Frequently asked questions
What is the character limit for a single API request?
Each API request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For texts exceeding this length, you must split the content into multiple requests and join the resulting audio files. This ensures reliable processing within the standard endpoint constraints.
Which languages are supported for text to speech?
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and others are not supported.
Can the API handle long texts for language courses?
Yes. You can split long texts into parts of up to 4096 characters and join the resulting audio files. The API processes requests sequentially, so under load a request may wait in a queue. Typical generation speed is roughly real time, approximately 25 characters per second.
How is the API key authenticated in requests?
Authentication uses a Bearer token in the Authorization header. The format is Authorization: Bearer tts-.... Each account holds one active key. If you issue a new key, the old one stops immediately. Ensure your key is included in every request to the API endpoint.
What audio formats are available for output?
The API supports five output formats: mp3, wav, opus, flac, and pcm. You specify the desired format using the response_format field in the JSON body. This allows flexible integration with various language learning platforms and playback systems requiring specific audio codecs.
Does the API support speed adjustment for voice?
Yes, you can adjust the playback speed between 0.25 and 4.0. Use the speed parameter in your request to modify the generation rate. This feature allows you to create audio materials at varying difficulty levels for different stages of language learning courses.
Are failed requests charged to the account balance?
No. If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures that your account balance reflects only the usable audio files produced by your API calls, protecting your budget during integration testing.
How many voices are available in the preset library?
There are eight preset voices available. Four are female (aria, nova, luna, sage) and four are male (felix, milo, atlas, orion). Each voice has a distinct tone, such as warm, bright, soft, or calm, suitable for different educational contexts and learner preferences.
Is there a free trial for new API accounts?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test the API integration before committing to a top-up. The credit covers approximately 50,000 characters.
What payment methods are accepted for top-ups?
Top-ups are accepted via USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Credits are automatically added within minutes after transfer. We do not accept cards, PayPal, or subscriptions. There are no invoices or VAT charges for these transactions.
How long is input text retained 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 retain request metadata, such as time, characters, and status, strictly for billing purposes. No other data is kept.
Is synthetic speech watermarked in the audio files?
Yes, every generated file carries an inaudible watermark that marks it as synthetic speech. This applies to all audio outputs regardless of the voice or format used. The watermark is embedded within the audio data and is not audible to the listener.
What is the typical generation speed for text?
Generation speed is roughly real time on long texts, approximately 25 characters per second. Short phrases may take a few seconds to process. Requests are processed sequentially, so under load a request may wait in a queue. This ensures consistent processing order.
Can I use OpenAI SDKs with this API endpoint?
Yes, the request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.playvebet.com/v1 and using your site's key. This allows seamless integration into existing workflows without requiring custom client libraries or significant code changes.
First request
curl
curl https://api.playvebet.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.mp3API Architecture for Developers
The PlayVeBet API uses a standard OpenAI-compatible endpoint for text-to-speech synthesis. Developers send POST requests to https://api.playvebet.com/v1/audio/speech with a JSON body. The request shape mirrors the OpenAI speech endpoint, allowing direct use of official OpenAI SDKs by adjusting the base_url to https://api.playvebet.com/v1.
Audio generation occurs server-side. You receive the audio file directly in the response. This architecture ensures seamless integration into educational workflows without requiring custom protocol handling. The system handles the conversion from text input to audio output efficiently, supporting rapid iteration for language learning applications.
Standard OpenAI-Compatible Endpoint
The endpoint POST https://api.playvebet.com/v1/audio/speech accepts JSON payloads. It returns audio files in the specified format. This compatibility reduces integration time for developers already familiar with OpenAI’s speech infrastructure.
JSON Request Body Structure
Requests require a model field (tts-1 or tts-1-hd), an input string up to 4096 characters, a voice preset, and a response_format (mp3, wav, opus, flac, pcm). Optional fields include speed (0.25–4.0) and language (ISO code).
- Model: tts-1 or tts-1-hd
- Input: max 4096 characters
- Voice: 8 presets
- Format: mp3, wav, opus, flac, pcm
Real-Time Audio Generation
Audio is generated synchronously. The response contains the audio data directly. For longer texts, split the input into parts under 4096 characters, generate each segment, and join the files client-side.
Voice Selection for Educational Content
PlayVeBet provides eight distinct voice presets optimized for educational workflows, ensuring consistent audio quality across language learning applications. Voices are derived from licensed LibriTTS-R recordings, providing clear, synthetic speech suitable for instructional content.
