do I need to manage servers for this TTS?
No, ScribbleVoice is a cloud API. You send text via HTTP requests, and we handle the synthesis infrastructure. You do not need to manage servers, install software, or handle scaling. Just integrate the API into your WordPress plugin or custom code using your API key.
Can I embed the audio directly in my blog?
Yes. The API returns audio files (MP3, WAV, etc.) that you can download and embed directly into your WordPress posts. You can use standard HTML5 audio tags or WordPress block editors to play the generated speech. This allows readers to listen to your content without reading it.
What happens if the synthesis fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generations. You can retry the request or adjust parameters like speed or voice if the initial attempt encounters an error.
Are the voices based on real people?
Yes, our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. While they sound realistic, every generated file carries an inaudible watermark marking it as synthetic speech. They are presets, not custom clones of specific celebrities or individuals.
Does the API support custom voice cloning?
No, we do not offer custom voice cloning. You choose from eight preset voices (like Aria, Nova, or Felix). Each voice is a distinct preset based on licensed recordings. You cannot upload your own voice or create a custom clone of a specific person for your blog.
How long does it take to generate audio?
Typical speed is roughly real time, about 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures consistent quality without requiring real-time streaming infrastructure.
Can I use the generated audio commercially?
Yes, you can use the generated audio for commercial purposes, such as in WordPress blogs or apps. The voices are based on CC BY 4.0 licensed recordings. We do not provide an SLA. You are responsible for your usage rights and compliance.
First request
curl
curl https://api.play67bd.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.mp3Why Indie Developers Choose Our TTS API
ScribbleVoice provides a straightforward REST API designed for indie developers who want to add audio to their sites without managing complex infrastructure. You simply send text and receive an audio file, keeping your workflow clean and predictable.
Our API is compatible with the OpenAI SDK, meaning you can use familiar tools by changing the base URL. This allows for quick integration into your existing projects without learning a new system from scratch.
Simple REST API with OpenAI SDK compatibility
Send a POST request to our endpoint and receive an audio file directly. The request shape matches the OpenAI speech endpoint, so existing OpenAI SDKs work by updating the base_url to https://api.play67bd.com/v1. This reduces integration time significantly for developers already familiar with standard HTTP libraries.
- POST https://api.play67bd.com/v1/audio/speech
- Standard JSON body with model, input, voice, and format
- Works with official OpenAI SDKs via base_url change
No infrastructure to manage or scale
You do not need to provision servers or manage voice synthesis queues. Our cloud handles the processing, returning the audio file in the response. This lets you focus on your content rather than backend scaling.
Pay only for what you generate
Costs are based strictly on characters processed. Failed requests are free, and there are no monthly plans or minimum spend requirements. You only pay for successful audio generation, making it easy to budget for small projects.
8 Natural Voices for Every Content Type
ScribbleVoice offers eight distinct voice presets designed to match the tone of your content, whether you are narrating a long-form blog post or creating a quick social clip. Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0), ensuring a consistent listening experience without the need for complex voice design.
Warm narrators for audiobooks and blogs
For long-form content, choose Aria, Luna, or Sage. Aria provides a warm, clear narrator style ideal for storytelling. Luna offers a soft, engaging tone perfect for personal blogs, while Sage delivers a calm, instructional voice suitable for guides and tutorials.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling
- Sage: Calm, instructional
Upbeat voices for promos and social clips
When you need energy, Nova brings a bright, upbeat quality to short videos and promotional snippets. Felix adds an energetic, promo-ready tone that captures attention quickly, making these voices perfect for social media clips and product highlights.
- Nova: Bright, upbeat
- Felix: Energetic, promo
Neutral tones for news and instructions
For straightforward content, Atlas provides a neutral, news-style delivery that feels professional and unbiased. Orion offers a deep, documentary voice for serious topics, while Milo delivers a friendly, conversational tone that works well for customer updates or casual announcements.
