Frequently asked questions
Which TTS API is best for IoT?
We don’t claim to be the best, but our API is built for IoT developers using Node.js. Send text via a simple POST endpoint to receive audio files, making integration easy for smart home projects. With support for 23 languages and eight distinct voice presets, you can add clear, synthetic speech to your devices without complex infrastructure or heavy coding.
How do I compare TTS APIs?
Compare based on supported voices, language coverage, pricing per character, and request limits. Check if the API supports standard formats like MP3 or WAV and if it requires specific SDKs. Our API uses the OpenAI request shape, allowing you to use existing Node.js libraries by simply changing the base URL.
Is our API the best choice?
We don’t claim to be the best. We offer a straightforward API for IoT developers needing simple text-to-audio conversion. Pricing is transparent at $0.01 per 1,000 characters, with USDT TRC-20 payments. Choose us for a no-nonsense solution without monthly plans or subscriptions, perfect for smart home projects.
What makes a TTS API good?
A good TTS API provides clear audio, supports multiple languages, and offers reasonable rate limits. It should allow easy integration via standard HTTP requests. Our API supports eight voices, 23 languages, and formats like MP3 and WAV, ensuring your smart home devices can play diverse voice prompts effectively.
How much does a TTS API cost?
Our pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. You start with a $0.50 trial credit valid for 7 days. Top-ups via USDT TRC-20 are credited automatically, with no minimum spend or monthly fees required to keep your service running.
Do I need an npm package?
No specific npm package is required. You can use the official OpenAI SDKs by changing the base URL to https://api.tk971.info/v1. Alternatively, send standard HTTP POST requests with JSON bodies. This flexibility allows you to integrate the API directly into your Node.js IoT projects without extra dependencies, keeping your smart home setup simple and lightweight.
Can I use multiple APIs?
Yes, you can use multiple TTS APIs simultaneously. Each account has one active API key, but you can issue new keys anytime. You can mix our API with other providers based on your project needs, such as using different voices or languages for various smart home devices or notifications.
What is voice cloning?
Voice cloning typically means uploading a sample to create a custom synthetic voice. Our API does not offer custom voice cloning or voice design. Instead, we provide eight preset voices based on licensed recordings. Every generated file carries an inaudible watermark to mark it as synthetic speech.
Is streaming important?
We return complete audio files, not streaming. Short phrases take a few seconds to generate, while longer texts process at roughly real-time speed (about 25 characters per second). For immediate playback in your IoT projects, buffer the response or pre-generate audio files for local device playback. This ensures smooth voice integration without requiring complex streaming infrastructure.
How do I choose a voice?
Select from eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Each has a distinct tone, from warm narrators to energetic promos. All voices speak any of our 23 supported languages. Choose a voice matching your device’s personality, like Atlas for news or Luna for storytelling.
What languages should I support?
Support the 23 languages we offer: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, allowing you to serve a global audience of smart home users effectively.
How do I handle errors?
Failed requests are free, with the charge returned in full. Monitor API responses for status codes. If you exceed the rate limit of 60 requests per minute, requests may queue or fail. Ensure your input text is under 4,096 characters per request to avoid errors. For longer texts, split them into parts and join the resulting audio files.
Is our API secure?
Yes. We use standard Bearer token authentication with your API key. 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 is kept for billing purposes only. Note: We do not offer SLAs, uptime guarantees, or certifications like SOC 2 or HIPAA.
Can I upgrade later?
We don’t offer monthly plans or seats to upgrade. Instead, you can top up your balance anytime using USDT on the TRON network. The minimum top-up is $5, and credits are added automatically. Your balance never expires, allowing you to scale your IoT project’s voice usage as needed without any commitment.
Criteria for Choosing a TTS API
For IoT developers, selecting a Text-to-Speech API hinges on seamless integration, transparent pricing, and natural voice output. The ideal solution minimizes code changes while delivering reliable audio for smart home devices.
Ease of Integration
A RESTful API compatible with the OpenAI SDK allows developers to integrate voice capabilities with minimal code changes. You can also use plain HTTP requests, ensuring flexibility without requiring the official OpenAI package or custom libraries.
- Standard HTTP or OpenAI SDK compatibility
- Simple JSON request structure
- No custom libraries required
Cost Efficiency
Our pricing is $10 per million characters, equating to just $0.01 per 1,000 characters. This pay-per-character model ensures no monthly fees or budget surprises, making it ideal for both occasional alerts and continuous device updates.
