Frequently asked questions
Is this service affiliated with Amazon or Amazon Polly?
No, IoT Voice Lab is not affiliated with Amazon or Amazon Polly. We are an independent storefront providing a cloud text-to-speech API. Our service operates separately, offering a modern alternative for IoT developers who want reliable synthetic speech without dependency on Amazon’s ecosystem or branding.
Can I use Amazon Polly voices in this API?
No, you cannot use Amazon Polly voices. We provide eight specific presets: aria, nova, luna, sage, felix, milo, atlas, and orion. These voices are based on licensed recordings from LibriTTS-R and LibriVox. Each voice has a distinct tone, such as warm, upbeat, or deep, tailored for different use cases.
How does the pricing compare to Amazon Polly?
Our pricing is simple: $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. We do not charge for separate voices or languages. This flat rate applies to all models, making it easy to predict costs for your IoT devices without complex tiered pricing structures.
What audio formats are supported for IoT devices?
We support mp3, wav, opus, flac, and pcm formats. These options ensure compatibility with various IoT hardware and workflows. You can select the format that best fits your device’s decoding capabilities. All generated audio files are returned directly in the API response for immediate use in your applications.
Can I generate speech in multiple languages?
Yes, we support 23 languages including English, Spanish, German, French, Japanese, and Chinese. 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 top up later using USDT on the TRON network. No credit card is required to start.
How do I integrate this with Alexa or Amazon Connect?
You can integrate this API with Alexa or Amazon Connect by using our standard HTTP endpoint. Since our request shape matches the OpenAI speech endpoint, you can use standard HTTP clients or SDKs. Simply point your integration to https://api.playa111.com/v1 and use your API key for authentication.
What are the rate limits for the API?
The limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures fair usage and stable performance for your IoT devices generating speech.
Can I stream audio in real-time?
No, we do not support streaming or WebSocket connections. You send a text request and receive the complete audio file in the response. For longer texts, you must split them into parts of up to 4096 characters and join the resulting audio files manually in your workflow.
Do you support SSML for voice control?
No, we do not support SSML. Our API accepts plain text input up to 4096 characters. You can control speed using the speed parameter (0.25–4.0) and select a voice preset. There are no phoneme dictionaries or custom pronunciation lexicons available for fine-tuning specific words within the text.
How long is my input text stored?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, for billing purposes. Your raw text content is not retained after synthesis.
Can I clone my own voice for my devices?
No, we do not offer custom voice cloning. You must choose from our eight preset voices: aria, nova, luna, sage, felix, milo, atlas, or orion. These voices are based on licensed recordings. We do not allow uploading your own voice or designing custom voices for your specific IoT needs.
Is there an SLA or uptime guarantee?
No, there is no SLA or uptime guarantee. We do not offer enterprise contracts or on-premise installations. Our service is provided as-is without certified guarantees like SOC 2 or HIPAA. You should build your IoT systems to handle potential variability in response times or availability.
How do I contact support if I have an issue?
Support is available by email only. We do not offer a phone number or live chat. You can find contact details on our /contact/ page. Please include your API key and details of the issue in your email for the fastest possible response from our team.
First request
curl
curl https://api.playa111.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 IoT Makers Are Leaving Amazon Polly
Amazon Polly’s billing structure can be confusing for IoT developers who just want predictable costs for their smart devices. You often pay for requests, characters, and neural processing separately, making it hard to estimate monthly expenses for thousands of devices.
Voice variety is another hurdle. Many legacy services limit you to a small set of generic voices that sound robotic or repetitive, which doesn’t fit the diverse needs of modern smart home ecosystems where distinct personalities enhance user experience.
Complex Billing Models
With Amazon Polly, costs accumulate quickly due to separate charges for standard, neural, and long-form voices. For an IoT project generating hundreds of prompts daily, these fragmented bills make budgeting difficult and unpredictable.
You might find yourself overpaying for features you don’t need or underestimating the cost of high-volume text-to-speech generation for your connected devices.
- Separate pricing for standard vs. neural voices
- No flat rate per character
- Hard to predict monthly costs for scale
Voice Variety Limits
Legacy providers often restrict you to a handful of voices, forcing your entire IoT ecosystem to sound monotonous. This lack of variety makes smart speakers and home assistants feel less engaging and more mechanical.
Our API offers eight distinct, realistic voices, allowing you to assign specific personalities to different devices or users, enhancing the overall user experience without complexity.
- Limited voice selection in legacy services
- Generic robotic tones
- No distinct character options
Integration Friction
Integrating Amazon Polly often requires managing multiple endpoints and complex authentication flows. For no-code users or small IoT teams, this adds unnecessary technical debt.
