Frequently asked questions
What is Arabic TTS?
Arabic TTS is a cloud API that converts text into audio files. It supports Arabic alongside 22 other languages. You send text via a POST request and receive an audio file. The system guesses the language from the script, but you can explicitly set the language code for accuracy. This allows mobile app teams to generate natural-sounding speech for international releases without complex infrastructure.
How many characters can I send in one request?
You can send up to 4096 characters per request. Spaces and punctuation count toward this limit. For longer texts, split them into parts of this size and join the resulting audio files. This ensures consistent processing and allows you to manage token usage effectively within the API constraints.
Can I use the same voice for multiple languages?
Yes, every voice can speak any of the 23 supported languages. You do not need separate voices for different languages. Simply specify the desired language in the request or let the system guess it from the script. This simplifies your voice selection process for global mobile applications.
Does the API support streaming audio?
No, the API does not support streaming, WebSocket, or real-time partial audio. You send a text request and receive the complete audio file in the response. This synchronous approach is suitable for pre-generating audio assets for mobile apps rather than live conversation scenarios.
What happens if my request 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. You can retry the request with adjusted parameters without worrying about duplicate charges for the same text input.
Is the free trial available for all sign-up methods?
No, the free trial is only available when you sign in with Google. It provides $0.50 of credit valid for 7 days. Accounts created with an email and password start without this trial credit. Check your account status after signing up to see if you have received the trial credit.
Can I clone a custom voice for my app?
No, the API does not offer custom voice cloning for customers. You cannot upload your own voice or design a new one. You must choose from the eight available presets. These voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings.
What formats can I receive the audio in?
You can receive audio in mp3, wav, opus, flac, or pcm formats. Specify the desired format in the request body using the response_format field. This allows you to choose the best balance between file size and quality for your mobile app's storage and bandwidth constraints.
Is there a rate limit for the API?
Yes, 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. Monitor your usage to ensure smooth operation for your mobile app features.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5, and credits are automatically added within minutes after the transfer. There are no other payment methods like cards or PayPal. Your balance does not expire, allowing you to use credits at your own pace.
Do I need to pay for failed requests?
No, you do not pay for failed requests. If synthesis fails, the charge is returned in full. You only pay for successfully generated audio files. This policy ensures that you are charged only for the value delivered to your application, reducing risk during development and testing.
Are the voices based on real people?
Yes, the voices are based on licensed recordings from LibriTTS-R, which uses data from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech. This ensures the audio is distinct while maintaining high quality derived from real human recordings.
Can I use the audio for commercial purposes?
What is the maximum speed setting?
The maximum speed setting is 4.0. You can adjust the speed between 0.25 and 4.0 using the speed field in the request body. This allows you to control the pacing of the speech to match the tone of your mobile app, whether for narration or instructions.
First request
curl
curl https://api.playx333.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 voice selection matters for mobile apps
Mobile localization requires more than translated text; it demands natural audio that resonates with regional users. Voice selection impacts how users perceive your app's quality, especially in markets like the Middle East where Arabic TTS needs specific rhythmic handling.
Natural-sounding narration reduces churn by making interfaces feel polished and accessible. Poor voice choices break immersion, while consistent, clear audio keeps users engaged longer across international releases.
Localization beyond translation
Translating UI text is only the first step. To truly localize, you need audio that matches the linguistic nuances of each target market. Our API supports Arabic alongside 22 other languages, ensuring your app sounds native, not just translated.
Consistent voice selection across languages helps build brand identity. Whether your user is in Cairo or Berlin, the audio experience remains cohesive and professional, supporting retention in diverse regions.
- Support for Modern Standard Arabic and 22 other languages
- Consistent voice branding across international releases
- Reduces cognitive load for non-native speakers
User retention through natural audio
Users abandon apps that feel robotic or confusing. Natural intonation and clear pacing in TTS improve comprehension and reduce frustration, particularly for accessibility features or onboarding flows.
Testing voices before production ensures you pick the right tone. A warm narrator or upbeat presenter can significantly improve user engagement compared to a generic voice.
Long-form content like guided tours or audiobooks benefits from consistent quality. Our API maintains tone across segments, preventing jarring transitions that disrupt the user experience.
Reducing production costs with API integration
Traditional voice-over production is slow and expensive. With a RESTful API, you generate audio on-demand, eliminating studio booking and engineer fees for every update.