- $0.01 per 1,000 characters
- $10 per million characters
- No monthly subscription fees
Voice Quality
High-quality synthetic speech enhances user experience in smart speakers and home assistants. Our API offers eight distinct voices, ensuring clear and engaging audio output for various IoT applications.
- Natural-sounding synthetic speech
- Eight distinct voice presets
- Clear audio for smart devices
Our API: Features and Benefits
API key management is straightforward: issue a single key per account, with instant revocation if needed. Our endpoints mirror the OpenAI speech API shape, allowing you to swap the base URL and use official OpenAI SDKs with minimal code changes. This compatibility means you can leverage existing Node.js libraries without learning a new interface, keeping your smart home integration simple and maintainable.
OpenAI SDK Compatibility
Our API endpoint matches the OpenAI speech request structure. By changing the base_url to https://api.tk971.info/v1, you can use the official OpenAI SDKs directly. This means your existing Node.js code for HTTP requests works with just a configuration tweak, reducing integration time for IoT projects.
8 Realistic Voices
Choose from eight presets like Aria, Nova, Luna, and Sage for female tones, or Felix, Milo, Atlas, and Orion for male tones. These voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), sourced from LibriVox public-domain audiobook readings. Each generated audio file carries an inaudible watermark marking it as synthetic speech.
23 Languages Supported
Support includes Arabic, Chinese, English, French, German, Japanese, Korean, Spanish, and more. Any voice can speak any supported language. If the language field is omitted, the system guesses from the script, defaulting to English for Latin text. For non-English Latin-script text, explicitly set the language code to ensure accuracy.

Pricing Comparison
We charge strictly per character, including spaces and punctuation, at $10 per million characters. Failed requests are free, with the charge returned in full, so you only pay for successful audio generation. This model eliminates waste from trial runs or network errors.
Pay Per Character
Each character counts toward your usage, making costs predictable for any text length. With a free trial of $0.50, you can test up to 50,000 characters for seven days when signing in with Google. This allows IoT developers to validate integration without upfront commitment.
- Cost: $10 per 1,000,000 characters
- Includes spaces and punctuation
- Failed requests are free
No Monthly Fees
There are no subscriptions, seats, or minimum spending requirements. Your balance does not expire, and you can top up anytime using USDT on the TRON network (TRC-20). This pay-as-you-go structure suits projects with variable voice generation needs, from occasional alerts to continuous broadcasting.
- No monthly plans or subscriptions
- No minimum spend required
- Balance never expires
Competitive Rates
At $0.01 per 1,000 characters, our rates are transparent and direct. We do not issue invoices with VAT, keeping the process simple for global IoT deployments. Top-ups are credited automatically within minutes, ensuring your smart home devices never miss a cue due to payment delays.
- Transparent per-character billing
- No VAT or invoice fees
- Instant TRC-20 top-ups
Voice Options for IoT
We offer eight distinct voice presets derived from licensed LibriTTS-R and LibriVox public-domain audiobooks, ensuring authentic quality for your IoT projects. These voices support 23 languages, allowing your smart devices to communicate naturally in the user's preferred tongue.
Female Voices
Aria provides a warm, clear narrator tone ideal for ambient notifications. Nova offers a bright, upbeat style for cheerful reminders. Luna delivers a soft, storytelling sound perfect for bedtime routines. Sage presents a calm, instructional style for guiding users through device settings.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male Voices
Felix brings an energetic, promo-focused tone suitable for dynamic alerts. Milo offers a friendly, conversational style for daily check-ins. Atlas provides a neutral, news-like delivery for reliable information updates. Orion adds a deep, documentary feel for immersive experiences.
- Felix: Energetic, promo-focused
- Milo: Friendly, conversational
- Atlas: Neutral, news-like
- Orion: Deep, documentary
Specialized Voices
All eight voices can speak any of our 23 supported languages, providing flexibility for global IoT deployments. Whether you need a neutral tone for a vehicle system or a soft voice for a home assistant, these presets cover diverse use cases without requiring custom cloning.
Technical Capabilities
Control audio output precisely with our flexible format and speed options. Choose mp3 for broad device compatibility, wav for lossless quality, or opus and flac for efficient storage. You can also select pcm for raw data processing. Adjust playback speed using the speed parameter, ranging from 0.25 to 4.0, allowing you to optimize audio length for smart speakers or vehicle systems without sacrificing clarity.