- Atlas: Neutral, news
- Orion: Deep, documentary
- Milo: Friendly, conversational

Support for 23 Languages
ScribbleVoice supports 23 languages, covering major markets for indie developers and bloggers. You can generate audio in English, Spanish, French, German, Italian, Japanese, Korean, and others without needing separate voice models.
Our API handles language detection automatically for Latin-script text, defaulting to English if unspecified. You can also explicitly set the language parameter to ensure accurate pronunciation for non-English content, such as Dutch or Swahili.
English, Spanish, French, German, and more
We support 23 languages including Arabic, Chinese, Danish, Finnish, Greek, Hebrew, Hindi, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Any voice preset can speak any of these languages, giving you consistent audio quality across your global content.
This broad coverage allows you to expand your blog’s reach without managing multiple voice engines or negotiating separate contracts for different regions.
- 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 manual override
If you do not set the language field, our API guesses the language from the script. Latin text defaults to English, so remember to specify the language ISO code for non-English Latin-script posts to ensure correct pronunciation.
For precise control, pass the desired language code in the request. This ensures consistent voice tone regardless of the input text's origin, which is crucial for maintaining brand voice across multilingual blogs.
- Automatic detection for Latin text (defaults to English)
- Manual
languageparameter for precise control - Any voice can speak any supported language
Not supported: Vietnamese, Thai, Ukrainian
We currently do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and all others not in the list. If your content relies heavily on these languages, you may need a different solution.
All other listed languages are fully supported with all 8 voice presets, ensuring you have options for narration, instruction, or storytelling regardless of the language.
Fast Integration for WordPress & Blogs
For indie developers and WordPress bloggers, turning written content into audio is straightforward. You send a simple POST request to our API endpoint, providing your text and desired voice settings. The system processes the input and returns the audio file directly, requiring no complex infrastructure or scaling logic on your end.
Once generated, you can download the audio in formats MP3, WAV, Opus, FLAC, or PCM. These files are ready to be embedded directly into your blog posts or downloaded for local use. This seamless workflow allows you to enhance your site's accessibility and content reach with minimal code.
Generate audio files via POST request
Integration is built around a standard REST API. You simply send a POST request to the speech endpoint with your text payload. The API returns the audio file directly in the response, making it easy to handle programmatically in your scripts or plugins.
Download MP3, WAV, Opus, FLAC, or PCM
Choose the audio format that best fits your blog's performance needs. Whether you prefer the small file size of MP3 and Opus or the lossless quality of FLAC and WAV, the API supports all these options. PCM is also available for raw audio processing.
Embed audio players directly in posts
With the audio file generated, you can easily embed it into your WordPress posts using standard HTML5 audio tags. This allows readers to listen to your content directly on the page, improving accessibility for visually impaired users without requiring them to leave your site.
Transparent Pricing for Indie Projects
Pricing is straightforward: you pay only for the characters you actually generate. The rate is $10 per million characters, which breaks down to just $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you never pay for errors.
$10 per million characters
This flat rate applies to both the standard and HD models. Since characters are counted precisely, you can easily estimate costs before sending your text. Long articles are split into 4,096-character chunks, but the pricing remains consistent regardless of length.
$0.01 per 1,000 characters
For indie developers budgeting per post, this unit cost makes integration affordable. A 5,000-character blog post costs $0.05. You can start with a free $0.50 trial credit (valid for 7 days) to test the API without spending.
No monthly plans or minimums
There are no subscriptions, seats, or minimum spend requirements. You can top up as needed using USDT on the TRON network. Credits are added automatically within minutes, giving you full control over your cash flow without locking into recurring costs.
- Top-ups via USDT (TRC-20) are minimum $5.
- Balance never expires.
- No VAT or hidden transaction fees.

Start Free with $0.50 Credit
Start testing our TTS API immediately without financial commitment. When you sign up using your Google account, we automatically issue a $0.50 trial credit to your new account. This allows indie developers and WordPress bloggers to validate voice quality and integration speed before committing to a permanent setup.
