Frequently asked questions
Is Japanese text to speech natural for e-commerce?
Yes. Our API supports Japanese alongside 22 other languages. You can choose from eight distinct voice presets, such as Luna for storytelling or Felix for energetic promos. Each voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring clear and professional audio suitable for product descriptions and notifications.
How long does it take to generate audio?
Generation takes roughly real time, averaging 25 characters of text per second. Short phrases may take a few seconds, while longer texts are processed sequentially. Under load, requests may wait in a queue, but typical performance aligns closely with the duration of the spoken audio.
Can I use the audio commercially?
Yes. The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can generate audio for product descriptions, help content, and notifications. Each file includes an inaudible watermark marking it as synthetic speech, but there are no restrictions on your commercial usage.
Do I need to install software?
No. PlayPW provides a simple cloud API. You send text via a standard HTTP POST request and receive an audio file. You can use the official OpenAI SDKs by changing the base URL, or use plain HTTP. No mobile SDKs, WordPress plugins, or local installations are required.
What happens if the generation fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not billed for errors, making the API risk-free for testing and production workflows in your e-commerce infrastructure.
Is there a limit on text length?
Yes, each request accepts up to 4096 characters. For longer texts, you can split the input into parts, generate audio for each, and join the files. Spaces and punctuation count toward the character limit, so plan your input size accordingly to stay within the boundary.
Can I adjust the speaking speed?
Yes. You can set the speed between 0.25 and 4.0 using the speed parameter. This allows you to slow down complex product details or speed up simple notifications. The adjustment applies to both tts-1 and tts-1-hd models without affecting the voice character or language.
Do I need to set the language manually?
Not always. If omitted, the system guesses the language from the script, defaulting to English for Latin text. However, for non-English Latin-script text, you should set the language field explicitly. Japanese text will be detected automatically, but explicit settings ensure accuracy for ambiguous inputs.
How are voices licensed?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This means the source material is freely available for commercial use. We provide eight presets, including female voices like Aria and male voices like Atlas, all derived from these licensed sources.
What formats are supported?
You can request audio in mp3, wav, opus, flac, or pcm formats. Choose the format that best fits your e-commerce platform or notification system. The API returns the audio file directly in the response, allowing immediate playback or storage without additional conversion steps.
Is there a free trial available?
Yes. Signing in with Google gives you $0.50 of credit, valid for 7 days, allowing about 50,000 characters of generation. Email-based accounts start without trial credit. You can top up with USDT on the TRON network to continue using the API after the trial expires.
How do I pay for the API?
Pricing is $10 per 1 million characters. Payments are made via USDT on the TRON network (TRC-20), with a minimum top-up of $5. Credits are credited automatically within minutes. There are no monthly plans, subscriptions, or VAT invoices. Balance does not expire once added.
Can I use my own voice?
No. We do not offer custom voice cloning or uploading your own voice. You can choose from eight preset voices like Nova, Milo, or Orion. These voices are based on licensed recordings, but you cannot create a unique voice profile or design custom tones for your brand.
Is my data used for training?
No. Input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We keep request metadata like time and status for billing purposes, but your content remains private and unused for other purposes.
First request
curl
curl https://api.playpwpw.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 Japanese TTS for E-commerce?
E-commerce is global, but customers prefer shopping in their own language. Native audio helps Japanese shoppers understand product details and builds trust faster than text alone. It turns static descriptions into engaging experiences.
Boost localization with natural audio
Translate your store copy and generate speech that sounds authentic. Our API supports Japanese alongside 22 other languages, ensuring your brand voice remains consistent across markets. Ship text, receive audio files ready for your storefront.
Enhance accessibility for Japanese customers
Make your product pages inclusive. Audio support helps users with visual impairments or those who prefer listening while multitasking. It also aids non-native speakers who may struggle reading dense Japanese text.
Reduce production costs for video content
Skip expensive voice actors and studio bookings for every product update. Generate fresh audio instantly when prices or descriptions change. Pay only for what you use, starting with a free trial credit.
How It Works
PlayPW transforms your product descriptions and help content into natural-sounding Japanese audio with a single API call. Instead of hiring voice actors or editing studio recordings, your team sends text to our endpoint and receives a ready-to-use audio file, streamlining your localization workflow.
This process eliminates the need for complex infrastructure or specialized audio engineers. By integrating speech generation directly into your content pipeline, you can update product notifications or help articles and have audio versions available almost instantly.
Send text via our REST API
Use the standard POST endpoint to submit your text. The API accepts JSON bodies similar to the OpenAI speech format, making it easy to plug into your existing backend services without learning a new system.
Send up to 4,096 characters per request. If your content is longer, split it into parts and join the resulting audio files. The system handles the synthesis from text to sound efficiently.
