Frequently asked questions
What is speech synthesis online?
It is a cloud API where you send text and receive an audio file. You POST JSON to the endpoint, specifying model, voice, and format. The service converts your text into synthetic speech instantly, returning the audio directly in the response without storing the generated file.
How does TTS work for fintech?
Send text via POST request to the API endpoint. The system generates audio using licensed voices like Aria or Atlas. You receive the file immediately. This allows banks to automate customer notifications, fraud alerts, and balance updates at scale.
What are the benefits of voice notifications?
Voice notifications improve engagement and clarity for complex financial data. Synthetic speech carries an inaudible watermark for verification. You can select presets like Felix or Sage, ensuring consistent voice quality across all customer communications.
Can I use TTS for fraud alerts?
Yes. Use voices like Atlas for neutral news or Orion for deep, serious tones. Each generated file includes an inaudible watermark marking it as synthetic speech. This helps verify authenticity. You can generate alerts instantly via API, ensuring customers receive timely, clear audio warnings about their accounts.
What languages are supported?
We support 23 languages including English, Spanish, German, French, Japanese, and Hindi. Any voice can speak any supported language. If you do not set the language, it guesses from the script, defaulting to English for Latin text. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
How much does it cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. Top-ups are via USDT on TRON. There are no monthly plans or minimums. You only pay for what you use, with balance that does not expire.
Is data used for training?
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. Only request metadata like time and characters are kept for billing purposes, ensuring your customer data remains private.
Can I use OpenAI SDKs?
Yes. The endpoint matches the OpenAI speech endpoint shape. Use the official OpenAI SDKs by changing the base_url to https://api.playq22.com/v1 and providing your site’s key. This allows seamless integration into existing fintech infrastructure without rewriting your client code.
What formats are supported?
You can receive audio in mp3, wav, opus, flac, or pcm formats. Choose the format that best fits your delivery channel. MP3 is efficient for bandwidth, while WAV offers high quality. All formats are generated instantly upon successful synthesis request.
How fast is generation?
Generation is roughly real-time, producing about 25 characters of text per second of audio. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Long texts are split and joined automatically.
What is the character limit?
Each request supports up to 4096 characters of input text. For longer notifications, split the text into parts, generate each, and join the audio files. Spaces and punctuation count toward the character limit. This ensures consistent audio quality and manageable processing times.
How do I integrate the API?
Sign up at /get-api-key/ to get your Bearer token. Send a POST request to /v1/audio/speech with your text, voice, and format. Use the OpenAI SDK by setting the base_url to https://api.playq22.com/v1. The API returns the audio file directly in the response.
What is a rate limit?
You are limited to 60 requests per minute per key. Before your 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 notification delivery.
Is there a free trial?
Yes, signing in with Google gives $0.50 credit, valid for 7 days. Email accounts start without trial credit. This allows you to test the API with about 50,000 characters. Top-ups via USDT on TRON are required for ongoing use after the trial or balance is exhausted.
Definition of speech synthesis
Text-to-speech (TTS) technology converts written text into audible speech. For fintech teams, this means transforming static alert text into spoken notifications that users can listen to while on the go. It is a core automation tool that replaces manual recording or simple beep tones with natural-sounding voice messages.
The process is straightforward: you send text to an API, and the system returns an audio file. This automated voice generation ensures consistent quality across thousands of daily notifications, from fraud alerts to payment confirmations, without requiring human voice actors for every message variant.
Text-to-speech technology
TTS technology enables banks to deliver clear, spoken updates to customers instantly. Instead of reading an SMS, users hear a natural voice that conveys urgency or calm, depending on the context. This bridges the gap between digital alerts and human interaction.
The technology relies on pre-trained models that synthesize speech from text input. For fintech, this means reliable, scalable audio delivery that works seamlessly with existing mobile apps and notification systems.
- Instant conversion of text to audible alerts
- Consistent audio quality across all messages
- Support for high-volume notification workflows
Converting text to audio
The core function is simple: input text, receive audio. You send a JSON request with your message, and the API returns an audio file in formats like MP3, WAV, or FLAC. This file is then played by your banking app or SMS gateway.
