Frequently asked questions
Is the AI voice generator truly free?
Google sign-ups receive a $0.50 trial credit valid for 7 days, covering approximately 50,000 characters. Standard accounts start with zero balance. After the trial, usage costs $0.01 per 1,000 characters. Failed requests are free, and your balance never expires.
Which voices are best for banking alerts?
For clear, compliant alerts, we recommend aria (warm narrator), sage (calm instructor), or atlas (neutral news). These voices provide professional clarity. You can also use felix for energetic promos or milo for friendly conversations. All eight presets support any of our 23 languages.
How many languages does the API support?
We support 23 languages, including English, Spanish, German, French, Japanese, and Hindi. Any voice can speak any supported language. If you do not specify a language, the system guesses it from the script, defaulting to English for Latin text.
What is the character limit per request?
Each API request accepts up to 4,096 characters of input text. For longer texts, you must split the content into chunks of this size and join the resulting audio files. Spaces and punctuation count toward the character total.
Can I use the OpenAI SDK with this API?
Yes. Our endpoint matches the OpenAI speech request shape. You can use official OpenAI SDKs by changing the base_url to https://api.playa71.com/v1 and providing your VerbaClear API key. This works seamlessly with standard HTTP clients as well.
How do I top up my account balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum deposit is $5. Credits are added automatically within minutes of transfer. We do not accept cards, PayPal, or subscriptions. No invoices or VAT are involved.
Is my input text used for training?
No. Your input text is used solely to produce the audio response and is not used for training models. Generated audio is returned in the response and not stored. We retain request metadata like time and status only for billing.
Do you offer SSML support?
No, we do not offer SSML support. Our API uses simple text input with optional speed and language parameters. We also do not provide phoneme dictionaries, custom pronunciation lexicons, or emotion tags. Keep your input plain text for best results.
What happens if a 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 or adjust parameters like speed or voice.
Is there a minimum spend requirement?
No, there is no minimum spend requirement. You pay only for what you use at $0.01 per 1,000 characters. There are no monthly plans, seats, or mandatory subscriptions. Your balance does not expire, so you can use it whenever needed.
Can I clone my own voice?
No, we do not offer custom voice cloning. You cannot upload your own voice or design a new one. We provide eight preset voices based on licensed recordings. Each generated file includes an inaudible watermark marking it as synthetic speech.
Do you provide an SLA guarantee?
No, we do not provide an SLA or uptime guarantee. We are an independent API without enterprise contracts or certifications like SOC 2 or HIPAA. Support is available via email only. We focus on reliability and cost-efficiency for high-volume systems.
How long does audio generation take?
Generation is roughly real-time on long texts, processing about 25 characters per second. Short phrases take a few seconds. Requests are processed sequentially, so under load, your request may wait in a queue. Rate limits apply at 60 requests per minute.
What audio formats are available?
We support mp3, wav, opus, flac, and pcm formats. You can specify your preferred format in the request body. These options allow you to balance file size and quality according to your fintech notification system's requirements.
First request
curl
curl https://api.playa71.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.mp3Voice Notifications for Fintech
VerbaClear provides a reliable text-to-speech API designed specifically for fintech product teams who need to deliver clear, compliant, and human-sounding voice alerts. By integrating our straightforward API, you can transform transactional data into engaging audio notifications that keep users informed and engaged.
Clear transaction alerts
Send voice notifications for payments, login attempts, or balance changes via a simple POST request. The API processes requests sequentially, so under load a request may wait in a queue. This ensures consistent delivery of critical alerts without overwhelming your users with simultaneous audio bursts, maintaining a calm user experience during high-volume events.
Compliant voice messages
Generate professional audio that meets regulatory standards for clarity and intelligibility. Our voices are based on licensed recordings from LibriVox public-domain audiobook readings, providing a legally sound foundation for your financial communications. Each generated file carries an inaudible watermark, clearly marking it as synthetic speech to maintain transparency with your end-users.
Global user support
Support your diverse user base with 23 languages, including English, Spanish, German, French, and Chinese. Voices can speak any supported language, ensuring consistent quality across markets. If the language is not explicitly set, it is guessed from the script, but you can override this for non-English Latin-script text to ensure accurate pronunciation.
Why Fintech Teams Choose Us
VerbaClear’s API aligns with fintech workflows, allowing product teams to inject voice alerts directly into transaction flows. By using standard HTTP requests compatible with OpenAI SDKs, integration takes hours, not weeks. This reliability ensures your notification system scales smoothly during high-volume periods without complex infrastructure changes.