- Simple JSON request structure
- Supports up to 4,096 characters per call
- Compatible with standard HTTP libraries
Receive audio in seconds
Once submitted, the API processes your request and returns an audio file. For short phrases, generation takes just a few seconds. Longer texts are processed sequentially, typically generating audio at roughly real-time speed.
You can choose from multiple formats like MP3, WAV, FLAC, or Opus to suit your playback needs. Failed requests are free, ensuring you only pay for successful audio generation.
- MP3, WAV, Opus, FLAC, PCM formats
- Fast generation for short texts
- Real-time speed for long texts
Integrate with your existing stack
PlayPW works with the official OpenAI SDKs by simply changing the base URL. This allows you to use familiar tools and libraries without rewriting your code from scratch.
Authentication is handled via a simple Bearer token. You can manage your API key and monitor usage directly from your account dashboard, keeping your development process smooth and transparent.
- OpenAI SDK compatible
- Standard Bearer token auth
- Easy dashboard integration
Supported Voices
Choose from eight distinct voice presets designed to match your brand’s tone. Our library includes four female voices—Aria, Nova, Luna, and Sage—and four male options: Felix, Milo, Atlas, and Orion. Each voice is based on licensed recordings, ensuring high-quality, natural-sounding speech for product descriptions and notifications.
Female voices: Aria, Nova, Luna, Sage
Aria offers a warm, clear narrator style ideal for product storytelling. Nova brings a bright, upbeat energy perfect for promotional content. Luna provides a soft, storytelling voice for help content, while Sage delivers a calm, instructional tone for detailed guides.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male voices: Felix, Milo, Atlas, Orion
Felix is energetic and great for promos. Milo offers a friendly, conversational style for customer support. Atlas provides a neutral, news-like tone, and Orion delivers a deep, documentary voice for long-form content. All voices are based on licensed recordings from LibriTTS-R and LibriVox.
Every generated audio file includes an inaudible watermark identifying it as synthetic speech, which helps maintain transparency with your end users.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
All voices speak all 23 supported languages
Each of the eight voices can speak any of our 23 supported languages. This allows you to maintain a consistent audio identity across your global store, regardless of the customer’s language. Simply set the language parameter or let the system guess it from the text script.
Languages We Support
PlayPW’s TTS engine supports Japanese, English, Chinese, and Korean, ensuring natural-sounding audio for your primary markets. Each voice can speak all 23 supported languages, so you can maintain consistent voice personalities across different regions without managing separate voice models.
Our coverage extends to major European languages like French, German, and Spanish, as well as high-demand markets including Arabic, Hindi, and Russian. If a language isn’t listed, it’s likely not supported, so check our docs for the full 23-language list before integrating.
Japanese, English, Chinese, Korean
Generate localized product descriptions and help content in these key Asian and Western markets. Since any voice can speak any supported language, you can assign your preferred voice—like Aria or Felix—to Japanese text without needing a dedicated Japanese-specific voice model.
European languages: French, German, Spanish
Expand your store’s reach in Europe with natural-sounding audio in French, German, and Spanish. The API handles complex phonemes and intonation patterns automatically, so your store copy sounds professional whether it’s a product notification or a detailed guide.
Other languages: Arabic, Hindi, Russian
Support growing markets with Arabic, Hindi, and Russian audio generation. These languages are fully supported across all eight voices, allowing you to scale your multilingual content strategy without hiring separate voice actors or managing multiple audio production pipelines.
Audio Formats
Choose the audio format that best fits your store’s performance and quality requirements. Our API supports MP3, WAV, Opus, and FLAC, giving you full control over file size and fidelity without needing external conversion tools.
Select MP3 for standard web playback, WAV for high-quality needs, or efficient formats like Opus and FLAC for archiving. Each format is generated instantly alongside your voice selection and speed settings.
MP3 for web playback
MP3 is the default choice for most e-commerce use cases. It offers a good balance between file size and audio quality, making it ideal for product descriptions, notification alerts, and help content played directly in browsers.
Most modern web players and mobile apps support MP3 natively, ensuring broad compatibility across devices without additional plugins or codecs.
- Small file size reduces bandwidth costs
- Universal browser and mobile support
- Ideal for dynamic content insertion
WAV for high-quality needs
Use WAV when you need uncompressed, high-fidelity audio. This format is perfect for premium product showcases or professional voiceovers where audio detail matters more than file size.
WAV files retain full audio data, ensuring no loss in quality during playback or further editing in your content management system.
- Uncompressed audio quality
- No loss during processing
- Best for professional editing workflows
FLAC and Opus for efficient storage
For large-scale libraries or frequent updates, FLAC and Opus offer excellent compression with minimal quality loss. FLAC is lossless, while Opus provides superior compression for streaming and storage.
