Frequently asked questions
What makes a TTS API best?
Reliability means consistent, clear multilingual output for smart home devices. Our API processes requests sequentially, so high load may cause slight delays. It is optimized for embedded systems, ensuring stable integration without complex infrastructure. While we offer no SLA guarantees, our 60 requests-per-minute limit and automatic queue handling keep connected voice experiences running smoothly for product teams.
How many voices are available?
There are eight presets available. Four female voices include Aria, Nova, Luna, and Sage. Four male voices are Felix, Milo, Atlas, and Orion. These voices are based on licensed recordings from LibriTTS-R and LibriVox. Each voice can speak any of the supported 23 languages, providing versatile options for your device.
Which languages are supported?
We support 23 languages: 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. If the language is not set, it is guessed from the script.
Is the API easy to integrate?
Yes, it uses the standard OpenAI SDK shape. Send a POST request to the speech endpoint with JSON body. You only need to change the base_url to our API domain. This allows you to use existing OpenAI SDKs directly. Authentication is handled via a simple Bearer token in the header.
How does pricing compare?
Pricing is $10 per 1 million characters. Failed requests are free. There are no monthly plans, seats, or minimum spends. You can top up using USDT on the TRON network. This model suits variable usage in smart home products, ensuring you only pay for the audio you actually generate successfully.
What are the technical limits?
Each request accepts up to 4096 characters. You can split longer texts into parts and join the audio files. Rate limits are 60 requests per minute per key. Short phrases take a few seconds, while longer texts generate at roughly real-time speed. Requests are processed sequentially under load.
Which audio formats are supported?
You can choose from mp3, wav, opus, flac, and pcm. These formats cover most embedded systems and voice assistants. The API returns the audio file directly in the response. Generated audio is not stored, ensuring immediate delivery for your smart home device's playback requirements without additional storage overhead.
Is data privacy guaranteed?
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. We do not offer specific certifications like SOC 2 or HIPAA, but data handling is straightforward and transparent.
What support is available?
Support is available by email only. There is no live chat or phone number. We do not provide an SLA or uptime guarantee. For technical issues, you can reach out via email. Our documentation provides ready curl examples to help you troubleshoot integration issues quickly and independently.
Is there a free trial?
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 with USDT to continue using the API. The balance does not expire after the trial.
Which use cases fit best?
Our API is optimized for embedded systems, voice assistants, and smart home devices. It provides clear, multilingual audio output for product teams. Use cases include device prompts, notifications, and interactive voice responses. The sequential processing suits moderate traffic levels typical in connected home environments without requiring complex scaling infrastructure.
Can I clone voices?
No, we do not offer custom voice cloning. You cannot upload your own voice or design new voices. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. This ensures clear identification of AI-generated audio.
Do I need streaming?
No, we do not offer streaming or WebSocket support. The API returns the complete audio file in the response. This is suitable for most smart home devices that can handle standard HTTP responses. If you need real-time partial audio, you will need to implement buffering or wait for the full file.
How do I choose a voice?
Choose based on your device's personality. Aria is a warm narrator, while Nova is bright and upbeat. Luna is soft for storytelling, and Sage is calm for instructions. Male voices include Felix for promos, Milo for conversation, Atlas for news, and Orion for documentaries. Test them with your specific use case.
Criteria for Evaluation
Selecting a TTS API for smart home devices requires balancing audio fidelity with system constraints. For voice assistants and embedded systems, clarity is paramount. Our API delivers clear, natural-sounding speech across eight distinct voice presets, ensuring your product’s audio feedback remains crisp even in noisy environments.
Beyond quality, the breadth of language support determines your global reach. We support 23 languages, allowing you to deploy products in major markets without managing multiple voice models. Additionally, our pricing structure is straightforward and scalable, charging only for the characters you actually process, which aligns costs directly with usage volume.
Voice quality and clarity
Our eight voice presets are designed for distinct use cases, from warm narrators to energetic promo voices. Each voice is generated from licensed recordings, ensuring a consistent and professional tone.
- Eight distinct voice personalities for varied user experiences
- Optimized for clear playback on embedded hardware
- Consistent tone across all supported languages
Language support breadth
We support 23 languages, covering most major global markets. If you do not specify a language, the system guesses it from the script, defaulting to English for Latin text. This automatic detection simplifies integration, though you should explicitly set the language parameter for non-English Latin scripts to ensure accuracy.
