Frequently asked questions
Is the Speechify app the same as this API?
No. This is a cloud text-to-speech API endpoint, not a consumer application. You send JSON requests to receive audio files. It is designed for developers to integrate directly into mobile apps or backend services, whereas Speechify is a standalone end-user application.
Can I use the OpenAI SDK with this API?
Yes. The request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.playbe99.com/v1 and providing your site-specific key. This ensures SDK compatibility without requiring custom integration code.
How many languages are supported?
The API supports 23 languages, including English, Spanish, German, French, Japanese, and Arabic. Any voice can speak any of these languages. If the language parameter is omitted, the system guesses the language from the script, defaulting to English for Latin text.
What happens if a request fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures you do not pay for wasted compute resources when the API encounters an error during processing.
Are there monthly subscriptions?
No. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you generate at $0.01 per 1,000 characters. Balance does not expire, and you can top up via USDT (TRC-20) whenever needed.
Do I need to pay for USDT to start?
No. You can start with a free trial of $0.50 credit (approx. 50,000 characters) valid for 7 days when signing in with Google. USDT (TRC-20) is required only for subsequent top-ups, which have a minimum of $5.
Is the free trial available for all accounts?
No. The $0.50 trial credit is given only when you sign in with Google. Accounts created using an email and password start without any trial credit. You must add funds via USDT to begin using the API in those cases.
Can I clone my own voice?
No. Custom voice cloning is not offered. You must choose from the eight available presets (e.g., Aria, Nova, Felix, Atlas). These voices are based on licensed recordings from LibriTTS-R and LibriVox, ensuring clear licensing for commercial use.
Does the API support SSML?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control pacing and tone primarily through the speed parameter (0.25–4.0) and by selecting one of the eight predefined voice presets for your text-to-speech generation.
How is the audio quality?
Audio is generated using two models: tts-1 and tts-1-hd. Both use the same engine and price. The output is synthetic speech with an inaudible watermark. Quality is consistent across all eight voice presets, designed for clear narration and conversational tones.
What is the character limit per request?
Each request accepts up to 4096 characters of input text. For longer texts, you must split the content into parts of this size and join the resulting audio files. Spaces and punctuation count toward the character limit.
Can I use the audio commercially?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. Input text is not used for training, and generated audio is not stored, making it suitable for integration into commercial mobile applications.
How do I check my balance?
Visit the /get-api-key/ page after signing in. The dashboard displays your current balance, trial status, characters remaining, and usage history. You can also issue a new API key at any time, which immediately invalidates the previous one.
Is there a mobile SDK available?
No. There is no official mobile SDK or browser extension. You should use the OpenAI SDK or standard HTTP requests. The API is designed to be integrated directly into your iOS or Android app code using standard networking libraries.
First request
curl
curl https://api.playbe99.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 Freelancers Are Switching from Speechify App
Freelance mobile developers often find Speechify App’s subscription model restrictive for scaling. Our cloud TTS API charges $10 per million characters, with no monthly fees, allowing precise budget control for high-volume audio generation in iOS and Android apps.
Unlike proprietary ecosystems, our API maintains strict OpenAI SDK compatibility. By simply adjusting the base URL, developers can integrate TTS without vendor lock-in, leveraging familiar tools like the official OpenAI SDKs for seamless deployment.
Cost Efficiency for High-Volume Mobile Apps
With character-based billing at $0.01 per 1,000 characters, costs scale directly with usage. This model suits apps with variable traffic, avoiding the waste of fixed monthly plans when user activity fluctuates.
SDK Compatibility Without Vendor Lock-in
Our endpoint mirrors the OpenAI speech structure, allowing immediate integration using existing codebases. This reduces engineering overhead, as developers can swap the base URL to https://api.playbe99.com/v1 and use standard authentication headers.
Transparent Licensing for Audiobook Content
Voices derive from LibriTTS-R and LibriVox public-domain readings, offering clear licensing for commercial audiobook projects. Each generated file includes an inaudible watermark, ensuring synthetic origin is detectable without complicating content distribution.
Core API Capabilities for Mobile Integration
Freelance mobile developers can integrate our text-to-speech API using the official OpenAI SDKs with a simple base URL adjustment. By pointing the client to https://api.playbe99.com/v1, you maintain existing code structures while accessing our engine. This approach minimizes refactoring effort for iOS and Android applications, ensuring rapid deployment without requiring a custom HTTP client implementation for basic synthesis tasks.
OpenAI SDK Compatibility with Base URL Change
Integration requires only updating the base_url to https://api.playbe99.com/v1. The request shape mirrors the standard OpenAI speech endpoint, allowing immediate use with existing SDKs. This compatibility reduces development time for freelancers evaluating alternative TTS providers for their mobile apps.
