Frequently asked questions
Is this site affiliated with OpenAI?
No, we are not affiliated with OpenAI. While our API endpoint and request format match the OpenAI speech endpoint for easy integration, we are an independent storefront for our own text-to-speech service. We do not use OpenAI’s infrastructure or models.
Who owns the voices used in the API?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the raw audio data used to create our voice presets, ensuring legal clarity for your generated content.
Do you sell customer data?
We do not sell customer data. Input text is used only to produce the audio and is not used for training. We keep request metadata (time, characters, status) strictly for billing purposes and do not share your information.
Is my text used to train AI models?
No, your input text is used only to produce the audio and is not used for training. We do not retain your text content for model improvement, ensuring your specific phrases remain private to your immediate use case.
Can I request a new voice?
We do not offer custom voice cloning or voice design. You can choose from eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). If you need a specific voice, you must use one of these existing options.
Do you have a physical office?
We are a cloud-based service and do not have a physical office for customer visits. Our team operates remotely to manage the API infrastructure and support, ensuring we can serve no-code e-commerce stores efficiently without geographic constraints.
How do I contact support?
Support is available by email only. We do not offer a phone number or live chat. Please reach out via the contact page for any questions regarding your API key, billing, or technical issues with the speech endpoint.
Are the voices royalty-free?
The voices are based on CC BY 4.0 and public-domain sources. While we do not charge additional royalties, you should verify specific license requirements for your commercial use case. The generated audio is synthetic speech with an inaudible watermark.
Do you store audio files?
Generated audio is returned in the response and not stored by us. We only retain request metadata, such as time, character count, and status, for billing purposes. Your actual audio files are not kept on our servers after delivery.
Is the API open source?
No, our API is not open source. We provide a standard REST API compatible with the OpenAI SDK format. You can use the OpenAI SDK by changing the base URL to our API endpoint.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer general refunds for successful requests. Your balance does not expire, so you can use your credit whenever you are ready.
Can I use the API for government projects?
Yes, you can use the API for government projects. We do not restrict usage by industry. However, we do not offer specific enterprise contracts or SLAs, so you should evaluate our standard reliability and data handling for your needs.
Are there any certifications like SOC 2?
No, we do not have certifications like SOC 2, HIPAA, or GDPR certificates. We are an independent service without formal enterprise audits. We handle data securely but do not maintain third-party compliance documentation for our cloud infrastructure.
Who we are
We are an independent storefront for a text-to-speech API serving online stores. Our focus is simple: helping no-code merchants turn text into natural speech for product pages, ads, and updates. We keep the process straightforward and practical.
Our work centers on the unique needs of e-commerce. We provide a reliable text-to-speech API that integrates easily into existing store backends. Our goal is to give you clear, usable audio without unnecessary complexity.
Independent editorial team
We are a small, focused group dedicated to creating practical tools for online businesses. We prioritize clarity and reliability over hype, ensuring our API works exactly as described without hidden features or complex setups.
Focused on e-commerce tools
Our product is built specifically for online stores. We designed our API to handle product descriptions, promotional ads, and customer updates efficiently. This specialization means you get a tool that fits seamlessly into your no-code workflow.
No affiliation with big tech brands
We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We operate independently, offering our own key and pricing structure. This means you are buying directly from us, with no reliance on other tech giants for your voice generation needs.
Voice licensing
We do not clone human voices. Our eight presets are built from licensed recordings, providing clear legal grounding for your generated audio.
This foundation ensures that your product pages and ads use speech derived from transparent, accessible sources without complex royalty chains.
LibriTTS-R dataset (CC BY 4.0)
Our voice presets are based on the LibriTTS-R dataset, licensed under CC BY 4.0. This standard license allows for broad commercial and personal use with proper attribution.
The dataset provides high-quality audio samples that serve as the raw material for our synthesis engine, ensuring legal clarity for your generated content.
- CC BY 4.0 licensed data
- High-quality audio samples
- Clear commercial usage rights
LibriVox public domain readings
The underlying recordings come from LibriVox, featuring public domain audiobook readings. These recordings are in the public domain, allowing us to build reliable voice models without restriction.
This combination of public domain source material and permissive dataset licensing creates a stable foundation for our TTS service.
Licensed recordings used as base
We use these licensed recordings as the base for our eight voice presets. This approach ensures that every generated file carries an inaudible watermark marking it as synthetic.
You get natural-sounding speech without the need to track individual voice actor rights for each generated audio file.
Data policy
ShopVoice API is built for online stores that care about customer privacy. When you send product descriptions or ad copy to our API, that text is used strictly to generate the audio file. We do not use your input text to train or improve our models, ensuring your unique marketing content remains yours.
Once the synthesis is complete, the generated audio is returned directly to your request and is not stored on our servers. This means we don't hold onto your voice assets, keeping your data minimal and secure for your e-commerce workflow.
