Frequently asked questions
Is the AI voice generator really free to start?
Yes. Signing in with Google provides $0.50 of free credit, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password start without this trial credit. After the trial or credit expires, you must top up your balance to continue generating audio files via the API.
How many characters can I send in one request?
Each request supports a maximum of 4096 characters in the input field. Spaces and punctuation count toward this limit. For longer texts, you must split the content into chunks of up to 4096 characters and join the resulting audio files. This ensures consistent processing and avoids request size errors.
Which voices are best for SaaS notifications?
For SaaS notifications, Atlas (neutral, news) and Sage (calm, instructional) are ideal for clear alerts. Felix (energetic, promo) works well for promotional updates. Milo (friendly, conversational) suits onboarding messages. All eight voices support 23 languages, allowing you to maintain a consistent brand tone across different regional user bases.
Do I need to install a specific SDK to use the API?
No. The API follows the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playa02.com/v1. Alternatively, you can send standard HTTP POST requests with a JSON body. No proprietary SDK installation is required.
How fast is the audio generation?
Generation speed is roughly real-time, 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. Longer texts are processed in parts, which may add slight latency.
Can I use the generated audio in my app without attribution?
The product facts do not specify attribution requirements for generated audio files. Voices are based on licensed recordings from LibriVox public-domain audiobook readings. However, every generated file carries an inaudible watermark marking it as synthetic speech.
What happens if the synthesis 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 the same text and parameters, or adjust settings like speed or voice if the error persists.
Do you support languages other than English?
Yes, we support 23 languages including Arabic, Chinese, French, German, Hindi, Japanese, Spanish, and more. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, defaulting to English for Latin text. Specify the ISO code for non-English Latin-script text.
Is there a limit to how many requests I can make per minute?
Yes, the rate limit is 60 requests per minute per API key. Before the first top-up, the limit is 10 requests per minute. If you exceed the limit, requests may be delayed or rejected. Monitor your usage via the dashboard to ensure smooth integration with your SaaS notification system.
How do I top up my balance using cryptocurrency?
Top-ups are accepted via USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Credits are automatically added to your balance within minutes after the transfer is confirmed. No other payment methods like cards or PayPal are supported. Balance does not expire once credited.
Can I clone my own voice for brand consistency?
No. We do not offer custom voice cloning for customers. You cannot upload your own voice or design a new voice. You must choose from the eight preset voices available in the API. Each voice is based on licensed recordings from LibriVox public-domain audiobook readings.
Do you offer SSML support for fine-tuning?
No. The API does not support SSML (Speech Synthesis Markup Language). You cannot use SSML tags to control pacing, pitch, or emphasis. You can adjust the speed using the speed parameter (0.25–4.0) and select different voices to achieve the desired tone for your notifications.
Is my input text stored after generation?
No. 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. Request metadata, including time, characters, and status, is kept for billing purposes. Your text content remains private and transient.
How do I contact support if I have an issue?
Support is available by email only. There is no phone number or live chat. You can find the support email address on the /contact/ page of playa02.com. Responses are provided via email, so allow for standard processing times for your inquiries.
First request
curl
curl https://api.playa02.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 SaaS Teams Choose API-First Audio
SaaS teams building notification systems require audio that integrates seamlessly with existing infrastructure. A unified API endpoint allows developers to attach synthetic voice output directly to user workflows without managing complex media servers or third-party dashboards.
Variable workloads demand flexible pricing. Unlike fixed monthly plans, our character-based model ensures you only pay for what you generate. This structure aligns costs directly with user activity, preventing waste during low-usage periods.
Unified Integration with Existing Stacks
Integrating text-to-speech into SaaS interfaces no longer requires custom middleware. Our API follows a standard request shape, allowing you to inject audio generation directly into your backend services. This reduces engineering overhead and keeps your architecture simple.
Cost Efficiency for Variable Workloads
Notification volumes fluctuate. A flat subscription fee often leads to overpaying for unused capacity or hitting strict limits during spikes. Our per-character pricing scales naturally with your user base, offering predictable costs without minimum spend requirements.
No Vendor Lock-In with Standard SDKs
By adhering to the OpenAI-compatible endpoint structure, you can use standard SDKs by simply changing the base URL. This prevents dependency on proprietary libraries and makes switching providers or updating versions straightforward for your engineering team.
Core Capabilities for Notification Systems
Playa Voice delivers reliable synthetic audio directly through a standard REST API, ensuring consistent quality for your in-app notifications. The system processes text inputs up to 4,096 characters, returning high-fidelity audio files that integrate seamlessly with your existing notification stacks without requiring custom middleware.
