Frequently asked questions
Who owns ScribeSound?
ScribeSound is an independent storefront operating under the domain play55win.com. We are a standalone provider of a cloud text-to-speech API, distinct from larger technology corporations. Our team manages the infrastructure, voice licensing, and billing directly to serve publishers and developers without corporate overhead.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint mimics the OpenAI speech endpoint structure for convenience, but we use our own engine and infrastructure. We are a completely independent service.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These recordings form the basis of our neural models. We do not use celebrity voices or perform custom cloning for individual customers.
Is the audio copyrighted?
Generated audio files are not stored by us and are returned directly in the response. While the underlying voice models derive from licensed sources, the generated synthetic audio is yours to use. Each file carries an inaudible watermark marking it as synthetic speech.
Do you store my input text?
No. Your input text is used only to produce the audio and is not used for training our models. The generated audio is returned in the response and not stored on our servers. We retain only request metadata for billing purposes.
How long do you keep logs?
We keep request metadata, including time, character count, and status, strictly for billing and usage tracking. This data is retained to ensure accurate charging of your account balance. We do not store the actual text content or the generated audio files.
Can I request a new voice?
We currently offer eight fixed presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. We do not offer custom voice cloning or voice design services. If you need a different voice, you must choose from our existing eight options.
Is the site secure?
We use standard HTTPS encryption for all API requests and site interactions. Authentication is handled via Bearer tokens. We do not offer SLAs or uptime guarantees, but we maintain secure infrastructure to protect your API keys and billing data.
Who writes the content on this site?
The content on play55win.com is written by the ScribeSound team to accurately reflect our product facts. We aim for honest, specific descriptions tailored to WordPress publishers. We do not use AI-generated filler or hired third-party agencies for our core site content.
Do you have a physical office?
We operate as a distributed team and do not list a physical office address. Support is available by email only. We do not have a phone number or live chat. Our infrastructure is cloud-based, allowing us to serve publishers globally.
Can I advertise on your site?
We do not currently offer advertising space on play55win.com. Our focus is on providing a lightweight TTS API for publishers. If you have specific inquiries about partnerships or advertising, please contact us via email for further discussion.
How do I report a bug?
You can report bugs or issues via email. We do not have a public bug tracker or phone support. Please include your API key (masked), request details, and steps to reproduce the issue in your email for faster resolution.
Is the API open source?
No, our API and underlying models are proprietary. We provide a standard HTTP interface compatible with OpenAI SDKs, but the code running our service is not open source. You interact with our endpoints via standard JSON requests.
Do you hire freelance writers?
We do not currently have a public listing for freelance writers. Our content is managed internally to ensure accuracy regarding our product facts. If you are interested in contributing, please reach out via our contact page to discuss potential opportunities.
Who We Are
ScribeSound is an independent storefront for a single text-to-speech API, designed specifically for WordPress bloggers and content publishers. We are not a large tech conglomerate but a focused editorial team that understands the daily need for accessible audio in digital publishing.
Editorial Team
Our team consists of developers and editors who publish content daily. We built this API to solve our own workflow problems: providing reliable audio for articles without the complexity of enterprise-grade platforms.
Publisher Focus
We prioritize simplicity and cost-effectivity. Our API integrates directly into WordPress workflows, allowing you to convert long-form articles into audio files seamlessly. We focus on keeping the integration lightweight and the pricing transparent.
- Optimized for blog content and articles
- Simple JSON API compatible with standard tools
- No monthly subscriptions or seat limits
Independent Storefront
We operate as an independent storefront, distinct from the underlying voice providers. This means we control the billing, the key management, and the support directly. You deal with one team for one API.
Voice Licensing
ScribeSound’s voices are derived from licensed recordings sourced from LibriTTS-R, a dataset built from LibriVox public-domain audiobook readings. This foundation ensures our audio retains the natural cadence and clarity of human narration without the legal complexity of celebrity voice licensing.
LibriTTS-R Source
We utilize the LibriTTS-R dataset, which contains high-quality speech data from thousands of volunteers reading public-domain books. This source provides a diverse range of vocal styles, ensuring our eight presets—from the warm narrator 'Aria' to the deep documentary voice 'Orion'—are grounded in authentic human performance.
CC BY 4.0 License
The underlying recordings are available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means the base audio data is freely available for commercial use, provided appropriate credit is given to the original speakers and the LibriVox project. The attribution requirement applies to the source dataset, not the generated audio files.
Public Domain Audio
Because the source texts are in the public domain, the spoken content itself is free of copyright restrictions. This allows publishers to generate audio for articles and blogs without fearing copyright strikes on the underlying material, though the synthetic audio itself carries a watermark. The only mark on your generated files is an inaudible watermark identifying the speech as synthetic, keeping your content clean and professional.