8 Voice Presets for Diverse Narratives
Select from eight licensed voice presets tailored for different narrative styles. Female voices include Aria (warm narrator), Nova (upbeat), Luna (storytelling), and Sage (instructional). Male options feature Felix (energetic promo), Milo (conversational), Atlas (news), and Orion (documentary). These presets cover the primary requirements for audiobook and educational app content.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Support for 23 Languages Including Latin and Cyrillic
The API supports 23 languages, covering Latin and Cyrillic scripts. If the language field is omitted, the system guesses the language, defaulting to English for Latin text. For non-English Latin scripts, explicitly setting the language parameter ensures accurate synthesis. Supported languages include Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
Technical Specifications for Mobile Engineers
The API enforces a strict rate limit of 60 requests per minute per key, scaling from 10 per minute for new accounts until the first top-up. Long texts must be split into chunks of up to 4096 characters and joined client-side. Requests are processed sequentially; under load, synthesis may queue, with generation speed averaging roughly real-time (25 characters per second).
Request Limits and Rate Throttling Strategies
Implement exponential backoff to handle queue delays efficiently. Split input text into 4096-character segments to ensure consistent processing times and avoid timeout errors during high-volume audiobook generation.
Audio Format Options: MP3, WAV, Opus, FLAC, PCM
Select response_format from mp3, wav, opus, flac, or pcm. Opus and MP3 provide optimal file sizes for mobile data usage, while FLAC offers lossless quality for archival needs. PCM is available for raw audio pipelines.
Character Count Billing: 1 Million Characters Per $10
Billing occurs at $10 per 1 million characters, including spaces and punctuation. Failed requests incur no charge, ensuring cost efficiency for trial integrations. This linear pricing model simplifies budget forecasting for freelance mobile projects without hidden tier fees.
Voice Library and Licensing Model
Voxera’s voice library is built on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This foundation ensures transparent licensing for mobile apps distributing audio content, avoiding complex royalty negotiations. The eight voice presets—four female and four male—cover diverse narrative needs without requiring additional legal clearance.
LibriTTS-R and LibriVox Public Domain Sources
The underlying recordings come from CC BY 4.0 datasets and public-domain sources. This structure simplifies compliance for freelance developers building commercial iOS or Android applications, as the base audio assets do not carry restrictive per-user fees beyond the API usage cost.
- LibriTTS-R (CC BY 4.0) recordings
- LibriVox public-domain audiobook readings
- Transparent licensing for commercial mobile apps
Inaudible Watermarking for Synthetic Detection
Every generated audio file includes an inaudible watermark identifying it as synthetic speech. This feature aids in content verification for users and publishers, providing a technical marker that distinguishes API-generated narration from human-recorded audio without affecting playback quality.
No Custom Voice Cloning or Emotion Tags
The service does not offer custom voice cloning, emotion tags, or phoneme dictionaries. Developers must work with the eight fixed presets. This limitation reduces complexity and ensures consistent voice quality across all requests, which is preferable for predictable mobile app behavior.
- No custom voice cloning
- No emotion tags
- No phoneme dictionaries
Comparison with Amazon Polly Service
For mobile developers evaluating TTS infrastructure, Amazon Polly’s tiered pricing structure often introduces complexity compared to our straightforward $10 per million character model. Polly’s costs vary by voice selection and volume tiers, requiring careful monitoring of usage spikes in high-frequency mobile contexts.
Our flat-rate billing simplifies budget forecasting for freelance iOS and Android projects. You pay exactly $0.01 per 1,000 characters, regardless of voice complexity or request volume, eliminating the need to track tier thresholds or negotiate enterprise contracts for scaling.
Price Per Character vs. Usage Tier Pricing
Polly charges based on specific voice tiers (Neural vs. Standard) and usage volume brackets, which can obscure total costs during peak app usage. Our model charges uniformly per character, ensuring predictable expenses for audiobook chapters or accessibility features without tier penalties.
SDK Flexibility: OpenAI vs. AWS Native
Amazon Polly requires integrating AWS SDKs or using REST APIs specific to AWS infrastructure, potentially increasing bundle size for lightweight mobile apps. Our API mirrors the OpenAI speech endpoint, allowing you to use existing OpenAI SDKs by simply adjusting the base_url to our API endpoint.
This compatibility reduces boilerplate code and leverages familiar authentication patterns, streamlining integration for developers already accustomed to OpenAI-style API structures in their mobile environments.