These formats are ideal for storing thousands of product audio files without consuming excessive disk space or bandwidth, keeping your infrastructure costs low.
- FLAC: Lossless compression
- Opus: High efficiency for storage
- Ideal for large-scale archives

Pricing Overview
Our pricing model is straightforward: you pay only for what you use, calculated per character generated. The rate is $10 per 1 million characters, meaning every 1,000 characters cost just $0.01. Spaces and punctuation count toward this total, ensuring clear, predictable billing without hidden fees.
Pay per character generated
Failed requests are free, so you only pay for successful audio generation. There is no minimum spend or usage threshold to trigger charges.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Spaces and punctuation count as characters
- Failed requests are free
No monthly subscriptions
We do not require monthly plans, seats, or minimum commitments. Your balance does not expire, so you can top up when convenient and use it over any timeframe.
Transparent billing via crypto
Top-ups are processed via USDT on the TRON network (TRC-20) with a $5 minimum. Credits are added automatically within minutes, and no invoices or VAT are involved.
- USDT on TRON (TRC-20)
- $5 minimum top-up
- Automatic credit within minutes
Technical Specifications
Our API uses a standard endpoint compatible with existing OpenAI SDKs, allowing you to integrate TTS into your workflow by simply changing the base URL. This means you can leverage familiar development patterns without learning a new protocol.
Standard OpenAI-compatible endpoint
Send requests to POST https://api.playpwpw.com/v1/audio/speech using the same JSON structure as OpenAI. This compatibility ensures smooth integration with your current stack.
Support for speed and voice selection
Choose from eight distinct voices, such as Aria or Felix, to match your brand tone. Adjust speech speed between 0.25x and 4.0x to control pacing for product descriptions or notifications.
- 8 voice presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion
Simple JSON request format
Pass your text in the input field and specify the model (tts-1 or tts-1-hd). The response returns the audio file directly, ready for playback or storage.
Integration Guide
Integrate PlayPW into your product stack using any standard HTTP client. Send a POST request to https://api.playpwpw.com/v1/audio/speech with your text, voice selection, and language code in a simple JSON body. The API returns the audio file directly, fitting seamlessly into existing backend workflows.
For faster development, use the official OpenAI SDKs by pointing the base URL to our endpoint. This allows you to leverage familiar libraries while accessing our specific voice models and language support without writing custom serialization logic from scratch.
Use standard HTTP libraries
Any HTTP library works. Send a POST request to https://api.playpwpw.com/v1/audio/speech with a JSON body containing model, input, voice, and response_format. The API returns the audio file directly, fitting seamlessly into existing backend workflows.
- Supports MP3, WAV, Opus, FLAC, and PCM formats
- JSON body accepts up to 4096 characters per request
Compatible with OpenAI SDKs
Leverage existing code by changing the base_url to https://api.playpwpw.com/v1. The request shape matches the OpenAI speech endpoint, so you can use the official OpenAI SDKs without modification to generate speech for product descriptions.
- Works with Python, Node.js, and other SDKs
- Standard JSON request structure
Easy authentication with API keys
Include your API key in the request header as Authorization: Bearer tts-.... Generate your key instantly on the /get-api-key/ page. Each account has one active key, which can be rotated anytime if needed.
- Bearer token authentication
- One key per account
Get Started Today
Start with a free trial to test the API's capabilities without upfront costs. Create an account via Google or email to receive $0.50 in credit, valid for seven days.
Your account dashboard provides immediate access to your unique API key and usage metrics. You can generate keys instantly, allowing you to begin integration with your e-commerce platform right away.
Sign up for a free trial
Create an account on the get-api-key page using Google or an email password. This grants you $0.50 in trial credit, equivalent to approximately 50,000 characters, valid for seven days. Email-based accounts start without trial credit.
Use this credit to test voice generation for product descriptions or help content. You can top up later with USDT on the TRON network if you need more volume.
Get your API key instantly
Upon signing up, your dashboard displays your active API key immediately. You can issue a new key at any time, which stops the old one instantly. Use this key for authentication via the Authorization header.
The dashboard also shows your balance, characters remaining, and usage history. This transparency helps you monitor consumption against the rate limit of 60 requests per minute.
Start generating audio now
Send a POST request to the /v1/audio/speech endpoint with your text and selected voice. The API returns the audio file directly, allowing you to embed it in your store.
You can adjust speed and language parameters to match your needs. For longer texts, split the input into chunks under 4,096 characters and join the resulting audio files.
- Post text to the speech endpoint
- Receive audio in MP3, WAV, or other formats
- Embed directly into product pages or notifications
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Streamline your digital storefronts to boost conversion rates and delight every shopper with seamless experiences across all devices.
23 languages
Any voice speaks any of these languages.