Narrator and Instructor Presets
Use aria for warm, clear narration or luna for soft storytelling. For instructional modules, sage delivers a calm tone, while nova offers a bright, upbeat delivery for engaging exercises.
Neutral and Conversational Tones
Atlas provides a neutral, news-style voice ideal for objective content. Milo offers a friendly, conversational tone for dialogues, while orion suits documentary-style lessons, and felix adds energy to promotional or introductory segments.
Consistent Audio Quality
Each generated file carries an inaudible watermark marking it as synthetic speech.
Multilingual Support Scope
PlayVeBet’s TTS API supports 23 languages, enabling language learning startups to deploy synthetic speech across diverse educational workflows. The system ensures character-accurate audio generation, allowing developers to build consistent learning modules without managing multiple voice providers.
Accurate language handling is critical for pedagogical effectiveness. Our API combines automatic detection with explicit coding to maintain audio quality, ensuring that learners receive clear, intelligible speech regardless of the target language.
23 Supported Languages
The API supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice preset can generate audio in any of these languages, providing flexibility for curriculum design.
This range covers major global languages and several regional variants, allowing startups to target specific markets without additional integration overhead. Each language is processed with the same engine quality, ensuring consistent user experience.
- 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
When the language field is omitted, the API guesses the language from the input script. Latin script text defaults to English. This simplifies initial integration for English-heavy applications.
For non-English Latin-script text, automatic detection may fail. Developers should verify the output to ensure correct pronunciation and intonation for the intended language.
Explicit Language Coding
For non-English Latin-script text, set the language parameter to the ISO code to ensure correct synthesis. This prevents mispronunciation and maintains educational accuracy.
Explicit coding is essential for languages with unique scripts or where Latin text could be ambiguous. This ensures that the synthetic speech matches the intended linguistic context for learners.
Technical Specifications
PlayVeBet processes input text in chunks of up to 4,096 characters per request. Spaces and punctuation are counted as individual characters. For longer educational texts, developers must split the content into valid segments and join the resulting audio files sequentially to maintain continuity.
Character Limits per Request
Each API call accepts a maximum of 4,096 characters in the input field. Exceeding this limit results in a request error. Developers should implement client-side splitting logic to handle textbooks or lesson plans that exceed the single-request threshold.
- Maximum input length: 4,096 characters
- Spaces and punctuation count toward the limit
- Multiple short requests may queue behind longer ones
Audio Format Options
The API returns audio in five standard formats: mp3, wav, opus, flac, and pcm. Select the format based on your application’s bandwidth and playback requirements. MP3 offers efficient compression for web delivery, while WAV provides uncompressed quality for local processing.
- Supported formats: mp3, wav, opus, flac, pcm
Speed Adjustment Parameters
Adjust speech rate between 0.25x and 4.0x using the speed parameter. Slower speeds aid comprehension for language learners, while faster rates suit review sessions. The default speed is 1.0x. Changes apply globally to all voices and do not affect audio quality.
- Speed range: 0.25 to 4.0
- Applies to all selected voices
- No emotion or pitch customization
Integration Workflow
PlayVeBet’s API follows the standard OpenAI-compatible endpoint structure, allowing teams to integrate synthetic speech into language learning workflows using familiar patterns. Authentication relies on a single active Bearer token issued per account, which can be rotated instantly via the dashboard without service interruption.
Developers configure their HTTP clients by setting the base URL to https://api.playvebet.com/v1. This single configuration change enables compatibility with existing OpenAI SDKs, ensuring that standard request libraries function correctly without requiring custom wrappers or proprietary client implementations.
API Key Authentication
Each account receives one active API key displayed on the /get-api-key/ dashboard. Pass this key as an Authorization: Bearer <key> header in every request. If a new key is generated, the previous one becomes invalid immediately, ensuring strict access control without requiring manual revocation.
Base URL Configuration
Set your API base URL to https://api.playvebet.com/v1. This endpoint supports the same request shape as the OpenAI speech endpoint, including POST /v1/audio/speech. This alignment allows you to reuse existing HTTP client configurations and reduce integration overhead for engineering teams.
SDK Compatibility
The API is compatible with official OpenAI SDKs (e.g., Python, Node.js) by overriding the base_url parameter. This enables seamless adoption for startups already familiar with the OpenAI ecosystem, allowing rapid prototyping of audio generation features within language learning applications without learning a new SDK.
