Frequently asked questions
Is the AI voice generator really free?
You start with a $0.50 free trial (about 50,000 characters) valid for 7 days when signing in with Google. After that, the rate is $10 per 1 million characters. Failed requests are free, and there are no monthly subscriptions or minimum spends required to use the API.
Which voices are best for elderly users?
We do not claim any voice is best. For elderly users, aria (warm, clear narrator), luna (soft, storytelling), and milo (friendly, conversational) are strong choices. They prioritize clarity and natural pacing, supporting clear audio comprehension in assistive devices and care tools where the end-user experience depends on easy listening.
Can the API handle Hindi and other non-English languages?
Yes, we support 23 languages including Hindi, Spanish, German, Japanese, and Arabic. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses it, but for non-English Latin-script text, we recommend explicitly setting the language code.
How do I integrate this into my assistive device app?
Use a standard HTTP POST request to https://api.playtk333.com/v1/audio/speech with your Bearer token. The request shape matches the OpenAI speech endpoint, so you can use the official OpenAI SDK by changing the base URL. Send text and receive an audio file directly.
What happens if the synthesis fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files, protecting your budget when dealing with network issues or invalid input parameters during device operation.
Do I need to pay for a monthly subscription?
No, there are no monthly plans, seats, or subscriptions. You pay only for what you use at $10 per 1 million characters. Your balance does not expire, and you can top up as needed. There is no minimum spend required to keep your account active.
Are the voices robotic or natural-sounding?
Our voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They offer warm, clear, and soft speech patterns rather than robotic tones. Each generated audio file carries an inaudible watermark to mark it as synthetic speech, ensuring transparency in your assistive applications.
How long can the text input be?
Each request can handle up to 4096 characters of text. For longer texts, you should split the input into parts of this size and join the resulting audio files. This allows you to generate extended content for audiobooks or long-form assistive device narratives.
Is my user's text data stored after generation?
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 like time, characters, and status for billing purposes, but not the actual content of your users' text.
Can I use this for commercial products?
Yes. You can use the audio in assistive devices, care tools, or other commercial applications. Since generated audio is returned in the response and not stored, you can integrate it into your products. You simply need an active account with sufficient balance to cover your usage costs.
What audio formats are supported?
We support mp3, wav, opus, flac, and pcm formats. You can specify the desired response format in your API request. This flexibility allows you to choose the best balance between file size and quality for your specific assistive device hardware and network constraints.
How fast is the voice generation?
Generation is roughly real-time on long texts, processing about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue before being synthesized.
Do I need special hardware for the API?
No special hardware is needed to use the API itself; it is a cloud service accessed via HTTP. Your assistive device just needs internet connectivity to send requests and receive audio files. The processing happens on our servers, so your device hardware requirements are minimal.
How do I top up my account balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and funds are credited automatically within minutes after the transfer. We do not accept cards, PayPal, or invoices, ensuring a simple, direct payment method for your API usage.
First request
curl
curl https://api.playtk333.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 Assistive Tech Teams Choose AidVoice
AidVoice provides natural, clear voices designed to reduce listening fatigue for elderly users. Our engine delivers consistent, real-time audio synthesis, ensuring that assistive devices can read text smoothly without abrupt pauses or robotic tones that disrupt comprehension.
Clear, natural voices that reduce listening fatigue
Listening to synthetic speech for extended periods can be tiring. Our voices, such as Aria and Luna, offer warm and soft tones that feel more like a companion than a machine. This clarity helps users focus on the content rather than straining to understand the delivery.
- Aria: Warm, clear narrator for books and news
- Luna: Soft, storytelling tone for comfort and relaxation
- Sage: Calm, instructional voice for clear guidance
- Atlas: Neutral, news-style voice for straightforward updates
Multilingual support for diverse elderly populations
Many elderly users prefer hearing assistive content in their native tongue. AidVoice supports 23 languages, including Hindi, Spanish, and Arabic, allowing you to serve diverse demographics without managing separate voice engines. Automatic language detection works for most cases, but you can explicitly set the ISO code for precision.
- Support for 23 languages including Hindi, Spanish, and Arabic
- Automatic language detection or explicit ISO code setting
- Consistent voice quality across all supported languages
- Not supported: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali
Simple API integration without complex SDKs
You don’t need to build a custom audio player or manage complex state. AidVoice uses a standard OpenAI-compatible endpoint. If your team already uses OpenAI SDKs, you only need to change the base URL. This reduces development time and keeps your tech stack simple and maintainable.