Integrate directly into your mobile app using the OpenAI SDK or standard HTTP requests. This allows dynamic voice changes without recompiling, keeping your development cycle lean and responsive to user feedback.
Pay only for what you use. With no monthly subscriptions, you avoid overhead for unused capacity. This model scales perfectly for startups testing new markets or rolling out features incrementally.
- No monthly fees or subscriptions
- Pay only for successful generations
- Integrate with existing mobile tech stacks
Arabic TTS capabilities
LuminaVoice delivers high-quality Modern Standard Arabic synthesis suitable for international mobile releases. The engine handles complex Arabic script correctly, ensuring accurate character-by-character processing without formatting errors.
Support for Modern Standard Arabic
The API processes Arabic text with precision, maintaining correct pronunciation and grammar structures. You can specify the language code explicitly to avoid guessing errors, ensuring consistent output for your app’s localized content.
- Accurate handling of Arabic script and diacritics
- Explicit language code support prevents guess errors
Natural rhythm and intonation
Voices like Aria and Luna provide warm, clear narration with natural cadence. The synthesis engine produces natural-sounding audio, making it less robotic and more engaging for end-users.
Consistent quality across long texts
Long texts are split into parts of up to 4,096 characters and joined seamlessly. This ensures that audio generated for lengthy app instructions or stories maintains consistent tone and quality throughout.
Voice catalog overview
LuminaVoice provides eight distinct voice presets designed for mobile app interfaces. Female voices include Aria (warm narrator), Nova (upbeat), Luna (soft storyteller), and Sage (calm instructor). Male options feature Felix (energetic promo), Milo (conversational), Atlas (neutral news), and Orion (deep documentary).
Female voices: Aria, Nova, Luna, Sage
Each female voice offers a distinct tonal quality suitable for different app contexts. Aria delivers clear narration, while Nova provides an energetic tone for updates. Luna suits storytelling features, and Sage offers a calm, instructional presence for guides.
Male voices: Felix, Milo, Atlas, Orion
Male voices cover diverse use cases from promotional content to news delivery. Felix adds energy to ads, Milo feels friendly for chat interfaces, Atlas provides neutrality for information, and Orion suits documentary-style audio.
All voices speak all 23 supported languages
All eight voices support all 23 languages, including Arabic, Hindi, and Spanish. You can select any voice for any supported language, allowing consistent character identity across your app’s international releases without needing separate voice assets.
Technical integration for mobile
To integrate LuminaVoice into your mobile app, use the standard OpenAI-compatible endpoint at https://api.playx333.com/v1. Update your SDK’s base URL and use your API key for authentication. This allows you to use familiar client libraries for quick integration without learning a new protocol.
RESTful API with OpenAI SDK compatibility
Point your existing OpenAI SDK configuration to our base URL. The request shape matches the standard speech endpoint, ensuring seamless compatibility with popular mobile development libraries.
Simple JSON requests for audio generation
Send a POST request with a JSON body containing the model, input, voice, and response_format. The API returns the audio file directly in the response, ready for playback or caching in your app.
Support for MP3, WAV, Opus, FLAC, and PCM
Choose the optimal format for your use case. MP3 and Opus are ideal for mobile data efficiency, while WAV and FLAC provide lossless quality for high-fidelity applications. PCM is available for raw audio processing.
Performance and limits
Understanding performance boundaries helps mobile teams plan their audio generation workflows efficiently. Our infrastructure handles requests sequentially, meaning high concurrency may introduce brief queue delays during peak usage. Knowing these limits prevents unexpected timeouts in your app’s audio pipeline.
By respecting character caps and rate limits, you ensure consistent delivery of synthetic speech without overloading the API. This predictability allows for smoother integration testing and reliable production releases across different regions.
Rate limits: 60 requests per minute
Each API key supports up to 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. This structure helps manage burst traffic while maintaining service stability.
- Standard limit: 60 requests/minute per key
- Initial limit: 10 requests/minute until first top-up
- Limits reset every 60 seconds
Character limit: 4,096 per request
Each API call accepts input text up to 4,096 characters, including spaces and punctuation. For longer content, split the text into smaller chunks and concatenate the resulting audio files. This approach ensures consistent quality and avoids truncation.
