Frequently asked questions
Who runs IoT Voice Lab?
IoT Voice Lab is an independent storefront for a single cloud text-to-speech API. We help IoT developers and smart home creators find reliable voices for their hardware. Our guide simplifies switching from legacy services like Amazon Polly to a modern, cost-effective API that fits your budget.
Where do the voices come from?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We use eight presets like Aria, Nova, and Felix. Every generated file carries an inaudible watermark marking it as synthetic speech, ensuring transparency for your smart home projects.
Do you use input text for training?
No. Input text is used only to produce the audio and is not used for training. This ensures your data privacy remains intact while generating speech for your IoT devices or smart home applications without contributing your specific text to our model training data.
Do you store generated audio?
Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, solely for billing purposes. Your actual audio files are not retained on our servers after delivery to your application or device.
How can I contact you?
Support is by email only. We do not offer a phone number, live chat, or instant messaging. Please reach out via the contact page if you have questions about your API key, billing, or technical integration with your smart home ecosystem.
Do you have an SLA?
No. We do not offer an SLA, uptime guarantee, or enterprise contract. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, but performance depends on current server load and queue status.
Are you affiliated with Amazon?
No. We are not affiliated with Amazon, Google, Microsoft, or any other brand mentioned in comparisons. We are an independent storefront. Our API endpoint and SDK usage are similar to OpenAI, but we are a separate entity with our own pricing and keys.
Do you offer voice cloning?
No. We do not offer custom voice cloning, uploading your own voice, or voice design. We provide eight preset voices like Felix and Luna. These are based on licensed recordings, not cloned from specific individuals, ensuring consistent quality for your IoT text-to-speech needs.
Is there a mobile SDK?
No. We do not offer an official SDK of our own, nor a mobile SDK. You can use the official OpenAI SDKs by changing the base_url to our API endpoint, or use plain HTTP. This flexibility allows easy integration into various IoT hardware and apps.
Do you have a WordPress plugin?
No. We do not offer a WordPress plugin, browser extension, or speech-to-text service. Our product is a cloud text-to-speech API. You can integrate it into your smart home workflows using standard HTTP requests or compatible SDKs without needing specific platform plugins.
What is your data retention policy?
Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored. Request metadata (time, characters, status) is kept for billing purposes only. This ensures minimal data retention for your IoT projects.
How do I verify the license?
Voices are based on licensed recordings: LibriTTS-R (CC BY 4.0) from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech.
Can I use the voices commercially?
Yes. The voices are based on CC BY 4.0 licensed recordings and public-domain readings. You can use the generated audio commercially. The inaudible watermark marks the file as synthetic. There are no monthly plans, seats, or minimum spend requirements for commercial use.
Do you offer refunds?
Failed requests are free. If synthesis fails, the charge is returned in full. We do not offer general refunds for successful requests. Top-ups via USDT on the TRON network (TRC-20) are credited automatically. Balance does not expire, and you can issue a new API key at any time.
Our Mission
We bridge the gap between legacy text-to-speech services and modern IoT hardware. Our goal is to provide a reliable, cost-effective API that fits your smart home budget without complex infrastructure.
Simplifying TTS
Sending text to receive audio is straightforward. We handle the complexity so you can focus on your device’s voice. Our API mimics familiar structures, making integration quick for existing projects.
Empowering IoT Makers
Whether you are building a smart speaker or a voice-enabled thermostat, our voices are ready. We support 23 languages, ensuring your devices sound natural globally. You get consistent results across different hardware.
No-Code Friendly
You do not need deep engineering skills to start. Our dashboard provides a ready-to-use API key and clear examples.
Our Voices and Licensing
We believe in transparency regarding the source of our synthetic voices. Our entire voice library is built upon high-quality, open-source audio data, ensuring that every sound you generate is both legally clear and ethically sourced for your smart devices.
This foundation allows us to offer a consistent, reliable TTS experience without the complexity of proprietary black boxes. You get clear, licensed audio that integrates seamlessly into your IoT workflows.
LibriTTS-R License
All our voices are derived from the LibriTTS-R dataset, which is licensed under CC BY 4.0. This means the underlying recordings are publicly available and legally cleared for commercial use, giving you confidence in your device's audio output.
The CC BY 4.0 license ensures that the source material is robust and widely recognized in the speech synthesis community, providing a solid base for our API's performance.
- CC BY 4.0 licensed source data
- Clear commercial usage rights
8 Preset Voices
We offer eight distinct voice presets designed to cover a wide range of smart home and IoT use cases. From the warm, clear narration of Aria to the deep, documentary tone of Orion, each voice is tuned for clarity and naturalness.
These presets are available for all 23 supported languages, allowing you to create consistent audio experiences across your global device fleet without needing multiple voice providers.
- Aria, Nova, Luna, Sage (Female)
- Felix, Milo, Atlas, Orion (Male)
- Available in 23 languages
Licensed Recordings
Our voices are based on licensed recordings from LibriTTS-R, which includes readings from LibriVox public-domain audiobooks. This ensures that the acoustic properties of our voices are grounded in real, high-quality human speech.
Every generated audio file carries an inaudible watermark, marking it as synthetic speech. This helps maintain transparency and distinguishes our AI-generated content from human recordings in your devices.
- Based on LibriVox public-domain readings
- Inaudible synthetic watermark in all files
- High-quality acoustic base