Input text not used for training
Your product descriptions, marketing copy, and other input texts are processed solely for the purpose of generating the requested audio file. We do not use this input text to train or improve our speech models. Your unique content remains yours, untouched by our training datasets.
Audio not stored after generation
After synthesis, the generated audio is returned in the response and is not stored on our servers. This ensures that your voice assets remain transient and private, reducing the risk of data retention issues for your online store.
Metadata kept for billing only
We keep request metadata, including timestamp, character count, and status, strictly for billing and usage tracking. This allows you to monitor your character usage against your balance without us retaining the actual content of your store's text.
Honest limits
ShopVoice API is an independent service built for no-code e-commerce stores. We focus on delivering reliable text-to-speech conversion without the overhead of enterprise-grade contracts or complex infrastructure guarantees.
No SLA or uptime guarantee
We do not offer a Service Level Agreement or guaranteed uptime percentage. While we strive for consistent performance, requests are processed sequentially and may queue during high load, meaning generation times can vary slightly.
No phone or live chat support
We keep things simple and cost-effective by not maintaining phone lines or live chat widgets. This allows us to focus resources on API performance and voice licensing rather than real-time support infrastructure.
Email support only
All inquiries are handled via email. Response times vary depending on volume, but we aim to address technical questions and billing issues promptly. Please include your API key and request details for faster assistance.

Technology stack
We built ShopVoice API to be a straightforward utility for online stores. Our service is fully compatible with the OpenAI speech endpoint structure, meaning you can use existing OpenAI SDKs by simply changing the base URL. This standardization ensures that your integration is robust and widely supported.
We do not maintain a custom SDK or proprietary plugins. If you need a WordPress plugin or a mobile SDK, it does not exist. You will rely on standard HTTP requests or the official OpenAI client libraries, which simplifies maintenance and keeps the technology stack transparent and easy to debug.
Standard OpenAI-compatible API
Our API endpoint mirrors the OpenAI speech structure. This means you can use the official OpenAI SDKs by updating the base_url to https://api.playg9999.com/v1. This compatibility allows you to use the official OpenAI SDKs by changing the base URL.
The request shape is identical: a POST to /v1/audio/speech with JSON body containing model, input, voice, and response_format. This standardization reduces friction for developers who already understand the OpenAI interface.
- Compatible with official OpenAI SDKs
- Same request shape as OpenAI speech endpoint
- Base URL: https://api.playg9999.com/v1
No custom SDK or plugins
We offer a minimal, focused product. There is no dedicated ShopVoice SDK, no mobile SDK, and no WordPress plugin. This keeps our development lean and ensures that you are not locked into a specific vendor's proprietary tooling.
By sticking to standard HTTP, we avoid the overhead of maintaining multiple platform-specific clients. This approach is ideal for no-code users who can use simple code snippets or existing API connectors in their store’s backend.
Simple HTTP integration
Integration relies on standard HTTP POST requests. You send text, and we return an audio file. This simplicity makes it easy to integrate with any platform that can send web requests, including no-code automation tools like Zapier or Make.
Authentication is handled via a Bearer token in the Authorization header. This standard method is secure and easy to implement across various programming languages and store platforms.
Contact information
We keep things simple. Our only support channel is email, so you can reach us directly without navigating phone trees or waiting in live chat queues. This approach keeps our overhead low and lets us focus entirely on maintaining the API for your store.
We don’t list a physical office address because we operate independently and remotely. This isn’t a temporary setup; it’s just how we work. You don’t need to mail anything or visit us to get help with your text-to-speech integration.
Email support only
Send your questions, bug reports, or billing inquiries to our support email. We don’t have phone numbers or live chat widgets cluttering the page. Email allows us to provide detailed, written responses that you can reference later.
This is our sole channel for all support needs. Whether you’re integrating the API into your no-code store or have a question about voice licensing, email is the best way to connect with us.
- No phone number provided
- No live chat widget
- Written responses for clear documentation
No physical address listed
We operate as an independent digital service, so there is no public-facing office to visit. This independence allows us to remain agile and focused on the API’s reliability without the overhead of a physical location.
Our lack of a listed address doesn’t affect your service. All communications happen digitally, and your data policy remains clear regardless of our physical location.
- Remote-first operation
- No public office visits
Response time varies
Because we are a small independent team, response times can vary depending on the volume of support requests. We aim to reply promptly, but during high traffic or integration spikes, it may take a bit longer.
We appreciate your patience. For urgent API issues, you can also check our documentation first, as many common integration questions are already answered there.
- Support volume dependent
- No guaranteed SLA for support
- Check docs for common issues first
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This voice is ideal for blog posts, FAQ sections, or customer updates where a warm, approachable tone builds trust with your shoppers.
23 languages
Any voice speaks any of these languages.
