Frequently asked questions
What should I look for in a TTS API?
Prioritize transparent pricing, clear data handling, and reliable integration. Our API offers per-character billing with no hidden fees, ensuring you only pay for successful generations. It uses standard OpenAI-compatible endpoints, allowing easy adoption with existing tools. We provide straightforward rate limits and simple authentication, making it suitable for fintech teams needing consistent, predictable voice notifications without complex infrastructure.
Is per-character pricing better?
Per-character pricing ensures you pay only for actual usage, which is ideal for variable notification volumes. Our rate is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free, so you are not charged for errors. This model scales efficiently with your customer base, avoiding fixed monthly costs for unused capacity or seat licenses.
Which voices are best for banking?
For banking notifications, we recommend Atlas for neutral, clear alerts or Sage for calm, instructional updates. Milo offers a friendly, conversational tone suitable for customer service prompts, while Aria provides a warm, clear narrator voice for general announcements. These presets are designed for clarity and professionalism, ensuring critical financial information is delivered with an appropriate tone and readability.
How important is language support?
Broad language support is critical for global fintech products. We support 23 languages, including English, Spanish, German, French, and Japanese. Any voice can speak any supported language, ensuring consistency across regions. If the language is not specified, it is guessed from the script, but setting it explicitly ensures accuracy for non-English Latin-script text, preventing mispronunciation errors.
Is the API easy to integrate?
Yes, integration is straightforward. The endpoint matches the OpenAI speech endpoint shape, so you can use official OpenAI SDKs by simply changing the base URL. Send a POST request with your text, voice, and format preferences. Authentication uses a standard Bearer token. This compatibility allows your team to leverage existing HTTP clients or SDKs without learning a new proprietary protocol.
Is data privacy important?
Yes, we prioritize data privacy. Input text is used solely to produce the audio file and is not used for training models. Generated audio is returned in the response and not stored on our servers. We retain only request metadata, such as time, character count, and status, for billing purposes. This ensures your customer data remains private and secure during processing.
How fast is the generation?
Generation speed is roughly real-time, processing about 25 characters of text per second of audio. Short phrases may take a few seconds to generate. Requests are processed sequentially, so under high load, a request might wait in a queue. For longer texts, split them into parts of up to 4096 characters and join the resulting audio files for optimal performance.
What support do I get?
Support is provided via email only. There is no phone number, live chat, or dedicated account manager. We do not offer an SLA or uptime guarantee. For technical issues or billing questions, contact our support team through the email address provided in your account dashboard. Response times may vary based on volume, so plan your integration testing accordingly.
What are the technical limits?
Each request can handle up to 4096 characters of text. You are limited to 60 requests per minute per API key. The speed parameter ranges from 0.25 to 4.0. Supported audio formats include mp3, wav, opus, flac, and pcm. For texts exceeding 4096 characters, split the input into multiple requests and concatenate the resulting audio files to ensure complete delivery.
How do I pay?
Payments are made using USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are added automatically within minutes after the transfer is confirmed. We do not accept credit cards, PayPal, or subscriptions. There are no monthly plans or minimum spend requirements. Your balance does not expire, and you can top up as needed to continue service.
Is there a free trial?
Yes, signing in with Google provides a $0.50 credit, valid for 7 days, allowing approximately 50,000 characters of usage. Accounts created with an email and password do not receive this trial credit. This allows you to test the API’s quality and integration workflow before committing to a USDT top-up. The credit is deducted from your balance as you make requests.
Why choose this API?
We offer transparent, per-character pricing with no hidden fees or monthly commitments. Our API is compatible with standard OpenAI SDKs, easing integration. Data is not used for training, and audio is not stored. We support 23 languages and provide clear, professional voices suitable for fintech notifications. With simple USDT payments and straightforward rate limits,
Does it support SSML?
No, this API does not support SSML. You cannot use speech markup language to control pronunciation, pauses, or emphasis within the text. The API processes plain text input directly. If you need specific pronunciation control, you must adjust the text content itself before sending it to the API. We do not offer phoneme dictionaries or custom lexicons for fine-tuning audio output.
Can I clone voices?
No, custom voice cloning is not offered. You cannot upload your own voice or design a new voice. The API provides eight fixed presets based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark to identify it as synthetic speech. If you need a specific voice, you must choose from the available male and female presets.
Key Criteria for Fintech
Financial notifications demand consistency. When alerting customers about fraud or balance updates, the audio must be instantly recognizable and free of distortion. Reliable delivery ensures that critical information reaches users without ambiguity, maintaining trust during high-stakes moments.
Clear, professional voices reduce cognitive load. Our eight preset voices, such as Atlas for neutral news or Milo for conversational updates, ensure that tone matches the message. This clarity helps users process urgent details quickly, whether they are reading on a commute or listening in a busy office.
Reliability for critical alerts
Critical alerts require consistent synthesis. Our API processes requests sequentially, ensuring stable output for fraud warnings and balance updates. Requests are processed sequentially, so under load a request may wait in a queue.