This conversion supports up to 4,096 characters per request. For longer messages, texts are split and joined seamlessly. The result is a continuous, natural-sounding audio clip that delivers your notification clearly.
- Supports MP3, WAV, OPUS, FLAC, PCM
- Handles texts up to 4,096 characters
- Returns ready-to-play audio files
Automated voice generation
Automated voice generation removes the need for manual recording studios. Every notification sounds professional and consistent, whether it is a $5 transaction alert or a monthly statement summary. The system handles voice synthesis in real time, delivering audio quickly enough for immediate playback.
This automation scales with your user base. As transaction volumes grow, the API handles the load, ensuring that every customer receives a clear, audible notification without delays or quality degradation.
- No manual recording required
- Scales with transaction volume
- Delivers consistent voice quality
How it works for fintech
VerbaCore simplifies audio notification delivery by converting text into speech through a straightforward API call. Fintech teams send their message content via a POST request, and the system processes it to generate ready-to-play audio files.
Send text via API
Your backend sends a JSON payload to the speech endpoint. You define the text, select a voice preset like Aria or Atlas, and specify the desired audio format. The API handles the synthesis engine, ensuring high-quality output for each notification batch.
- POST request to the speech endpoint
- JSON body with text and voice parameters
- Support for up to 4096 characters per request
Receive audio file
The API returns the synthesized audio file directly in the response. You can choose from mp3, wav, opus, flac, or pcm formats. Failed requests incur no charge, ensuring you only pay for successful audio generation.
- Multiple audio formats supported
- No cost for failed requests
- Immediate response with audio data
Integrate with banking apps
Once received, the audio file is stored or played directly to your users. This integration allows banking apps to deliver consistent, professional voice notifications for fraud alerts or payment confirmations without managing complex audio infrastructure.
- Seamless integration with existing banking workflows
- Consistent voice quality across notifications
- Scalable delivery for large user bases
Benefits for banking teams
Banking teams can push high-volume alerts without manual effort. The API processes requests sequentially, ensuring critical messages like fraud warnings or balance updates are generated reliably. This automation reduces operational load while maintaining reliable delivery during peak traffic periods.
Scalable notifications
Send thousands of unique text snippets simultaneously. The system processes requests in sequence, queuing them as needed to maintain stability. This approach supports large teams managing diverse customer segments without infrastructure bottlenecks.
- Handle concurrent fraud alerts and payment confirmations
- Scale from hundreds to millions of requests seamlessly
Consistent voice quality
Every notification sounds professional and uniform. With eight distinct voice presets, you can select a calm, instructional tone for balances or a warm narrator style for general updates. This consistency builds trust and clarity across all customer communications.
- Uniform audio output for brand reliability
- Choose voices like Sage for instructions or Aria for narration
Cost-effective delivery
Pay only for what you use. At $10 per million characters, costs remain predictable. Failed requests are refunded automatically, and there are no monthly fees or minimum spends. This model fits variable notification volumes perfectly.
- Zero cost for failed synthesis attempts
- No monthly subscriptions or hidden fees
Use cases in finance
TTS APIs enable banks to deliver critical updates directly to customers’ ears, ensuring urgent messages are heard instantly. By converting text into natural-sounding audio, fintech teams can reduce notification fatigue and improve engagement rates for time-sensitive alerts.
This approach allows for consistent, professional voice delivery across all customer communications, regardless of volume. It simplifies the user experience by providing auditory confirmation of important financial events without requiring users to open an app or read lengthy emails.
Fraud alert voice messages
When unusual activity is detected, a TTS API can instantly generate a voice alert describing the transaction. This immediate auditory cue prompts users to verify the charge quickly, potentially preventing unauthorized withdrawals before they are finalized.
The system can convey urgency through voice tone while maintaining clarity, ensuring customers understand the nature of the alert without ambiguity. This is particularly useful for push notifications where visual attention may be limited.
- Instant voice alerts for suspicious transactions
- Clear articulation of transaction details
- Reduces time-to-action for users
Account balance readouts
Users can request their current balance via voice, receiving a clear, spoken response without navigating complex menus. This is especially valuable for accessibility, allowing visually impaired customers to manage their finances independently.