- Support for 23 languages including English, Spanish, German, and Japanese
- Automatic language detection for Latin scripts
- Explicit language parameter for precise control
Pricing structure
Pricing is based on character count, costing $10 per million characters. Failed requests are free, so you only pay for successful synthesis. There are no monthly fees or minimum spends, making it easy to predict costs for your product’s audio requirements. You can start with a free trial credit when signing up with Google.
- $0.01 per 1,000 characters
- No monthly fees or subscriptions
- Free trial credit for Google sign-ups
Voice Options Comparison
SmartVoice API offers eight preset voices, each tuned for specific tonal qualities. These options allow product teams to select audio that aligns with their brand’s personality without needing custom voice design. You can choose from warm narrators to energetic promo speakers, ensuring clear audio output for connected devices.
The selection includes four female and four male voices, providing balanced options for diverse user interfaces. Each voice is distinct, ranging from soft storytelling tones to deep documentary styles. This variety helps maintain consistent user experience across different smart home features, from weather updates to security alerts.
8 preset voices available
Our library includes eight distinct presets designed for clarity and natural flow. These voices are optimized for short commands and longer informational text, ensuring consistent quality across various use cases.
Each preset is based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. This foundation ensures high audio fidelity while keeping licensing straightforward. The voices carry an inaudible watermark to identify synthetic speech, which is useful for transparency in voice-enabled products.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat tone
- Luna: Soft, storytelling style
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Male and female options
The API provides four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). This balance allows you to match the gender of the voice to your app’s identity or user demographics. You can switch voices easily by updating the voice field in your API request.
All voices support the same 23 languages, so gender preference does not limit language options. Whether you need a friendly conversational tone or a neutral news style, the available presets cover common voice assistant archetypes. This flexibility helps maintain a cohesive brand voice across multiple languages.
Distinct personalities
Each voice has a unique character, from the deep, documentary style of Orion to the bright, upbeat Nova. These distinct personalities help differentiate features in your smart home ecosystem. For example, use Atlas for neutral system alerts and Luna for engaging story modes.
The tones are designed to be clear and non-fatiguing during repeated use. Since requests are processed sequentially, the audio quality remains consistent even under load. You can adjust the speed between 0.25x and 4.0x to further tailor the voice’s delivery to your specific context.
Language Coverage
SmartVoice API supports 23 languages, covering major global markets like English, Spanish, German, French, Japanese, and Chinese. This breadth allows product teams to deploy voice assistants in diverse regions without managing multiple voice models. Each voice can speak any of these languages, ensuring consistent audio quality across your smart home devices.
The API automatically detects the language from the text script. Latin script defaults to English, but you can explicitly set the language parameter for other Latin-script texts.
23 languages supported
We support 23 languages, including 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 preset can deliver clear audio in any of these languages, making it easy to localize your smart home products for different markets.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Major global markets covered
Our language list covers key regions for smart home adoption, including North America, Europe, East Asia, and parts of South Asia and Africa. This allows you to reach a wide audience with a single API integration. We do not currently support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, or other languages outside this list.
Automatic detection feature
If you do not set the language field, the API guesses the language from the script. Latin text defaults to English. For non-English Latin-script text, you should explicitly set the language parameter to ensure accurate pronunciation. This feature reduces the need for complex language detection logic in your voice assistant's backend.
Integration Ease
SmartVoice API is designed for seamless integration into smart home ecosystems. By adhering to the OpenAI speech endpoint structure, existing SDKs work with minimal configuration. Simply update the base_url to https://api.playll88.com/v1 and supply your API key, allowing your product team to leverage familiar tools without learning a new protocol.
OpenAI SDK compatibility
Our API mirrors the standard OpenAI speech endpoint shape. This means you can use official OpenAI SDKs by simply changing the base_url to https://api.playll88.com/v1. This compatibility reduces development time, as your existing code structure remains valid, requiring only the endpoint and key adjustments.
Simple JSON structure
Requests are sent via POST with a clean JSON body. You specify the model ("tts-1" or "tts-1-hd"), input text, voice, response_format, and optional speed or language. The endpoint is POST https://api.playll88.com/v1/audio/speech. This straightforward structure ensures quick implementation for voice assistants and IoT devices.
Quick start examples
Getting started is immediate. Create an account at /get-api-key/ to receive your API key. Use the provided curl example on the dashboard to generate your first audio file. For longer texts, split input into 4096-character chunks and join the resulting audio files seamlessly.
- Endpoint:
POST https://api.playll88.com/v1/audio/speech - Auth:
Authorization: Bearer tts-... - SDK: Use OpenAI SDK with modified
base_url
Pricing Models
SmartVoice API charges $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free, ensuring you only pay for successful synthesis. This model scales naturally with usage, making it ideal for products with variable voice output needs.
