Frequently asked questions
Who runs IoT TTS Lab?
IoT TTS Lab is an independent storefront providing a cloud text-to-speech API for indie developers. We operate as a standalone service, offering a simple character-based API designed specifically for smart home and IoT products without complex dependencies.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base_url. We are a separate entity providing our own engine and voices.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each generated audio file includes an inaudible watermark to identify it as synthetic speech, ensuring transparency about the source.
Is my data private?
Input text is used solely to produce the audio and is not used for training. Request metadata (time, characters, status) is retained for billing purposes. We do not store the generated audio files after returning them in the response.
How do I contact support?
Support is available via email only. We do not offer a phone number, live chat, or on-site support team. For technical issues or billing inquiries, please send an email to our support address for assistance with your account.
Do you have an SLA?
We do not provide a Service Level Agreement (SLA) or an uptime guarantee. Our service is designed for indie developers who can handle standard cloud variability. There is no enterprise contract or on-premise installation option available for this API.
Are the voices real people?
The voices are based on licensed recordings from LibriTTS-R. They are preset voices (like Aria, Nova, or Felix) based on licensed recordings. We do not offer custom voice cloning or uploading your own voice.
Do you store audio files?
No, we do not store generated audio files. The audio is returned directly in the API response. Only request metadata, such as timestamp, character count, and status, is kept for billing and usage tracking purposes on our servers.
How much does the API cost?
Pricing is $10 per 1 million characters ($0.01 per 1,000 characters). Failed requests are free. You can start with a $0.50 free trial via Google sign-in. Top-ups are accepted via USDT (TRC-20) with no monthly plans or subscriptions.
Who We Are
IoT TTS Lab is an independent storefront for a text-to-speech API. We provide a straightforward service designed specifically for the constraints of edge devices and smart home assistants. Our approach strips away unnecessary complexity, allowing indie developers to integrate voice capabilities with minimal overhead.
Independent Editorial Team
We are a small, focused team that understands the practical constraints of building voice-enabled IoT products. We prioritize simplicity and reliability over marketing fluff, ensuring our API documentation and pricing reflect real-world usage patterns for developers working with limited resources.
Focus on Indie Developers
Our platform is built for indie developers who need a reliable, character-based TTS API without the overhead of complex SDKs or streaming dependencies. You can send text and receive audio files directly, making it easy to integrate into custom hardware or software stacks.
No Affiliation with Big Tech
We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other major brand. Our voices are derived from licensed recordings, and our infrastructure operates independently. This ensures that your integration relies on a dedicated, transparent service rather than a fragmented feature within a larger ecosystem.
Our Voice Library
Our voice library consists of eight distinct presets derived from licensed recordings in the LibriTTS-R dataset. Each voice, from Aria to Orion, is built on licensed recordings.
We provide these eight voice presets for smart home assistants and IoT devices.
Licensed from LibriTTS-R
All eight voices in our library are based on the LibriTTS-R dataset, which provides a robust foundation for natural-sounding text-to-speech synthesis.
CC BY 4.0 License
The underlying audio data is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This allows us to integrate these voices into our API while maintaining clear licensing standards for our users.
Public Domain Source Material
The original recordings come from LibriVox, utilizing public-domain audiobook readings. This ensures that the source material is free from restrictive copyright claims, providing a stable legal basis for our API service.
Data Privacy Policy
Data privacy is built into our API design for developers who handle sensitive voice data in smart home environments. We prioritize clarity about how your input and output are processed, ensuring you retain full control over the synthetic audio generated for your IoT products.
Text Not Used for Training
Your input text is used strictly to produce the audio file and is not used for training our models. This ensures that your specific voice content remains yours, regardless of volume or usage frequency.
No Audio Storage
Generated audio is returned directly in the response and is not stored on our servers. Once you receive the file, we have no copy of it, allowing you to manage retention entirely on your own infrastructure.
Metadata for Billing Only
Request metadata, including time, character count, and status, is kept solely for accurate billing and troubleshooting. This limited data does not include the audio content or the raw text itself.