Data Privacy Policy
At IoT Voice Lab, we respect the privacy of your smart home data. Our text-to-speech engine is designed for simplicity and transparency, ensuring that your voice commands and notifications remain secure without unnecessary data exposure.
We operate on a clear principle: your input is processed solely for the immediate generation of audio. This straightforward approach means you retain full control over how your device data is handled.
No Training Data
Input text is used exclusively to produce the audio file for your request. We do not use your generated content or text inputs for training our models, ensuring your data remains yours.
No Audio Storage
Generated audio is returned in the response and is not stored on our servers. Once the audio file is delivered to your device, it is not retained for future use or analysis.
Metadata Retention
Request metadata, including time, character count, and status, is kept strictly for billing purposes. This minimal data ensures accurate tracking of your usage and credits without exposing your actual voice content.
Technical Limitations
We prioritize simplicity and reliability for IoT workflows, which means we omit features that add complexity without proportional benefit. Understanding these constraints helps you design robust integrations that handle API responses predictably, whether you are triggering a smart speaker or logging data from a sensor array.
Our API follows a straightforward request-response pattern. You send text, and we return the final audio file. This simplicity reduces edge cases in your code but requires you to manage waiting times for longer texts appropriately within your device's logic.
No Streaming
We do not offer WebSocket or real-time partial audio streaming. The API returns the complete audio file only after synthesis finishes. For short phrases, this takes a few seconds; longer texts may take longer due to sequential processing.
- No partial audio chunks
- Complete file return only
No SSML
Our interface does not support SSML markup. You cannot inject pause tags, break elements, or emphasis controls directly into the audio generation. If you need precise timing adjustments, you must split your text into separate requests and manage the playback sequence in your application logic.
No Custom Cloning
We do not offer custom voice cloning for customers, no uploading your own voice. Our eight presets are based on licensed recordings from LibriTTS-R and LibriVox. While this ensures consistent, high-quality synthetic speech, you cannot train a unique voice model on your own data or create a clone of a specific person.
This limitation keeps our infrastructure lean and our costs low. You get reliable, deterministic results from our eight established voices rather than experimenting with variable cloning quality.

Support and Contact
We handle all customer inquiries exclusively via email, ensuring every question from IoT developers and smart home creators receives a thoughtful, detailed response. There is no phone number and no live chat widget to interrupt your workflow or your device’s testing phase.
Our small, focused team prioritizes accuracy over speed, making sure you get clear answers about voice selection, API limits, or billing issues without waiting in a queue for a generic agent.
Email Support
Send your questions to our dedicated support address. We are here to help you integrate our TTS API into your smart home projects, whether you are using no-code tools or writing custom scripts.
We do not offer phone support or live chat, keeping our communication channel simple and asynchronous to match the nature of hardware development.
No Live Chat
Unlike many modern SaaS platforms, we do not offer real-time live chat. This decision keeps our overhead low, allowing us to pass those savings on to you in our competitive pricing.
You will not encounter a bot asking for your email before you can speak to a human; just email us directly with your issue.
Response Time
For urgent issues related to API key generation or billing discrepancies, please mention "Urgent" in the subject line to help us prioritize your ticket.

Our Team
IoT Voice Lab is built by a small, dedicated group of smart home enthusiasts and developers who understand the unique constraints of edge devices. We bridge the gap between complex cloud APIs and the simple needs of no-code makers, ensuring that every voice preset and language option works reliably with your existing hardware workflows.
Our team combines practical engineering experience with a passion for accessible technology. We focus on delivering clear, specific guidance that helps you switch from legacy services like Amazon Polly to a modern, cost-effective API without unnecessary complexity or hidden fees.
Editorial Team
Our editors craft honest guides that cut through the marketing noise. We test every voice and language to ensure compatibility with smart speakers, dashboards, and notifications, providing clear examples that fit your budget and technical level.
Technical Experts
We understand the nuances of TTS APIs, from the 4096-character limit to voice presets. Our experts ensure our documentation is accurate, helping you integrate the API seamlessly into your IoT projects without needing deep infrastructure knowledge.
Community Focus
We are passionate about empowering IoT makers. Our community is a place to share ideas, tips, and tricks for using TTS in your projects. We listen to your feedback and strive to make our API as user-friendly and cost-effective as possible.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your devices connect seamlessly to create a simple, intelligent living space without any coding knowledge.
23 languages
Any voice speaks any of these languages.