Pay per character
The cost is $10 per million characters, or $0.01 per 1,000 characters. This straightforward metric helps you predict expenses based on character count, whether for short notifications or longer audio feedback loops.
No monthly fees
There are no subscriptions, seats, or minimum spend requirements. You can top up with USDT (TRC-20) whenever needed, with a $5 minimum. Balances never expire, allowing you to pay exactly for what you use.
Transparent costs
Request metadata tracks characters and status for billing clarity. Input text is not used for training, and generated audio is not stored, keeping your data usage clean and predictable without hidden fees.
Technical Limits
Smart home devices often have constrained memory and network buffers. Our API processes requests sequentially, meaning under load, synthesis may wait in a queue. This affects latency expectations for real-time interactions.
4096 character limit
Each API call accepts up to 4096 characters, including spaces and punctuation. For longer product descriptions or notifications, split the text into chunks and join the resulting audio files client-side. Short phrases take a few seconds to generate, while longer texts generate at roughly real-time speed.
60 requests per minute
Your API key allows 60 requests per minute. New accounts start with a limit of 10 requests per minute until the first top-up. This rate limit applies per key, so ensure your integration handles retries gracefully without overwhelming the endpoint.
No streaming support
The API returns the complete audio file only after synthesis finishes. There is no WebSocket or partial audio streaming. For voice assistants, this means a slight delay before playback begins. Plan your UI to show a loading state while waiting for the response.
Audio Formats
The API supports standard formats like MP3, WAV, and OPUS, ensuring compatibility with most smart home speakers and IoT devices. These formats balance quality and bandwidth, making them ideal for voice assistants delivering quick audio feedback or notifications.
MP3, WAV, OPUS options
MP3 offers efficient compression for general use, while WAV provides uncompressed clarity for high-fidelity playback. OPUS is optimal for low-bandwidth environments, ensuring clear audio even on slower IoT connections.
FLAC and PCM support
For lossless quality, FLAC preserves audio integrity without significant file size inflation. PCM provides raw, uncompressed audio data, suitable for direct hardware processing where minimal decoding overhead is required.
Format selection flexibility
Include the response_format field in your JSON request to specify your preferred output. This allows you to optimize storage and playback performance based on your device’s capabilities, ensuring seamless integration across diverse smart home ecosystems.
- Specify format via
response_formatparameter. - Choose MP3 for balanced efficiency.
- Use WAV for maximum compatibility.
- Select OPUS for low bandwidth.
- Opt for FLAC for lossless quality.
- Choose PCM for raw data.

Data Privacy
We prioritize your data’s journey through our system. Your input text is processed solely to generate the requested audio file. We do not use your content to train our models or improve voice quality, ensuring your product’s unique phrasing remains proprietary.
Input text not trained
The text you send to the API is used exclusively for synthesis. Once the audio is generated and returned, the original text is not retained for machine learning purposes. This ensures that your specific voice commands or notifications remain private.
Audio not stored
Generated audio files are returned directly in the response and are not stored on our servers after delivery. This minimizes storage risks and ensures that your smart device’s audio output is transient, appearing only where you choose to play it.
Metadata retention policy
We retain request metadata, including timestamp, character count, and status, strictly for billing verification. This data helps us process your TRC-20 top-ups accurately and resolve any discrepancies without storing the actual content of your voice interactions.
Support and Reliability
SmartVoice API provides dedicated support via email, ensuring your team gets direct assistance without waiting on hold or navigating complex support tiers. This channel is ideal for product teams needing clear, documented responses to integration questions or billing inquiries.
We do not offer a formal Service Level Agreement (SLA) or uptime guarantees, keeping our model simple and transparent. You can expect standard reliability for embedded voice experiences, but there is no contractual promise of 99.9% availability or financial credits for downtime.
Email support only
Our support team responds to emails, providing answers to your technical and account questions. This approach allows for thorough documentation of your issues, making it easier for your engineering team to track progress and implement solutions without the noise of live chat interruptions.
For urgent matters, you can also reference our comprehensive documentation or use the quick-start examples to resolve common integration hurdles independently.
- Direct email access to support team
- Detailed, documented responses
- No wait times for live agents
No SLA guarantee
Unlike enterprise providers, we do not tie our pricing to strict uptime contracts. This simplicity aligns with our pay-per-character model, where you only pay for successful requests. If a synthesis fails, you are not charged, reducing your risk significantly.
This model works well for smart home devices that can retry failed requests automatically without penalty, ensuring your users get audio feedback even if a single request fails.