Our engine supports 23 languages, allowing you to reach global users with localized audio. Whether you need English, Spanish, or Arabic, the same API endpoint handles synthesis, ensuring a unified experience across diverse markets without managing separate voice providers.
Synthesis typically takes a few seconds for short phrases, with longer texts processing at roughly real-time speed. Under load, requests queue sequentially, maintaining stability. This predictable latency allows you to design user interfaces that feel responsive, even during peak notification bursts.
High-Quality Synthetic Audio Generation
The API generates clear, natural-sounding audio from text inputs up to 4,096 characters. Each request returns a direct audio file, eliminating the need for complex streaming infrastructure. The synthetic nature is marked by an inaudible watermark, ensuring transparency.
Audio formats include MP3, WAV, Opus, FLAC, and PCM, allowing you to choose the optimal balance between quality and bandwidth for your specific use case. Failed requests are free, ensuring you only pay for successful deliveries.
- Up to 4,096 characters per request
- Multiple output formats: MP3, WAV, Opus, FLAC, PCM
- Failed requests are free
Multi-Language Support for Global Users
Support covers 23 languages, including English, Spanish, French, Chinese, Japanese, and Arabic. Any voice can speak any supported language, providing flexibility in tone and style regardless of the target locale. The language can be explicitly set via ISO code or automatically guessed from the script.
This broad support allows SaaS teams to deploy localized notifications without integrating multiple voice providers. Consistent API behavior across languages simplifies testing and deployment workflows for international user bases.
- 23 supported languages
- Any voice can speak any supported language
- Automatic language detection or explicit ISO code setting
Fast Processing for Real-Time Feels
Short phrases typically take a few seconds to synthesize, 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.
This predictable processing time allows you to design interfaces that handle latency gracefully. The API’s rate limit of 60 requests per minute per key helps manage concurrency, ensuring consistent delivery speeds for your notification systems.
- Typical speed: ~25 characters per second for long texts
- Rate limit: 60 requests per minute
- Sequential processing ensures stability
Available Voices for Different Tones
Playa Voice offers eight distinct voice presets, each crafted for specific narrative or functional roles within SaaS interfaces. Whether you need a warm narrator for onboarding flows or a neutral announcer for system alerts, the library covers the tonal spectrum required for modern applications.
Narrative Voices: Aria and Luna
Aria delivers a warm, clear narration. Luna provides a soft, storytelling tone.
Conversational Voices: Milo and Felix
Milo offers a friendly, conversational style. Felix brings an energetic, promo-oriented tone.
Professional Voices: Atlas and Sage
Atlas projects a neutral, news-like clarity. Sage provides a calm, instructional tone.
Supported Languages and Scripts
SaaS applications serving global audiences require precise linguistic support. Our engine handles 23 distinct languages, ensuring that notification audio and in-app interfaces sound natural regardless of the user's region. The API detects language from the script by default, but you can explicitly set the ISO code for Latin-script texts to avoid ambiguity.
Latin Script Languages: English, Spanish, French
Beyond the primary Western languages, we support Dutch, Finnish, Greek, Malay, Norwegian, Polish, Portuguese, Swedish, and Turkish. This breadth allows SaaS teams to deploy localized notifications without managing separate voice assets for each region.
Asian Scripts: Chinese, Japanese, Korean
Support for CJK languages ensures accurate pronunciation and tone for East Asian markets. These voices are optimized for clarity in both notification alerts and longer instructional content within the application.
Other Supported Languages: Arabic, Hindi, Russian
We also cover Arabic, Danish, German, Hebrew, Hindi, Italian, Russian, and additional variants. Every voice can speak any of the 23 supported languages, providing a consistent audio experience across your entire user base without requiring language-specific voice selection.
Audio Formats and Delivery
The API returns audio in five standardized formats, allowing SaaS teams to optimize bandwidth and compatibility without custom encoding pipelines. Each format serves a distinct use case within notification systems, from lightweight push notifications to high-fidelity in-app player experiences.
You select the desired output via the response_format parameter. The service handles the encoding, ensuring consistent quality whether you need small payloads for mobile data or lossless files for archival.
Audio files are delivered directly in the HTTP response body, eliminating the need for asynchronous polling or storage management for transient notifications.
MP3 for Web Compatibility
MP3 is a common choice for web-based interfaces and mobile apps. It offers a balance between file size and quality, ensuring rapid playback across all major browsers and devices without requiring additional codec support.
This format is ideal for standard in-app notifications where user experience depends on quick loading times and broad device compatibility.
- Universal browser support
- Optimal size-to-quality ratio
- Default format for most use cases
WAV for High Fidelity
WAV provides uncompressed, lossless audio suitable for professional voiceovers or archival purposes. It preserves the full dynamic range of the generated speech without data loss.