SSML Support Differences in Mobile Contexts
Amazon Polly offers SSML support for fine-grained control over pauses, pitch, and prosody, which is valuable for complex audio scripts. Our API currently does not support SSML, focusing instead on straightforward text-to-audio conversion for rapid deployment.
For most mobile use cases like e-reading or educational narration, the eight preset voices provide sufficient expressive range without the overhead of parsing SSML tags in the client app.

Pricing Structure for Freelance Budgets
The pricing model eliminates recurring commitments, charging only for actual usage at $10 per 1 million characters. This structure allows freelance mobile developers to allocate precise budget amounts without managing subscriptions or seats, making it ideal for variable project workloads.
No Monthly Plans or Minimum Spend Requirements
There are no monthly plans, seats, or minimum spend requirements. You pay strictly for the characters processed, ensuring costs align directly with app usage patterns without idle fees.
USDT TRC-20 Top-Up for Instant Access
Top-ups are processed via USDT on the TRON network (TRC-20) with a $5 minimum. Credits are added automatically within minutes, providing immediate access without waiting for bank transfers or credit card approvals.
Failed Requests Are Free of Charge
If synthesis fails, the charge is returned in full. This ensures you only pay for successful audio generation, reducing financial risk during API integration and testing phases.
Data Privacy and Usage for Mobile Apps
The API processes input text exclusively for synthesis, ensuring your app’s content remains proprietary. Generated audio is returned in the response and not persisted on our servers, minimizing data retention risks for sensitive user information.
Input Text Not Used for Training Models
Text submitted via POST requests is used solely to generate the corresponding audio file. It is not ingested into our model training pipeline, preserving the exclusivity of your narrative data for commercial use.
Generated Audio Not Stored on Servers
Audio files are returned directly in the HTTP response and are not archived on our infrastructure. This ensures that your generated voice assets remain ephemeral unless your mobile app explicitly caches them locally.
Request Metadata Kept Only for Billing
We retain only request metadata—timestamp, character count, and status—to calculate accurate charges based on your usage. This minimal logging supports transparent billing without storing the actual content of your text or audio.
Getting Started with the API
Voxera provides a streamlined onboarding process for freelance mobile developers. Access the /get-api-key/ endpoint on playbe99.com to generate your authentication credentials using either Google authentication or a standard email and password combination.
Sign Up with Google or Email for API Key
Accounts are created per site, ensuring isolated billing and usage tracking. Upon registration, the dashboard displays your active API key, current balance, and a ready-to-use cURL example for immediate integration testing.
Free Trial Credit for Initial Testing
Signing in with Google grants $0.50 of trial credit, sufficient for approximately 50,000 characters. This credit is valid for seven days. Accounts created via email/password start without trial credit and require a top-up to begin synthesis.
Documentation for Quick Integration
The /docs/ page outlines the request shape, compatible with the official OpenAI SDK by simply changing the base_url to https://api.playbe99.com/v1. Engineers can verify voice options and rate limits (60 requests per minute) before committing to production deployments.
Common Use Cases in Mobile Development
Freelance mobile developers increasingly integrate text-to-speech APIs to enhance user engagement without heavy infrastructure costs. By offloading audio synthesis to a cloud endpoint, apps can support high-volume content delivery while maintaining strict budget control through character-based billing.
Audiobook Chapters for E-Reading Apps
Mobile readers can convert entire books into audio by splitting texts into 4096-character segments. This approach avoids vendor lock-in, allowing developers to switch providers if pricing or quality shifts. The API handles synchronization seamlessly, returning standard audio formats compatible with any native player.
- Support for 23 languages including Arabic, Chinese, and Russian
- Automatic splitting for long-form content exceeding 4096 characters
- No storage of generated audio, reducing server overhead
Accessibility Features for Visually Impaired Users
Apps serving visually impaired users benefit from consistent, high-quality narration across diverse content types. With voices like Aria or Atlas, developers can provide clear, instructional, or narrative tones. The absence of custom cloning ensures predictable output, while the inaudible watermark confirms synthetic origin for compliance.
- 8 distinct voice presets for varied tones
- ISO language code support for precise pronunciation
- Real-time generation speed approximating natural speech
Voice Narration for Educational Content
Educational platforms can generate lesson narrations on demand, reducing the need for pre-recorded studio sessions. Developers can adjust speed between 0.25x and 4.0x to accommodate different learning paces. Since input text is not used for training, student data remains private, and billing is strictly per character.
- Flexible speed settings from 0.25 to 4.0
- Support for Opus and FLAC formats for quality
- Transparent billing at $0.01 per 1000 characters
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Create intuitive mobile applications that empower freelancers to work efficiently from anywhere in the world.
23 languages
Any voice speaks any of these languages.