Audio Formats
Select from mp3, wav, opus, flac, or pcm via the response_format field. All formats are generated instantly upon request, ensuring quick delivery to your IoT devices. These options cater to various bandwidth and storage constraints common in smart home environments.
- mp3 for broad compatibility
- wav for lossless quality
- opus and flac for efficient storage
- pcm for raw data
Speed Control
Fine-tune voice timing with the speed parameter, supporting values from 0.25 to 4.0. This allows you to create faster announcements for alerts or slower, clearer instructions for accessibility features in home assistants.
Language Detection
The API automatically detects language from the text script. If Latin script is used without a language code, it defaults to English. For other Latin-script languages like Spanish or German, explicitly set the language ISO code to ensure accurate pronunciation.
- Automatic script detection
- Default English for Latin script
- Explicit
languagecode for non-English Latin text
Integration Experience
Getting voice into your IoT projects requires minimal coding effort. You can generate audio files by sending a simple HTTP request, making it easy to add voice capabilities to smart home devices without heavy lifting. Our API is designed for developers who want straightforward integration with tools like Node.js.
We provide ready-to-use cURL examples on the /get-api-key/ page to help you start quickly. This reduces the time needed to test voice synthesis in your specific environment, ensuring you can focus on building your device features rather than debugging complex audio pipelines.
Simple Setup
Integration is straightforward: send text via JSON and receive an audio file. You can use the official OpenAI SDKs by simply adjusting the base URL to our API endpoint. This compatibility means you likely already have the tools needed to start generating speech for your smart home projects.
- Standard JSON request body
- Works with existing OpenAI SDKs
- Ready cURL example provided
Good Documentation
The /get-api-key/ page displays a ready cURL example, giving you immediate access to a working request structure. This allows you to test the API directly from your terminal or IoT gateway without needing to read through extensive guides first. Clear endpoint details help you integrate voice features rapidly.
Community Support
Support is available by email only. We do not offer live chat, phone support, or a dedicated community forum for user discussions. For help with integration, please reach out via email with your specific questions or error logs.
Use Case Suitability
IoT Voice Labs provides a reliable way to add voice to IoT projects. You just send text and get audio files for your devices. This works well with Node.js, so there is no heavy coding. You can use simple scripts to make your smart home speak.
Smart Speakers
Use Aria for clear narration or Felix for energetic promo messages. These voices work well for daily updates or weather reports. You can adjust the speed from 0.25x to 4.0x to fit your device’s response time.
- Clear, natural-sounding voices like Aria or Felix.
- Adjustable speed from 0.25x to 4.0x.
Vehicle Systems
The deep, documentary-style voice of Orion provides authoritative guidance for navigation. You can send short text commands and receive audio files quickly. This is useful for turn-by-turn directions or vehicle status updates without distracting the driver.
- Deep, documentary-style voice of Orion for authoritative guidance.
- Fast generation for real-time updates.
Home Assistants
Use Sage for instructional cooking tips or Nova for upbeat reminders. These voices are friendly and conversational, perfect for daily home routines. You can integrate them into your Node.js app with a simple API call.
- Use Sage for instructional cooking tips or Nova for upbeat reminders.
- Friendly and conversational tones for daily routines.

Performance and Reliability
Performance depends on request volume and queue depth. Each API key allows 60 requests per minute, increasing to 10 per minute before the first top-up. Requests are processed sequentially, so high demand may cause brief queuing delays.
Response Time
Short phrases typically take a few seconds to generate. For longer texts, synthesis runs at roughly real-time speed (about 25 characters per second). Under load, requests may wait in a queue before processing begins.
Note that only one key is active per account at any given time. Issuing a new key immediately invalidates the previous one, so you cannot simply add keys to increase concurrency beyond 60 requests per minute per account.
- Approx. 25 characters generated per second for long texts
- 60 requests per minute standard limit
- 10 requests per minute before first top-up
- Sequential processing may cause queuing
Scalability
Scalability is managed by splitting long texts into parts of up to 4096 characters. The system processes these sequentially and joins the resulting audio files. This approach ensures consistent output quality without requiring complex infrastructure.
Since concurrency is limited to one active key per account, scaling for higher throughput requires careful key rotation or multiple distinct accounts. There is no automatic horizontal scaling or SLA guarantee.
- Split text into 4096-character parts
- Audio files are joined automatically
- One active key per account
- No automatic horizontal scaling
Developer Experience
Integrating IoT Voice Labs is straightforward for Node.js developers. The API mirrors the standard OpenAI speech endpoint structure, allowing you to generate audio files by simply updating the base URL to https://api.tk971.info/v1. This compatibility means you can use existing OpenAI SDKs without learning a new library.