- Standard HTTP POST requests for speech generation
- Compatible with existing OpenAI SDK setups
- Clear documentation for quick developer onboarding
- No custom SDKs or proprietary protocols required
The AidVoice API: Built for Reliability
AidVoice delivers consistent latency suitable for real-time reading experiences. Short phrases take a few seconds to generate, while longer texts process at roughly real-time speed (about 25 characters per second). Requests are processed sequentially, so under heavy load a request may wait in a queue, ensuring stable performance without unpredictable spikes.
Consistent latency for real-time reading experiences
Our infrastructure prioritizes steady throughput. While short phrases require a few seconds for synthesis, extended texts stream at approximately real-time speeds. This consistency helps product teams maintain a natural listening rhythm for elderly users, reducing cognitive load during assistive reading tasks.
Standard OpenAI-compatible endpoint for easy adoption
Integrate quickly using the standard OpenAI-compatible endpoint. Simply update your base_url to https://api.playtk333.com/v1 and use your API key. Existing OpenAI SDKs work out of the box, allowing your developers to swap in AidVoice without rewriting your core audio generation logic.
- Use
POST https://api.playtk333.com/v1/audio/speech - Supports
tts-1andtts-1-hdmodels - Standard JSON body structure with
input,voice, andmodel
No hidden fees or subscription locks for your budget
We charge only for characters used, with no monthly minimums or subscription locks. Failed requests are free, and your balance never expires. Top-ups via USDT (TRC-20) are credited automatically, giving you predictable costs for your assistive device budget without unexpected invoices or VAT surprises.
- $0.01 per 1,000 characters
- No monthly plans or seats
- Failed requests are free

Voices Designed for Clarity
AidVoice offers eight distinct voice presets, each crafted to reduce listening fatigue for elderly users. Whether reading a bedtime story or delivering a medication reminder, the right tone makes the difference between background noise and clear communication.
We source our voices from licensed LibriTTS-R and public-domain audiobook readings, ensuring natural, human-like quality without the uncanny valley effect. Every generated file carries an inaudible watermark to mark it as synthetic speech.
Aria and Luna: Soft, storytelling tones for comfort
Aria provides a warm, clear narrator style, ideal for reading books or calming routines. Luna offers a soft, storytelling tone that feels gentle and engaging, perfect for longer texts or evening wind-downs.
Atlas and Sage: Neutral, instructional voices for instructions
Sage is calm and instructional, making it excellent for step-by-step guides or health reminders. Atlas provides a neutral, news-like delivery that conveys information clearly without emotional bias, suitable for urgent updates.
Felix and Milo: Energetic and friendly for engagement
Milo offers a friendly, conversational tone that feels like a companion, great for daily check-ins. Felix brings an energetic, promo-ready energy, useful for highlighting new features or encouraging activity.
Languages for Global Accessibility
AidVoice supports 23 languages, including Hindi, Spanish, and Arabic, ensuring your assistive devices reach diverse elderly populations globally. Any voice can speak any of these languages, providing flexibility in how users interact with content.
We handle language detection automatically, defaulting to English for Latin script, but you can explicitly set the ISO code for non-English Latin text. Note that we do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.
Support for 23 languages including Hindi, Spanish, and Arabic
Our API supports 23 languages, including Hindi, Spanish, and Arabic, ensuring your assistive devices reach diverse elderly populations globally. Any voice can speak any of these languages, providing flexibility in how users interact with content.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic language detection or explicit ISO code setting
We handle language detection automatically, defaulting to English for Latin script, but you can explicitly set the ISO code for non-English Latin text. Note that we do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.
Consistent voice quality across all supported languages
Every generated file carries an inaudible watermark, and voice quality remains consistent across all 23 supported languages. This ensures a uniform listening experience whether your user is reading a news summary in English or a story in Spanish.
Pricing That Fits Small Teams
AidVoice charges $10 per million characters, making it $0.01 per 1,000 characters. Failed requests are free, ensuring you only pay for successful audio generation. There are no monthly plans, seats, or minimum spend requirements.
Pay only for characters used, no monthly minimums
Your budget scales directly with usage. Spaces and punctuation count as characters, so a 4096-character request costs exactly $0.04. This model eliminates the risk of paying for unused capacity in assistive devices that may have variable daily usage patterns.
Start with $0.50 free trial credit
Sign in with Google to receive $0.50 in trial credit, valid for 7 days. This covers approximately 50,000 characters, allowing your team to test voice clarity and integration without financial commitment. Email-based accounts start without trial credit.
Simple USDT top-up for predictable costs
Top up via USDT (TRC-20) on the TRON network. The minimum deposit is $5, and funds are credited automatically within minutes. We do not accept cards or PayPal, keeping transaction fees low and balances valid indefinitely without expiry.

How It Works for Your Users
AidVoice delivers audio files via a standard HTTP POST request, allowing your assistive devices to receive synthesized speech without complex streaming setups. This straightforward interaction ensures that users receive clear, playable audio files quickly, supporting immediate feedback for reading assistance or content consumption.