The API processes the text query and returns an audio file that states the balance accurately. This integration enhances the user experience by providing a hands-free way to check finances, suitable for driving or multitasking.
- Hands-free balance inquiries
- Accessible for visually impaired users
- Seamless integration with banking apps
Payment confirmations
After a payment is processed, a TTS API can generate a confirmation message confirming the amount, recipient, and timestamp. This auditory confirmation provides immediate reassurance to the user, reducing anxiety about transaction success.
The audio file can be delivered via push notification or played within the app, ensuring the user hears the confirmation directly. This adds a layer of trust and clarity to the payment process, enhancing customer satisfaction.
- Immediate auditory confirmation of payments
- Details included: amount, recipient, time
- Enhances trust in transaction success
Technical requirements
Integrating VerbaCore’s TTS API into your fintech notification pipeline requires minimal code changes. By pointing your existing OpenAI SDK or HTTP client to our base URL, you can start generating audio files for fraud alerts or balance updates in minutes. The API handles the heavy lifting of synthesis, returning ready-to-play audio directly in the response.
The system is designed for high-volume delivery suitable for banking teams. You simply send a JSON payload with your text and voice preference, and receive a standardized audio file. This approach ensures consistent voice quality across all customer communications without managing complex infrastructure.
API integration
Connect by updating the base URL to https://api.playq22.com/v1. Use standard Bearer token authentication with your unique API key. The endpoint accepts POST requests to /v1/audio/speech, making it compatible with existing fintech notification engines that already handle web hooks or async job queues.
- Supports standard HTTP methods
- Uses Bearer token auth
- Compatible with existing notification queues
JSON request format
Send a simple JSON body containing the text input, target voice, and desired audio format. The API accepts up to 4096 characters per request. For longer notifications, split the text into chunks and join the resulting audio files. The model field accepts either tts-1 or tts-1-hd for identical pricing and engine performance.
- Max 4096 characters per request
- Standard JSON payload
- Optional language ISO code
Audio format support
Choose from mp3, wav, opus, flac, or pcm based on your app’s playback requirements. MP3 is recommended for general use due to its small file size and universal compatibility. WAV and FLAC offer lossless quality for high-fidelity notifications. PCM is available for raw audio processing pipelines.
- mp3 for general use
- wav and flac for lossless quality
- pcm for raw processing
Voice options for banking
Choosing the right voice ensures your fintech notifications are clear and trustworthy. Our eight presets cover every tone needed for banking communications, from urgent fraud alerts to calm account updates.
Calm and instructional voices
Sage offers a calm, instructional tone perfect for guiding users through complex banking steps. Luna provides a soft, storytelling style.
Clear and warm narrators
Aria delivers a warm, clear narrator voice that builds trust during payment confirmations. Nova adds a bright, upbeat energy suitable for promotional updates or new feature announcements.
Neutral and news-style voices
Atlas provides a neutral, news-style delivery for straightforward transaction notifications. Felix offers an energetic style, while Milo’s friendly conversational tone works well for general account updates.

Language support
VerbaCore supports 23 languages, covering major markets like English, Spanish, German, Japanese, and Hindi. Every voice can speak any of these languages, ensuring consistent quality across global fintech operations.
23 languages available
We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Voices are not language-specific; each preset adapts to the selected language, maintaining the same tone and style regardless of region.
- 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
The API guesses the language from the script. Latin script text defaults to English. This simplifies integration for teams handling predominantly English notifications, reducing configuration overhead.
Manual language setting
For non-English Latin-script text, set the language field explicitly. This ensures accurate pronunciation and intonation for languages like German or Dutch when the default guess might fail. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.
Data privacy
Your input text is used strictly to generate the audio file and is never repurposed for model training. This ensures that the specific content of your customer notifications remains isolated within the generation process, providing a clear boundary between your data and the underlying engine.
Input text not used for training
The generated audio is returned directly in the API response and is not stored on our servers. This means your voice assets are transient, reducing the risk of long-term data retention issues for sensitive banking communications.