Our API simplifies this with a single, straightforward endpoint that works with standard HTTP requests, reducing the time spent on integration and debugging.
You can switch from your current provider with minimal code changes, focusing on your product rather than the TTS infrastructure.
- Multiple endpoints to manage
- Complex authentication flows
- High technical debt for small teams
Meet Our 8 Realistic Voices
Our eight voices are built from licensed recordings, giving you clear, natural speech for your IoT projects without licensing headaches. Each voice brings a distinct character to your device, from warm narrators to energetic announcers.
Female Narrators: Aria, Nova
Aria offers a warm, clear narration style perfect for guided prompts. Nova brings a bright, upbeat energy ideal for engaging user interactions.
Male Voices: Felix, Milo
Felix delivers energetic, promo-style audio that grabs attention. Milo provides a friendly, conversational tone that feels like a helpful assistant.
Neutral & Deep: Atlas, Orion, Luna, Sage
Atlas offers a neutral tone suitable for news, while Orion provides a deep, documentary style. Luna provides soft storytelling, while Sage delivers calm, instructional audio.

Support for 23 Languages
Speak to the world with 23 supported languages, including English, Spanish, German, French, Chinese, Japanese, Arabic, and Hindi. Our API handles diverse scripts so your IoT devices sound natural wherever they are deployed.
Global Reach
Whether your device is in Tokyo, Berlin, or São Paulo, we cover the major markets. From Swahili to Turkish, you have a voice that fits the local context without needing separate integrations.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-Language Detection
Set your device to guess the language automatically. If you don't specify a code, the system detects the script. Latin script defaults to English, so you get instant results without extra config.
Non-English Latin Scripts
For languages like German or Dutch using Latin letters, you must set the language parameter. Auto-detection might assume English otherwise. Explicitly setting the language ensures accurate pronunciation for non-English Latin text.
Simple, Predictable Pricing
Pricing is straightforward: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, with charges returned in full if synthesis fails.
No monthly fees, no subscriptions, and no minimum spend. You only pay for what you use, making it ideal for variable IoT workloads.
Pay Per Character
Every character in your input text contributes to the cost. With a $0.50 free trial (valid for 7 days), you can generate about 50,000 characters immediately upon signing in with Google. Accounts created with email and password start without trial credit.
- $0.01 per 1,000 characters
- Failed requests are free
No Monthly Fees
There are no recurring costs or hidden fees. Balance does not expire, and there are no seats or enterprise contracts to manage.
Instant Top-Ups
Top up your balance with USDT on the TRON network (TRC-20). Minimum $5, credited automatically within minutes. No cards, PayPal, or VAT invoices.
Easy Integration for No-Code Users
Connect your smart devices without writing complex code. Our API mirrors the standard OpenAI structure, allowing you to use familiar libraries and tools. Simply update the base URL to point to our endpoint, and your existing scripts work immediately. This eliminates the learning curve often associated with switching TTS providers.
No need to hunt for proprietary SDKs or install heavy dependencies. The straightforward REST interface means you can integrate voice capabilities into your IoT projects using simple HTTP requests. It is designed to fit seamlessly into the workflows you already use for device communication.
OpenAI SDK Compatible
Leverage the official OpenAI SDKs by changing just one setting: the base_url. Point it to https://api.playa111.com/v1 and use your API key. This compatibility ensures that your existing code logic remains intact while gaining access to our specific voice models.
- Works with standard OpenAI client libraries
- Single configuration change required
- Familiar request structure
REST API Simplicity
Send a simple POST request with your text and voice preference to receive an audio file. The JSON body structure is intuitive, making it easy for no-code platforms to process the request. You get an audio file directly in the response, ready for playback.
- JSON-based input
- Direct audio file response
- Easy to automate
Multiple Audio Formats
Choose the audio format that best suits your hardware. Whether your device prefers MP3 for efficiency, WAV for quality, or FLAC for lossless storage, we support mp3, wav, opus, flac, and pcm. This flexibility ensures compatibility with a wide range of IoT speakers and displays.
- mp3, wav, opus, flac, pcm
- Optimize for bandwidth or quality
- Support legacy hardware

Technical Specs for Developers
The API enforces a strict rate limit of 60 requests per minute per key, with a lower threshold of 10 requests per minute before your first top-up. This ensures stable performance for your IoT devices without overloading the server.
Requests are processed sequentially, so under heavy load, synthesis may queue slightly. For texts exceeding 4096 characters, split your input into chunks and join the resulting audio files to maintain quality and compliance with the character limit.
Rate Limits
The API enforces a strict rate limit of 60 requests per minute per key, with a lower threshold of 10 requests per minute before your first top-up. This ensures stable performance for your IoT devices without overloading the server.