- Official OpenAI SDKs compatible via base URL override
- Standard JSON request body structure
- No proprietary client library required

Usage Metrics and Limits
PlayVeBet enforces a strict rate limit of 60 requests per minute per API key. New accounts begin with a lower threshold of 10 requests per minute until the first top-up is processed.
Rate Limiting Policy
Each active key is limited to 60 requests per minute. Before the initial top-up, this limit is reduced to 10 requests per minute to manage initial load.
Request Queue Processing
Requests are processed sequentially. Under high load, synthesis requests may wait in a queue before generation begins, which can increase latency for short phrases.
Character Counting Rules
Billing is calculated based on the total character count of the input text. This includes all spaces, punctuation marks, and special characters within the submitted string.
Pricing Model Overview
PlayVeBet utilizes a straightforward per-character billing model, charging $10 per 1 million characters ($0.01 per 1,000 characters). Spaces and punctuation are counted toward the total. This structure allows language learning startups to predict costs accurately based on text volume without complex tiered pricing.
Per-Character Billing
Billing is precise and transparent. Each character in your input text, including spaces and punctuation, contributes to the total count. Failed requests incur no charge, ensuring you only pay for successful audio synthesis.
Free Trial Allocation
Accounts signed in with Google receive a $0.50 trial credit, equivalent to approximately 50,000 characters, valid for seven days. Email-only accounts do not include this trial credit. The balance does not expire, allowing flexible usage timing.
Transparent Cost Structure
There are no monthly plans, seats, or minimum spending requirements. Top-ups are processed via USDT on the TRON network (TRC-20) with a $5 minimum. Credits are added automatically within minutes. No invoices with VAT are generated.
Data Handling and Privacy
Input text is processed solely to generate the requested audio file and is not used for training or model improvement. Generated audio is returned in the response and not stored on our servers, ensuring that your educational content remains transient unless you capture it.
Input Text Usage Policy
Your input text is used only to produce the audio and is not used for training.
Audio Storage Duration
Generated audio is returned in the response and not stored.
Billing Metadata Retention
Request metadata (time, characters, status) is kept for billing.
Support and Documentation
PlayVeBet provides technical assistance exclusively through email. There is no phone number, live chat, or on-site support team. Responses are provided by the engineering team directly, ensuring that queries regarding API behavior, integration issues, or billing discrepancies are handled by personnel with full context of the system architecture.
Comprehensive technical documentation is available at https://playvebet.com/docs/. This resource includes detailed reference material for the speech endpoint, voice lists, and authentication protocols. The documentation is updated to reflect the current API specification and serves as the primary reference for developers integrating the TTS service into language learning applications.
Email-Only Support Channel
Support requests are managed via email. This channel is the sole method for direct communication with the PlayVeBet team. We do not offer telephone support or real-time chat widgets. This approach allows for detailed, asynchronous troubleshooting of specific integration issues without the noise of concurrent conversations.
Email support is suitable for both technical queries and account-related questions. Since we do not maintain a support queue with tiered priority, all emails are processed in the order they are received. This ensures transparency in response times and allows developers to reference previous correspondence accurately.
- Single point of contact via email
- No phone or live chat options
- Asynchronous communication for detailed troubleshooting
Technical Documentation Access
The documentation site provides all necessary details for integration. It covers the JSON request structure, available voices, and supported audio formats. Developers can find code examples for the standard OpenAI-compatible endpoint and understand the rate limits and character counting rules essential for budgeting in language learning apps.
Each endpoint is described with its required fields and expected responses. The documentation also clarifies the behavior of the speed parameter and language detection. This ensures that developers can implement the API correctly without guessing parameters or assuming features that are not supported.
- Endpoint reference and request examples
- Voice and format specifications
- Rate limit and quota details
Issue Reporting Process
To report an issue, send an email with a clear description of the problem. Include the request timestamp, the voice used, and the specific error message or unexpected behavior. Providing the exact input text and the resulting audio file helps the engineering team reproduce the issue quickly.
We track request metadata for billing and debugging purposes. If you report an issue related to a specific request, reference the timestamp and the characters processed. This allows us to verify the status of the synthesis and determine if the request was charged correctly or if a failure occurred.
- Email with timestamp and error details
- Include input text and audio file
- Reference metadata for billing disputes
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Empower your global team with intuitive language learning tools that bridge cultural gaps and accelerate collaboration.
23 languages
Any voice speaks any of these languages.