Google sign-up gives instant trial credit
The trial balance is available the moment your account is created. You can immediately generate audio files to test voice presets, languages, and formats like MP3 or WAV.
- Instant access upon Google authentication
- Test all 8 voice presets
- Verify API compatibility with OpenAI SDK
Valid for 7 days after registration
Your trial credit remains active for seven days from the date of sign-up. This window is sufficient to complete integration, test long-form text splitting, and evaluate character usage against your project's needs.
No credit card required to start
Unlike many services, we do not require a payment method to begin. You only need to top up via USDT (TRC-20) when you are ready to scale beyond the initial trial characters.
Technical Details for Developers
We designed the API to integrate seamlessly into existing workflows using standard HTTP requests. The OpenAI SDK compatibility means you can switch base URLs and start generating audio immediately without rewriting your integration logic.
60 requests per minute rate limit
Each API key supports up to 60 requests per minute, with a lower 10 requests per minute limit for new accounts before the first top-up. Requests are processed sequentially, so under heavy load, a request may queue briefly.
- 60 req/min after first top-up
- 10 req/min for new accounts
- Sequential processing ensures order
4096 character limit per request
Each POST request accepts a maximum of 4096 characters of input text, including spaces and punctuation. For longer content, split the text into chunks, generate audio for each part, and join the resulting files.
- Max 4096 characters per request
- Split long texts manually
- Join audio files for full content
Audio files returned directly in response
The API returns the generated audio file directly in the HTTP response body. You can save the file locally or play it in your WordPress blog player without managing external storage or additional download endpoints.
- Direct response body delivery
- No external storage needed
- Immediate file access
Data Privacy and Usage
We keep your data simple and secure. Your input text is used exclusively to generate the audio file and is never used to train our models. This ensures your content remains yours, without being ingested into the training set for voice improvement.
Input text not used for training
When you send text to our API, it is processed solely for synthesis. We do not retain your raw text for machine learning purposes, keeping your proprietary content private.
Generated audio not stored on servers
The resulting audio file is returned directly in the API response. We do not store the generated audio files on our servers after delivery, ensuring your output remains ephemeral unless you save it yourself.
Metadata kept only for billing
We retain minimal metadata—such as request time, character count, and status—to calculate your usage accurately. This data is kept strictly for billing purposes and is not used for analytics or profiling.

Common Use Cases for Blogs
Turn static blog posts into listenable content with a single API call. Generate audio files from your article text and embed them directly into WordPress posts using standard HTML audio tags.
This workflow requires no complex infrastructure. You simply send the text via POST request, receive the audio file, and publish it. It is ideal for indie developers who want to add value without managing servers.
Audio versions of blog posts
Convert your written content into audio files that readers can stream or download. This keeps users engaged longer and fits modern consumption habits without requiring them to read every word.
Since audio files are returned directly in the API response, you can store them locally or play them on demand. The format options like MP3 and Opus ensure compatibility with most media players.
- Generate audio from any text up to 4096 characters
- Embed MP3 or WAV players directly in WordPress posts
- No need for external hosting or complex plugins
Accessibility for visually impaired readers
Provide an inclusive experience by offering audio alternatives for your blog content. Screen readers work well with text, but synthesized speech offers a different, often preferred way to consume long-form articles.
All generated files include an inaudible watermark marking them as synthetic speech, ensuring transparency for your audience while maintaining high quality.
Multi-language content expansion
Reach global audiences by generating audio in 23 languages, from English and Spanish to Japanese and Arabic. The API supports automatic language detection or manual overrides via ISO codes.
Use different voices to match the tone of each language, ensuring that your content sounds natural whether it is a warm narrator or a neutral news tone. This allows you to expand your reach without hiring voice actors.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Publish your latest coding discoveries and personal reflections using a reliable blogging platform to grow your independent audience effectively.
23 languages
Any voice speaks any of these languages.