Requests are processed sequentially, so under heavy load, synthesis may queue slightly. For texts exceeding 4096 characters, split your input into chunks and join the resulting audio files to maintain quality and compliance with the character limit.
- 60 requests/minute per key after top-up
- 10 requests/minute before first top-up
- Sequential processing may cause minor queue delays
Request Structure
Send a POST request to https://api.playa111.com/v1/audio/speech with a JSON body. The structure mirrors the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply updating the base_url. Auth requires a Bearer token.
Include the model ("tts-1" or "tts-1-hd"), input text, voice preset, response_format, and optional speed (0.25–4.0). The input field supports up to 4096 characters per request. If language is omitted, the system guesses from the script, defaulting to English for Latin text.
- Endpoint: POST /v1/audio/speech
- Auth: Authorization: Bearer tts-...
- Max input: 4096 characters
- Models: tts-1, tts-1-hd
Audio Formats
Choose your preferred output format by setting the response_format field in your request. Supported formats include mp3, wav, opus, flac, and pcm, ensuring compatibility with various IoT hardware and software pipelines.
Each generated audio file contains an inaudible watermark to identify it as synthetic speech. Failed requests are free, with charges returned in full if synthesis fails.
- mp3, wav, opus, flac, pcm
- Inaudible synthetic watermark included
- Failed requests are refunded instantly
Data Privacy and Security
When you send text to our API, we use it strictly to generate the audio file you receive. We do not use your input text to train our models or improve the engine, ensuring your content remains yours.
Once the audio is returned in the response, we do not store the generated files. Your data is transient, processed only for the immediate delivery of your voice output, keeping your IoT project's audio private and secure.
No Training Data Usage
Unlike many other services, your input text is not harvested for training purposes. We process your characters solely to create the audio response and then discard the text input, ensuring your unique voice prompts remain proprietary to your project.
No Audio Storage
The generated audio files are returned directly in the API response and are not saved on our servers. This means we do not retain copies of your smart speaker prompts or vehicle notifications, minimizing your data footprint in our cloud infrastructure.
Metadata Retention
We keep basic request metadata, including the timestamp, character count, and status, to accurately calculate your usage and billing. This limited data helps us ensure you are charged correctly for the $0.01 per 1,000 characters rate without storing your actual voice content.
Common Use Cases in IoT
IoT devices need clear, human-like audio feedback without complex infrastructure. Our API delivers natural speech for smart speakers, vehicle dashboards, and home automation alerts, ensuring users receive timely, understandable notifications.
By replacing legacy TTS services, you gain predictable costs and easy integration. Use any voice to create engaging prompts that enhance the user experience in your connected devices.
Smart Speaker Prompts
Generate warm narration for daily briefings or entertainment. Voices like Aria or Luna provide a natural listening experience for smart displays and speakers.
Use Nova for bright, upbeat energy or Felix for energetic promotional content in retail or home settings.
- Use Aria for warm, clear narration
- Use Luna for soft storytelling
- Use Nova for upbeat reminders
Vehicle Notifications
Deliver clear, energetic audio for navigation updates or safety warnings. Atlas provides neutral clarity for news-style updates, while Orion adds depth for documentary-style travel guides.
Ensure messages are understood even in noisy cabin environments with high-quality speech synthesis.
- Use Atlas for neutral, news-style updates
- Use Orion for deep, documentary style
- Use Felix for energetic, promo-style audio
Home Automation Alerts
Send friendly conversational notifications for security alerts or appliance status. Milo’s friendly tone makes routine checks feel personal and approachable.
Integrate quickly with existing IoT workflows using simple REST API calls to trigger audio responses for doors, cameras, or sensors.
- Use Milo for friendly, conversational tone
- Use Sage for calm, instructional audio
- Use local language support for global homes

Get Started in Minutes
Getting started with IoT Voice Lab takes just minutes, not days. You can sign up instantly using your Google account or create a standard email-based account. There are no complex contracts or enterprise sales calls to schedule.
Sign Up with Google
Visit the /get-api-key/ page and click the Google sign-in button. This method automatically grants you a $0.50 free trial credit, valid for 7 days, giving you about 50,000 characters to test your hardware setup risk-free.
Get Your API Key
Once logged in, your dashboard displays your unique API key immediately. You can also generate a new key at any time, which invalidates the old one instantly. There is only one active key per account, keeping your integration simple and secure.
Run Your First Test
Use the provided curl example on your dashboard to send your first request. Point your OpenAI SDK or HTTP client to https://api.playa111.com/v1 and swap the key. Your device will receive a clear audio file within seconds.
- Base URL: https://api.playa111.com/v1
- Endpoint: POST /v1/audio/speech
- Format: JSON body
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.