The API returns audio directly, ensuring seamless integration into your smart home projects. With a simple POST request, you receive the audio file, making it easy to add voice to IoT devices without heavy coding overhead.
Code Examples
Sending text to the API is simple. Use the standard OpenAI SDK by setting the base URL to https://api.tk971.info/v1. Pass your model, voice, and input text in a JSON body. The response contains the audio file, ready for playback on your device.
- Use standard OpenAI SDK with updated base URL
- Send JSON body with model, voice, and input
- Receive audio file directly in response
Error Handling
If synthesis fails, you are not charged. This ensures that errors do not impact your billing. Simply handle HTTP errors in your code to manage failed requests gracefully.
- No charge for failed synthesis
- Handle HTTP errors in code
- Graceful management of failed requests
Security and Privacy
Your input text is used solely to generate the audio file and is not used for training our models. Once the synthesis is complete, the generated audio is returned in the response and is not stored on our servers. Request metadata (time, characters, status) is kept for billing purposes only.
Data Usage
We prioritize privacy by ensuring your spoken data remains transient. Input text is processed strictly for audio generation and never reused for model training. The resulting audio files are delivered directly to your device and are not persisted on our infrastructure, keeping your smart home voice content private.
- Text is not used for training
- Generated audio is not stored
- Metadata kept only for billing
Key Management
Security is simplified with a single active API key per account. You can issue a new key at any time via the dashboard, and the old one stops immediately. This ensures that if a key is compromised, your IoT devices can be updated instantly without complex rotation protocols.
- One active key per account
- Instant revocation on new key issuance
- Simple dashboard management
Final Recommendations
Selecting the right TTS API depends on your specific IoT project needs. This guide helps you choose the best fit for your smart home or device integration.
We recommend our API for beginners due to its simplicity, for scale due to its predictable pricing, and for value due to its competitive rates.
Best for Beginners
Our API is ideal for developers new to voice integration. The straightforward setup allows you to generate audio with a simple HTTP request, requiring no complex configuration or custom SDKs.
You can start with a free trial credit of $0.50, providing about 50,000 characters to test the service without immediate financial commitment.
- Simple HTTP POST endpoint
- No custom SDK required
- Free trial credit included
Best for Scale
For growing IoT deployments, our pricing model scales linearly with usage. You pay only for the characters you generate, with no monthly fees or minimum spend requirements.
Rate limits of 60 requests per minute per key can be managed by issuing new keys as needed, ensuring your device fleet continues to operate smoothly.
- Pay-per-character pricing
- No monthly fees
- Flexible key management
Best Value
Our competitive rate of $10 per million characters offers excellent value for high-volume voice generation. Failed requests are free, ensuring you only pay for successful audio files.
With 8 diverse voices and support for 23 languages, you get a rich set of options without additional costs, making it a cost-effective solution for global IoT projects.
- $10 per million characters
- Free failed requests
- 8 voices, 23 languages

Conclusion
Summary of Findings
IoT Voice Labs delivers a reliable, character-based TTS API that integrates seamlessly with Node.js projects. With eight distinct voices, support for 23 languages, and OpenAI SDK compatibility, it removes heavy coding lifts for smart home developers. The straightforward pricing and simple key management make it ideal for both beginners and scaling IoT applications.
The API’s focus on simplicity, combined with transparent character counting and USDT top-ups, ensures predictable costs without monthly fees. Its compatibility with standard formats and speed controls provides the flexibility needed for diverse voice-enabled devices.
- Eight realistic voices for varied use cases
- Support for 23 languages with automatic detection
- Simple Node.js integration via OpenAI SDK
- Transparent character-based pricing with no hidden fees
Next Steps
Sign up at https://tk971.info/get-api-key/ to receive your API key and $0.50 free trial credit. Explore the documentation for quick start guides and code examples tailored to Node.js environments.
Test the API with your smart home scripts and adjust voice settings to match your device’s audio requirements. For support, email us directly at [email protected].
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your devices work together to create a simple, comfortable home without any complex setup or coding knowledge required by you.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-python on GitHub
- Python documentation
- TRON developer hub: TRC-20
- OpenAI API reference: create speech
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- openai-node on GitHub
- curl documentation
- LibriTTS-R corpus (OpenSLR 141)
- IETF RFC 7845: Ogg Opus
- Node.js documentation