Simple API integration
Send text via a single POST request and receive audio. Generation takes roughly real-time for long texts (about 25 characters per second), and requests are processed sequentially, so under load a request may wait in a queue. The endpoint accepts standard parameters, meaning your existing codebases can adapt quickly. Whether triggering fraud alerts or balance notifications, the process remains consistent and predictable.
- Standard JSON body format
- Compatible with OpenAI SDKs
- Easy curl or HTTP integration
Transparent pricing
Costs are calculated per character, starting at $0.01 per 1,000 characters. Failed requests incur no charge, protecting your budget during testing. This model ensures you only pay for successful audio generation, providing clear visibility into your API spend.
No hidden fees
There are no monthly subscriptions, seat limits, or minimum spends. You top up via USDT on TRON, and the balance never expires. This straightforward structure eliminates surprise costs, making it ideal for variable-volume fintech notification systems.
Our TTS API Capabilities
VerbaClear provides a robust text-to-speech API designed for high-volume fintech notifications. Send plain text via a simple POST request and receive synthesized audio. Generation takes roughly real-time for long texts, and requests are processed sequentially, so under load a request may wait in a queue.
Text-to-speech endpoint
Interact with the standard endpoint at https://api.playa71.com/v1/audio/speech. The API accepts JSON bodies with up to 4096 characters per request, returning audio files in formats like MP3, WAV, or FLAC. Failed requests incur no charge.
8 professional voices
Choose from eight distinct voice presets tailored for different notification contexts. Options range from Aria’s warm narration to Felix’s energetic promo style, ensuring your alerts sound human and engaging.
23 supported languages
Support your global user base with voices covering 23 languages, including English, Spanish, German, Japanese, and Hindi. Any voice can speak any supported language, with automatic detection or explicit language codes.
Voice Library Overview
Our voice library provides eight distinct presets designed for clarity and reliability in fintech communications. Each voice is derived from licensed recordings, ensuring professional quality for transaction alerts and account notifications.
The selection balances warmth and authority, allowing product teams to choose the perfect tone for their specific user base without complex configuration.
Female voices: Aria, Nova
Aria offers a warm, clear narrator style ideal for standard transaction confirmations. Nova brings a bright, upbeat energy suitable for promotional updates or quick balance checks.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
Female voices: Luna, Sage
Luna provides a soft, storytelling tone for detailed explanations or onboarding flows. Sage delivers a calm, instructional voice perfect for step-by-step verification processes.
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male voices: Felix, Milo
Felix is energetic and promo-focused, while Milo offers a friendly, conversational style for customer support or routine alerts.
- Felix: Energetic, promo
- Milo: Friendly, conversational
Technical Specifications
VerbaClear offers two model variants, "tts-1" and "tts-1-hd," which utilize the same engine and pricing. This ensures consistent audio quality and predictable costs for your fintech notification infrastructure without requiring code changes between standard and high-definition outputs.
Standard and HD models
Both models deliver reliable voice synthesis for transaction alerts. You can select the appropriate model based on your specific quality requirements while maintaining a unified billing structure.
Multiple audio formats
Generate audio in mp3, wav, opus, flac, or pcm formats. This flexibility allows seamless integration with various playback systems and compliance storage requirements.
Adjustable speech speed
Control delivery tempo between 0.25x and 4.0x speed. This feature ensures clear audibility for critical financial alerts across different user demographics and device types.

Supported Languages
VerbaClear supports 23 languages, ensuring your fintech notifications reach a truly global audience. The API handles language detection automatically for Latin-script text, defaulting to English, but you can explicitly set the language field for precise control over non-English Latin inputs like German, French, or Spanish.
English and European languages
Core European markets are fully supported, including English, German, French, Spanish, Italian, Portuguese, Dutch, and Polish. We also cover Nordic and Eastern European regions with Danish, Finnish, Norwegian, Swedish, Russian, and Greek. This breadth ensures compliant, clear audio alerts for users across major financial hubs without needing separate voice models.
- English, German, French, Spanish, Italian, Portuguese, Dutch, Polish
- Danish, Finnish, Norwegian, Swedish, Russian, Greek
Asian languages support
Expand your reach into high-growth Asian markets with dedicated support for Chinese, Japanese, Korean, and Hindi. These languages handle complex phonetic structures effectively, delivering natural-sounding transaction alerts that resonate with local users. Explicitly setting the language code is recommended for these scripts to ensure accurate synthesis.