Data Privacy
ScribeSound respects your content. We use your input text solely to generate the requested audio file and do not use it to train our models or improve future voice synthesis.
No Training Data
Unlike many commercial services, we do not repurpose your articles for model improvement. Your input is processed for immediate synthesis and remains independent of our training datasets.
Text Usage Policy
Your text is used only for the specific audio generation request. We do not scan or archive your content for other purposes, ensuring your editorial voice remains yours.
Audio Storage
Generated audio is returned in the response and not stored on our servers after delivery. We retain only request metadata—time, character count, and status—for accurate billing and transparency.
Technical Approach
ScribeSound uses a lightweight, standard HTTP interface that mirrors the OpenAI speech endpoint. By pointing your SDK’s base_url to https://api.play55win.com/v1, you can use existing OpenAI libraries without rewriting integration code.
OpenAI Compatible
Send a POST request to /v1/audio/speech with standard JSON fields. The endpoint accepts model, input, voice, response_format, and speed, ensuring seamless migration for developers already familiar with common TTS patterns.
Simple API Design
The API returns audio files directly in the response, eliminating the need for polling or complex callback setups. You can retrieve voice lists and model details via simple GET requests to /v1/voices and /v1/models.
No Proprietary SDK
We do not maintain our own SDK or require specific client libraries. Any HTTP client or the official OpenAI SDK works out of the box, keeping your stack lightweight and dependency-free.

Support Policy
ScribeSound operates as an independent storefront, meaning our support is lean and direct. We prioritize building a robust API over maintaining a large support team, ensuring that every dollar goes into voice quality and infrastructure rather than overhead.
Email Only
We handle all inquiries via email. This allows us to provide thoughtful, written responses that you can reference later, rather than rushing through live conversations.
No Phone Support
We do not offer phone support. Without the overhead of call centers, we keep our operational costs low. This model helps us maintain our simple pricing structure without hidden fees or minimum spend requirements for priority access.
Response Times
During business hours, we aim to respond within 24 hours. Since we are a small team, volume can vary. For urgent API issues, please include your API key and error logs in the first email to speed up troubleshooting.

Contact Us
ScribeSound is an independent storefront built for WordPress publishers who value clarity and direct communication. We keep our support simple: one email address, no waiting on hold, and no complex ticketing systems. Our goal is to help you integrate audio into your articles without administrative friction.
Email Address
For all inquiries, billing questions, or technical issues, please email us at [email protected]. This is our only support channel. We do not maintain a phone line or live chat widget, so email remains the most reliable way to reach our team.
Address Details
This address is used for billing correspondence and legal notices. We do not offer walk-in support or physical offices open to the public.
Feedback Channel
We build this API for publishers, so your input matters. If you notice a voice glitch, have a suggestion for a new feature, or want to report a bug, send a note to the same support email. We review every message to improve the experience for WordPress users.
- Feature requests are prioritized based on publisher needs.
- Bug reports are tracked and resolved sequentially.
- No guaranteed response time SLA.
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.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- ISO 639 language codes
- FFmpeg documentation
- W3C WAI: making audio and video accessible
- TRON developer hub: TRC-20
- LibriTTS-R corpus (OpenSLR 141)
- openai-python on GitHub
- Creative Commons Attribution 4.0
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- Node.js documentation