Technical Limitations
IoT TTS Lab provides a straightforward, character-based API. We prioritize simplicity over feature bloat, meaning you receive raw audio files via standard HTTP requests without the overhead of managing complex protocols.
No Streaming or SSML
The API returns complete audio files (mp3, wav, opus, flac, or pcm) after synthesis finishes. We do not support real-time streaming, WebSocket connections, or partial audio chunks. There is no SSML support, and the system cannot process custom pronunciation lexicons.
No Custom Voice Cloning
We offer eight fixed voice presets derived from licensed recordings. Custom voice cloning is not available; you cannot upload your own audio samples to create a unique voice. Each generated file contains an inaudible watermark to identify it as synthetic speech.
No SLA or Uptime Guarantee
As an independent service for indie developers, we do not offer formal Service Level Agreements (SLAs) or guaranteed uptime percentages. While we strive for reliability, requests are processed sequentially, so high load may cause queuing delays during peak usage.

Contact and Support
Support for IoT TTS Lab is handled entirely via email. We do not maintain a phone line or live chat widget, keeping operations lean and focused on asynchronous developer needs.
This approach ensures every query is documented and searchable, allowing us to provide detailed, code-aware answers without the pressure of real-time conversation.
Email Support Only
Send your questions, bug reports, or billing inquiries to [email protected]. Please include your API key and relevant request logs to help us diagnose issues quickly.
No Phone or Live Chat
We do not offer voice support or instant messaging. This allows our team to dedicate more time to deep-dive troubleshooting rather than managing queue wait times.
Response Time Expectations
Complex technical issues may take longer as we reproduce the specific voice synthesis scenario.
Our Mission
IoT TTS Lab exists to remove friction from voice-enabled hardware. We provide a straightforward API that lets indie developers generate speech without managing complex infrastructure or streaming dependencies. Our goal is to let you focus on building smart home assistants and IoT products, not debugging audio pipelines.
By simplifying the technical stack, we help you deliver clear, natural-sounding audio in devices where simplicity matters most.
Simplify TTS for IoT
We designed our API specifically for constrained environments. Send text, receive an audio file. No streaming protocols or WebSocket connections to maintain. This simplicity reduces integration time and hardware overhead, making it easier to embed voice capabilities into low-power devices.
- Single endpoint for all voice generation
- No complex streaming dependencies
- Optimized for simple HTTP requests
Transparent Pricing
Costs are based purely on character count: $10 per 1 million characters. You pay only for what you use, with no hidden fees or minimum commitments. Failed requests are free, ensuring you never pay for errors.
- $0.01 per 1,000 characters
- No monthly plans or subscriptions
- Free failed requests
Developer-First Approach
Our documentation and tools are built for developers who value clarity. We use standard JSON bodies compatible with OpenAI SDKs, so you can integrate quickly using libraries you already know. Support is direct via email, without waiting on hold.
- Standard JSON request format
- Works with OpenAI SDKs
- Direct email support
Pricing and Payment
Generate voice audio for your IoT devices at a flat rate of $10 per 1 million characters. This includes spaces and punctuation, making cost prediction straightforward for smart home assistants and voice-enabled gadgets.
Pay Per Character
Every request consumes characters based on the input text length. Failed synthesis requests are free, ensuring you only pay for successful audio generation. The standard rate is $0.01 per 1,000 characters, with a free trial credit of $0.50 available for new Google-sign-in accounts.
- Rate: $10 per 1 million characters
- Failed requests are free
- Free trial: $0.50 (7 days) for Google sign-ins
USDT (TRC-20) Only
We accept payments exclusively via USDT on the TRON network (TRC-20). There are no credit cards, PayPal, or bank transfers. Top-ups are processed automatically within minutes of transfer confirmation, with a minimum spend of $5.
- Currency: USDT (TRC-20) only
- Minimum top-up: $5
- Processing time: automatic, within minutes
No Monthly Plans
Our pricing model is purely usage-based. You pay only for what you generate, with no recurring subscriptions, seats, or minimum monthly commitments. Your balance never expires, allowing you to top up once and use it over time.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Beginners can start generating speech in minutes using the provided curl examples or standard HTTP clients.
23 languages
Any voice speaks any of these languages.