Use this format when audio quality is prioritized over bandwidth, such as in premium notification tiers or when the audio will be further processed.
- Lossless quality
- No compression artifacts
- Ideal for archival or processing
Opus and FLAC for Efficiency
Opus offers high-quality audio at lower bitrates than MP3, making it excellent for data-constrained environments. FLAC provides lossless compression, reducing file size while retaining 100% of the audio data.
Both formats are efficient for storage-heavy applications or when transmitting large volumes of audio notifications over limited bandwidth networks.
- Opus: Low bitrate, high quality
- FLAC: Lossless compression
- Reduced bandwidth usage
Pricing Model Overview
Playa Voice eliminates monthly subscription overhead by charging strictly on consumption. At $0.01 per 1,000 characters, costs scale linearly with your notification volume, making it ideal for variable SaaS workloads.
Pay Per Character Usage
Billing is calculated at $10 per 1 million characters, including spaces and punctuation. Failed requests incur no charge, ensuring you only pay for successful audio generation.
Free Trial Credit for Testing
Google sign-ups receive $0.50 in trial credit (approximately 50,000 characters) valid for seven days. Email-based accounts start with zero balance, allowing immediate testing of the API.
Transparent USDT Top-Up
Funds are added via USDT on the TRON network (TRC-20) with a $5 minimum. Credits are available within minutes of transfer, with no VAT, invoices, or subscription locks.
Technical Reliability and Limits
Playa Voice handles variable traffic with clear boundaries. Each API key allows 60 requests per minute, rising from an initial 10 per minute before your first top-up. Requests process sequentially, meaning high-volume bursts may enter a queue, but typical generation speed remains roughly real-time.
Rate Limits and Queue Management
Requests are processed one after another, so under load a request may wait in a queue. This linear processing ensures consistent delivery without complex concurrency overhead, allowing your notification system to scale predictably without managing individual connection states.
- Standard limit: 60 requests per minute per key.
- Initial limit: 10 requests per minute before first top-up.
- Sequential processing may cause brief queuing during peaks.
Input Text Character Constraints
Each API call accepts up to 4,096 characters. For longer notifications, split the text into chunks and join the resulting audio files. Spaces and punctuation count toward this limit, so plan your message length accordingly to avoid truncation.
Error Handling and Retry Logic
If synthesis fails, the charge is returned in full, ensuring you only pay for successful outputs. Your retry logic should handle standard HTTP errors gracefully; since audio is generated sequentially, rapid retries may temporarily hit the rate limit.
Data Privacy and Usage
When your application sends text to the TTS endpoint, that input is processed solely to generate the audio response. It is not ingested into any training dataset to improve our underlying models, ensuring your user data remains distinct from our core engine development.
The synthesized audio files are delivered directly in the HTTP response and are not stored on our servers after delivery. This minimizes data retention risks, as we hold no long-term copies of the generated voice outputs.
We retain request metadata—such as timestamps, character counts, and status codes—strictly for billing and usage verification. This limited data allows us to accurately calculate charges and troubleshoot issues without retaining the actual content of your notifications.
Input Text Not Used for Training
Your input text is used exclusively to produce the immediate audio output. It is not added to our training corpus, meaning your specific user notifications do not influence future model improvements.
No Long-Term Storage of Audio
Generated audio files are returned in the response stream and are not archived on our infrastructure. Once the audio is delivered to your client, we hold no copy of the synthetic speech.
Billing Metadata Retention
We keep minimal metadata including request time, character length, and status for billing accuracy. This data is used only to verify charges and does not include the content of your text or audio.
Getting Started with the API
To begin, visit https://playa02.com/get-api-key/ and sign in using Google or create an account with an email and password. This step establishes your independent storefront identity, allowing you to manage billing and access the dashboard.
Create an Account via Google or Email
Google sign-ups receive a $0.50 free trial valid for seven days, equivalent to roughly 50,000 characters. Email-based accounts start without initial credit, requiring a USDT top-up to begin usage. This distinction ensures immediate testing capability for most developers.
Generate Your API Key Instantly
The dashboard displays your active API key, current balance, and usage statistics. You can issue a new key at any time, which immediately invalidates the previous one, ensuring tight security control without complex rotation procedures.
Run Your First Synthesis Request
Use the standard OpenAI SDK by setting the base URL to https://api.playa02.com/v1. Send a POST request to /v1/audio/speech with your text and desired voice preset. The system returns the audio file directly, ready for integration into your notification system.
- Base URL: https://api.playa02.com/v1
- Endpoint: POST /v1/audio/speech
- Auth: Bearer tts-... key
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This simplicity allows engineering teams to forecast costs accurately as user bases grow, without renegotiating contracts or managing seat counts.
23 languages
Any voice speaks any of these languages.