Since the API processes requests sequentially, longer texts require your application to split the input into parts of up to 4096 characters. You generate each segment individually and then join the resulting audio files to create a continuous listening experience for your users.
Handle long texts with automatic splitting
The API does not split text automatically; your integration must divide input exceeding 4096 characters into smaller segments. After splitting, generate each part individually and concatenate the audio files on the client side to ensure seamless playback for longer content.
Audio formats suitable for various assistive devices
Choose from mp3, wav, opus, flac, or pcm to match your device’s capabilities. MP3 offers efficient compression for network传输, while WAV and FLAC provide lossless quality for high-fidelity playback. PCM is ideal for raw audio processing in embedded systems.
Selecting the right format balances storage efficiency and audio fidelity. Most modern assistive devices support MP3 or WAV, making these the safest defaults for broad compatibility across elderly care tools and hearing aids.
Send text, receive audio file instantly
Send your text via a simple JSON body to the speech endpoint. The API returns an audio file directly in the response, eliminating the need for polling or additional endpoints. This immediate feedback loop is crucial for real-time reading assistance.
Response times vary: short phrases take a few seconds, while longer texts generate at roughly real-time speed (25 characters per second). Under load, requests may queue, so design your UI to indicate processing status appropriately.
Technical Requirements Made Simple
Generating speech is straightforward: send a JSON payload via HTTP POST to the standard endpoint. You provide the text, voice, and format, then receive the audio file directly in the response. This simplicity means your team can integrate audio capabilities without building custom streaming pipelines or managing complex WebSocket connections.
Standard HTTP POST requests for speech generation
The core endpoint accepts standard JSON bodies. You specify the model (tts-1 or tts-1-hd), the input text, and the desired voice. The API returns the audio file immediately, handling the synthesis on our servers. This approach keeps your client-side code lightweight and compatible with any language that supports HTTP requests.
- JSON body with text, voice, and format parameters
- Returns audio file directly in the response
- No streaming or WebSocket complexity required
Compatible with existing OpenAI SDK setups
If your team already uses OpenAI SDKs, integration is seamless. Simply update the base_url to https://api.playtk333.com/v1 and use your AidVoice API key. The request shape is identical to the OpenAI speech endpoint, so you can reuse existing code with minimal changes. This reduces onboarding time and leverages familiar tools.
- Same request shape as OpenAI speech endpoint
- Update base_url and API key to switch
- Works with official OpenAI SDKs
Clear documentation for quick developer onboarding
Our documentation provides ready-to-use curl examples and clear parameter definitions. You can start generating speech within minutes of signing up. The endpoint structure is consistent, and we provide clear error codes for common issues like rate limits or invalid voices. This transparency helps your developers debug and deploy faster.
- Ready-to-use curl examples
- Clear parameter definitions and error codes
- Consistent endpoint structure
Data Privacy and Simplicity
AidVoice processes your text exclusively to produce the audio response, ensuring it is never reused for model training. This approach keeps your input data private and distinct from our development pipeline, providing clarity for assistive tech teams who value data integrity.
Generated audio files are returned directly in the API response and are not stored on our servers. We retain only minimal metadata—such as timestamps, character counts, and status—for billing transparency. This ensures you can audit usage without worrying about long-term storage of your users’ content.
Input text used only for generation, not for training
We use input text strictly to generate the requested audio file and never reuse it for model training.
No long-term storage of generated audio files
Generated audio is returned directly in the response and is not stored on our servers.
Minimal metadata kept for billing transparency
Request metadata including time, characters, and status is kept solely for accurate billing. This allows you to monitor usage and costs without storing your actual content or audio files long-term.

Get Started with AidVoice
To begin, visit /get-api-key/ and sign up using your Google account or an email and password. Once registered, you will receive your unique API key immediately. This key authenticates your requests to the API base URL and allows you to start testing right away.
Sign up with Google or email to get your API key
Accounts are created per site, so ensure you are on the correct domain. After signing up, you can view your key, balance, and usage details directly on your dashboard. You can also issue a new key at any time, which stops the old one instantly.
Test with our free trial credit instantly
Signing in with Google grants you $0.50 in trial credit, valid for 7 days. This provides about 50,000 characters to test voice quality and latency. Note that accounts created with email and password start without this trial credit.
View our curl example to start generating speech
Use the provided curl example to send your first request. Remember that new keys start with a limit of 10 requests per minute, increasing to 60 after your first top-up. You can top up with USDT on the TRON network for consistent usage.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Our assistive devices empower elderly users to navigate daily life with renewed confidence and independence through intuitive design.
23 languages
Any voice speaks any of these languages.