- Max 4,096 characters per request
- Spaces and punctuation count toward the limit
- Split and join for longer texts
Real-time generation speed
Generation speed approximates real-time for long texts, processing roughly 25 characters per second. Short phrases may take a few seconds to synthesize. Under heavy load, requests are queued and processed sequentially, so longer texts may experience slight delays.
- Approx. 25 chars/sec for long texts
- Short phrases take a few seconds
- Sequential processing under load

Pricing model
Pricing is straightforward: $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. You receive a $0.50 free trial credit (approx. 50,000 characters) valid for 7 days when signing in with Google, allowing immediate testing without a credit card.
$0.01 per 1,000 characters
Costs scale linearly with usage. Each request processes up to 4,096 characters; for longer texts, you must split and join the audio files.
No monthly fees or subscriptions
There are no seats, minimum spends, or recurring plans. You pay only for what you use, making it ideal for startups with variable demand.
Pay only for successful generations
If synthesis fails, the charge is returned in full. Top-ups via USDT (TRC-20) are credited automatically within minutes, with no expiration on your balance.
Getting started with a free trial
Create your account on playx333.com using your Google credentials to instantly access a $0.50 trial credit. This balance covers approximately 50,000 characters, allowing you to generate realistic audio samples for Arabic, Hindi, Spanish, and other supported languages without any financial commitment. The trial is valid for seven days, giving your team ample time to evaluate voice suitability for your mobile app's international releases.
You can begin testing immediately after sign-up. No credit card is required to activate the trial, and the process is straightforward. Use the provided API key to send test texts via the OpenAI-compatible SDK, ensuring your development workflow remains uninterrupted while you select the perfect voice for your users.
Sign up with Google for $0.50 credit
Register using your Google account to receive $0.50 in trial credit immediately. This amount allows for roughly 50,000 characters of audio generation. The credit expires after seven days, encouraging quick evaluation without long-term commitment.
- Instant activation via Google sign-in
- Approximately 50,000 characters of test audio
- Seven-day validity period
- No credit card required
Test Arabic and other voices immediately
Once registered, you receive an API key and can start generating audio right away. Test the warm narration of Aria or the clear instructional tone of Sage in Arabic, or explore the energetic promo style of Felix. Use the OpenAI SDK by changing the base URL to https://api.playx333.com/v1 and sending standard JSON requests.
No credit card required for trial
The trial account requires no payment method on file. This removes friction for startup teams wanting to evaluate voice quality before integrating the API into production. You pay for usage based on your balance, which is topped up with USDT on the TRON network, starting from a minimum of $5.
Data privacy and licensing
We prioritize your data integrity by ensuring that the text you send for synthesis is used exclusively to generate the audio file. It is not retained for training purposes, keeping your content secure and private during the generation process.
For billing transparency, we store only request metadata such as timestamps, character counts, and status to calculate accurate charges. The generated audio itself is returned in the response and is not stored on our servers after delivery.
Text not used for training
Your input text is processed solely to produce the requested audio file. We do not use your text data to train or improve our underlying models, ensuring your proprietary content remains yours.
Voices based on licensed recordings
Our voice presets are derived from high-quality licensed recordings. Specifically, the voices utilize data from LibriTTS-R, which is licensed under CC BY 4.0. This ensures legal clarity for your commercial mobile app releases.
Inaudible watermark on generated audio
Every audio file generated through our API carries an inaudible digital watermark. This marks the file as synthetic speech, helping you maintain transparency with your end-users regarding the nature of the audio content.
Support and contact
Our support is handled exclusively via email. We focus on providing clear, documented solutions rather than real-time hand-holding, allowing us to keep costs low and infrastructure simple for mobile startups.
Email support only
Send your questions to our support team. We prioritize clarity and accuracy in our responses, ensuring you get the specific technical details you need for integration.
No live chat or phone support
We do not offer live chat or phone lines. This streamlined approach reduces overhead and keeps our pricing competitive. You can reach us directly by email for any account or API issues.
Documentation for developers
Complete integration guides are available at /docs/. The API follows the OpenAI speech endpoint format, making it easy to use existing SDKs. We recommend reviewing the rate limits and character constraints before production.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Craft intuitive mobile applications that captivate early adopters and drive rapid user acquisition.
23 languages
Any voice speaks any of these languages.