- Chinese, Japanese, Korean, Hindi
Other global languages
Beyond the major regions, we support Arabic, Malay, Turkish, and Swahili. This allows fintech products to serve diverse user bases in the Middle East, Southeast Asia, and parts of Africa. Note that languages like Vietnamese, Indonesian, Thai, Ukrainian, and Romanian are not currently supported, so verify your target audience's language needs before integrating.
- Arabic, Malay, Turkish, Swahili
Pricing and Trials
VerbaClear offers a transparent, usage-based pricing model designed for fintech teams managing high-volume voice notifications. You pay only for what you process, with no monthly subscriptions, seats, or hidden fees. Failed requests are free, ensuring you never pay for errors in your critical alert pipelines.
Free trial credit
Sign up with Google to receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters to test voice quality and integration before committing to larger volumes. Email-based accounts start without trial credit.
Pay-per-character model
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. There is no minimum spend, and balances do not expire, allowing you to scale usage according to your notification needs.
USDT top-up option
Top up your account using USDT on the TRON network (TRC-20). The minimum deposit is $5, and funds are credited automatically within minutes of transfer. We do not support credit cards, PayPal, or traditional invoicing.
Integration Guide
VerbaClear’s API mirrors the OpenAI speech endpoint structure, allowing fintech teams to swap providers without rewriting core logic. By updating the base_url to https://api.playa71.com/v1, you can use official OpenAI SDKs directly. This compatibility ensures a smooth transition for existing infrastructure, minimizing development time for your notification systems.
For teams preferring direct HTTP calls, the standard POST endpoint accepts JSON bodies with model, input, voice, and response_format fields. This flexibility supports both SDK-driven and custom-built integrations, ensuring reliable delivery of voice alerts to your users regardless of your tech stack.
OpenAI SDK compatibility
Configure your SDK client with base_url=https://api.playa71.com/v1 and use your VerbaClear API key in the Authorization header. This setup leverages familiar OpenAI client methods, enabling rapid integration into your fintech apps with minimal code changes.
The SDK handles JSON serialization automatically, passing your text input and voice selection parameters directly to our synthesis engine. This reduces boilerplate code and accelerates deployment cycles for your product teams.
- Uses OpenAI SDKs (Python, Node, etc.)
- Simply change base_url
- Standard Authorization header format
Standard HTTP requests
Send a POST request to https://api.playa71.com/v1/audio/speech with a JSON body containing model, input, voice, and response_format. The endpoint returns the audio file directly in the response body, ready for immediate playback or storage in your notification pipeline.
Ensure your input text does not exceed 4096 characters. For longer messages, split the text into chunks of up to 4096 characters in your application logic, generate audio for each part, and concatenate the results before delivery to the user.
- Endpoint: POST /v1/audio/speech
- JSON body required
- Returns audio file directly
Quick start examples
Use the provided curl example on the /get-api-key/ page to test your integration immediately. Replace YOUR_API_KEY with your active key and send a short test string to verify audio generation and format selection.
For Python users, initialize the OpenAI client with our base URL and call client.audio.speech.create(). This single function call handles authentication, request formatting, and response handling, returning the audio bytes for your notification system. Note that the OpenAI SDKs do not natively support the speed or language parameters used by this API, so you may need to pass them as extra fields or use plain HTTP for full parameter support.
- Test with curl command
- Python SDK setup in 3 lines
- Verify audio output format
Data Privacy and Security
VerbaClear processes your input text strictly for the purpose of generating audio. We do not use your input text for training our models or improving our services. Your voice data remains yours.
Input text usage policy
Your text is sent to our API, converted into speech, and returned to you in the response. Generated audio is returned in the response and not stored on our servers.
Audio storage details
Generated audio is returned in the response and not stored on our servers. This means the audio is not stored on our servers after the response is sent.
Billing metadata retention
We keep request metadata, including time, character count, and status, solely for billing purposes. This ensures accurate invoicing based on the $0.01 per 1,000 characters model. Request metadata (time, characters, status) is kept for billing.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice maintains a consistent tonal character—such as upbeat, calm, or deep—throughout the generation.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriTTS-R paper (arXiv 2305.18802)
- W3C WAI: making audio and video accessible
- Creative Commons Attribution 4.0
- openai-node on GitHub
- TRON developer hub: TRC-20
- OpenAI API reference: create speech
- ISO 639 language codes
- curl documentation
- LibriTTS-R corpus (OpenSLR 141)
- Node.js documentation
- openai-python on GitHub