Audio returned in response
We retain request metadata—including timestamp, character count, and status—solely for accurate billing and usage tracking. No conversational context or personal details from your text are kept beyond what is necessary to process the charge and verify the request.
Metadata kept for billing
Pricing model
Our pricing is straightforward: you pay only for what you generate. The rate is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. If a synthesis fails, you are not charged, ensuring you only pay for successful audio delivery.
There are no monthly fees, no subscriptions, and no minimum spend. You can scale from a few notifications to millions without changing your plan. Top-ups are made via USDT on the TRON network (TRC-20) with a $5 minimum. Balances do not expire.
Pay per character
You are billed based on the exact character count of your input text. This includes all spaces and punctuation marks. The cost is $0.01 per 1,000 characters, making it easy to predict costs for high-volume fraud alerts or balance readouts.
- $10 per 1 million characters
- Spaces and punctuation count
- Failed requests are free
No monthly fees
We do not charge for seats, storage, or platform access. You simply top up your balance and use the API. There are no invoices with VAT or complex enterprise contracts to manage. Your balance never expires, so you can top up when convenient.
- No monthly subscriptions
- No seat limits
- No minimum spend
Free trial available
Sign in with Google to receive $0.50 of trial credit, enough for about 50,000 characters. This credit is valid for 7 days. Accounts created with email and password do not receive trial credit. It is a quick way to test voice quality and integration speed.
- $0.50 credit for Google sign-ins
- Valid for 7 days
- Approx. 50,000 characters
Integration with OpenAI SDK
Leverage existing infrastructure by using the official OpenAI SDKs for seamless integration. By simply adjusting the base URL, fintech teams can switch to VerbaCore’s TTS API without rewriting their core logic.
This compatibility ensures that your current development workflows remain intact while gaining access to our specific voice and language capabilities.
Compatible with OpenAI SDKs
Use the standard OpenAI SDKs in your preferred language. This allows your engineering team to adopt our API with minimal learning curve and code changes.
- Works with Python, Node.js, and other OpenAI SDK variants.
- No custom client library required.
Change base_url
Update your configuration to point to https://api.playq22.com/v1. This single change directs all speech requests to our dedicated infrastructure while maintaining your existing authentication headers.
Use same request shape
Send JSON bodies identical to the OpenAI speech endpoint. Include your model, input, voice, and response_format fields exactly as documented. This ensures predictable behavior across your notification pipelines.
- Supports
tts-1andtts-1-hdmodels. - Accepts
mp3,wav,opus,flac, andpcmformats.
Performance metrics
TTS API delivers audio at roughly real-time speed, generating approximately 25 characters of text per second. Short phrases take a few seconds, while long texts process proportionally. Requests are processed sequentially, meaning heavy loads may introduce delays in a queue before synthesis begins.
The API enforces strict rate limits to ensure stability. Each key allows 60 requests per minute, or 10 per minute before the first top-up. Failed requests incur no charge, preserving your budget even during high-volume spikes or integration testing phases.
Real-time generation
Text is converted to audio at a speed of roughly 25 characters per second. This ensures that generated audio length closely matches spoken time, making it ideal for time-sensitive banking notifications.
Short phrases typically require a few seconds to synthesize. Longer texts are split into 4096-character chunks and joined seamlessly, maintaining consistent playback speed across the entire message.
- ~25 characters generated per second of audio
Queue processing
Requests are processed one after another. Under heavy load, a request may wait in a queue before synthesis begins. This sequential processing ensures consistent quality but may introduce latency during peak usage times.
Each request is handled individually, allowing for reliable tracking of status and duration. This model supports predictable scaling for fintech teams sending bulk notifications without complex infrastructure management.
Rate limits
Each API key supports up to 60 requests per minute. Before the first top-up, the limit is 10 requests per minute. This ensures fair usage and prevents any single account from overwhelming the shared infrastructure.
Failed requests are free, meaning you are not charged for errors. This protects your balance while allowing teams to test integration endpoints thoroughly without financial risk.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your recent transaction has been successfully processed and verified by our secure banking network.
23 languages
Any voice speaks any of these languages.