Standard uptime
While we do not promise specific uptime percentages, our system is designed to handle typical loads for voice assistants and smart notifications efficiently.
Under heavy load, requests may queue, but they are processed sequentially to ensure accuracy. This ensures that your voice experiences remain consistent and predictable, even during peak usage periods.
Trial and Onboarding
Start testing your smart home voice features immediately. Sign up with Google to receive $0.50 in trial credit, valid for seven days. This provides approximately 50,000 characters of speech synthesis, allowing you to validate audio quality and integration logic without financial commitment. Accounts created via email and password do not receive this trial credit.
Upon successful registration, your API key is generated instantly. You can begin sending requests to the API base URL right away, with no waiting period for manual approval or setup steps. This rapid onboarding ensures your product team can move from concept to functional demo quickly.
Free trial with Google sign-up
Google sign-up grants $0.50 in credit, valid for seven days. This amount covers about 50,000 characters, sufficient for testing core voice outputs. Email-based accounts start without this initial credit, so choose your registration method accordingly.
- Instant credit activation
- 7-day validity period
- No credit card required
Instant API key generation
Your unique API key appears immediately after sign-up. Use this key with the standard OpenAI SDK by adjusting the base URL to https://api.playll88.com/v1. One active key is issued per account, ensuring simple authentication for your IoT devices.
- Immediate availability
- Standard Bearer token format
- Single active key per account
Demo ready in minutes
With the key and credit in place, you can execute your first synthesis request within minutes. The system processes requests sequentially, so initial tests may wait in a queue. This speed allows rapid iteration on voice assistant responses and smart notification audio.
Use Case Fit
SmartVoice API integrates seamlessly into connected devices, providing clear audio feedback for voice assistants and smart home interfaces. The API’s straightforward JSON structure allows product teams to quickly embed TTS capabilities without managing complex infrastructure or custom voice models.
For smart notifications and audio feedback loops, the API delivers reliable, multilingual responses that enhance user interaction. Whether it’s a simple confirmation or a detailed status update, the consistent audio quality ensures a polished experience across diverse global markets.
Voice assistants
Integrate SmartVoice API into your voice assistant to provide natural-sounding responses for commands and queries. The API’s support for 23 languages allows your assistant to communicate effectively with users worldwide, enhancing accessibility and user satisfaction.
Use the API to generate dynamic responses based on real-time data, such as weather updates or device status. The clear audio output ensures that users can easily understand the information, even in noisy environments.
- Supports 23 languages for global reach
- Clear audio output for noisy environments
- Dynamic response generation based on real-time data
Smart notifications
Leverage SmartVoice API to deliver timely and personalized notifications to users. Whether it’s a reminder, an alert, or a promotional message, the API ensures that the content is delivered in a clear and engaging manner.
The API’s ability to handle text up to 4096 characters allows for detailed notifications without compromising on audio quality. This is particularly useful for complex messages that require multiple sentences to convey the full context.
- Timely and personalized notifications
- Clear and engaging audio delivery
- Handles detailed notifications up to 4096 characters
Audio feedback loops
Implement audio feedback loops to confirm user actions, such as confirming a device has been turned on or off. The API generates audio files that are returned in the response, enhancing the overall user experience.
Use the API to generate audio cues for various events, such as a chime for a successful transaction or a tone for a device error. The consistent audio quality helps maintain a professional and reliable image for your product.
- Immediate audio feedback for user actions
- Audio cues for various events
- Consistent audio quality for a professional image
Final Recommendation
SmartVoice API is good for quick integration because it uses the familiar OpenAI SDK structure. You only need to change the base URL and provide your API key. This reduces setup time significantly for product teams building connected voice experiences without learning a new proprietary client.
Good for quick integration
SmartVoice API is good for quick integration because it uses the familiar OpenAI SDK structure. You only need to change the base URL and provide your API key. This reduces setup time significantly for product teams building connected voice experiences without learning a new proprietary client.
Good for multilingual products
The API supports 23 languages, covering major global markets like English, Spanish, German, and Japanese. Any voice can speak any of these languages, allowing you to maintain consistent audio quality across different regions. This makes it easy to localize smart home devices for international audiences without managing multiple voice providers.
Cost-effective for volumes
With a flat rate of $10 per million characters, you pay only for what you use. There are no monthly fees or minimum spend requirements. Failed requests are free, and you can top up easily with USDT on the TRON network. This transparent pricing model helps you budget accurately for your device fleet.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Connect devices seamlessly to deliver intuitive, responsive living experiences.
23 languages
Any voice speaks any of these languages.