Rate limits of 60 requests per minute allow for steady notification flows. If a request fails, the charge is returned in full, ensuring that billing aligns with successful delivery. This transparency helps product teams manage volume without unexpected costs during peak alert periods.
Clear, professional voices
Voice selection directly impacts user experience. Atlas provides a neutral, news-like tone suitable for standard updates, while Milo offers a friendly, conversational style for account notifications. Luna’s soft storytelling tone works well for detailed explanations, and Orion’s deep voice suits documentary-style financial reports.
Each voice is based on licensed recordings, ensuring legal compliance and consistent quality. The inaudible watermark marks synthetic speech, providing an additional layer of transparency. Users can distinguish between human and AI voices, which is crucial for regulatory clarity in fintech communications.
Transparent pricing
Our per-character model charges $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total, making costs predictable. There are no monthly plans, seats, or minimum spends, allowing you to scale usage based on actual notification volume.
Failed requests are free, so you only pay for successful audio generation. The balance does not expire, and top-ups via USDT on TRON are credited automatically. This structure eliminates hidden fees, making budget forecasting straightforward for product teams managing variable notification loads.
Pricing Models
Pricing models generally fall into two categories: subscription-based access or pay-as-you-go usage. For fintech teams managing fluctuating notification volumes, understanding the cost structure is essential for budgeting and forecasting expenses accurately.
Per-character vs subscription
Subscriptions often charge a flat monthly fee regardless of volume, which can be inefficient if your alert traffic varies. Per-character pricing aligns costs directly with usage, ensuring you only pay for what you generate.
Our per-character model
We charge $10 per 1 million characters, equivalent to $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, so you are not charged for errors.
Cost efficiency for high volume
High-volume fintech notifications benefit from this transparent model. With no monthly plans or minimum spend, costs scale linearly with your character count, providing predictable expenses for fraud warnings and account updates.

Voice Quality and Variety
Selecting the right voice ensures your fintech notifications are both clear and contextually appropriate. VocalLedger provides eight distinct preset voices, allowing you to match the tone of fraud alerts, balance updates, or general news with precision. Each voice is derived from licensed recordings, ensuring consistent quality across all outputs.
8 preset voices available
We offer eight curated voices: four female (Aria, Nova, Luna, Sage) and four male (Felix, Milo, Atlas, Orion). These are based on licensed LibriTTS-R recordings and LibriVox public-domain readings, providing a reliable foundation for your application.
Different tones for different uses
Choose warm narrators for story-driven updates, bright voices for promotional content, or calm tones for instructional guides.
Neutral voices for news
For daily market updates or financial news, use Atlas for a neutral news tone or Orion for a deep documentary style. These voices deliver information clearly without emotional bias, which is critical for maintaining trust in sensitive banking communications.
Language Support
VocalLedger supports 23 languages, including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This range covers major financial hubs, ensuring your fraud alerts and balance updates reach customers in their preferred language without requiring multiple specialized engines.
23 languages supported
Our API handles diverse scripts and phonetic structures, allowing product teams to deploy consistent voice notifications across global markets. Each voice is capable of speaking any of these 23 languages, maintaining uniform audio quality and tone regardless of the target locale.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Important for global banking
In fintech, clarity reduces user anxiety during critical events like fraud warnings or transaction failures. Supporting native languages ensures that non-native English speakers understand high-stakes notifications immediately. This reduces support ticket volume and improves user trust in automated communications.
Automatic detection feature
The API guesses the language from the script if none is specified, defaulting to English for Latin text. For non-English Latin-script text, we recommend explicitly setting the language field to ensure accurate pronunciation. This simplifies integration while maintaining high accuracy for global customer bases.
Integration Ease
VocalLedger is designed for seamless integration into fintech notification pipelines. By adhering to the standard OpenAI speech endpoint shape, your existing infrastructure requires minimal adjustment.
OpenAI SDK compatibility
The API accepts the same request structure as the official OpenAI speech endpoint. By simply updating the base_url to https://api.playga26.com/v1 in your OpenAI SDK configuration, you can use familiar libraries to send text and receive audio files. This reduces development time and leverages existing developer knowledge.
- Uses standard JSON request body
- Compatible with official OpenAI SDKs
- No custom client library required
Standard REST API
Our RESTful endpoints provide clear, predictable interactions. You send a POST request to /v1/audio/speech with your text and parameters, receiving a direct audio response. This simplicity ensures reliable integration with backend services generating fraud alerts or balance updates without complex orchestration.
Quick cURL setup
Getting started is immediate with standard command-line tools. You can test the integration directly from your terminal using a simple cURL command. This allows engineers to verify voice quality and latency before committing to a full implementation in the production notification system.
Data Privacy
When you send text to our API, it is used exclusively to generate the requested audio file. We do not use your input data to train our models or improve our voice engines, ensuring your notification content remains private and isolated from our broader dataset.
After synthesis, the audio is returned directly in the response and is not stored on our servers. This minimizes data retention risks, which is critical for fintech teams managing sensitive alert messages and fraud warnings where data persistence is unnecessary.
Text not used for training
Our system processes your input text solely for the purpose of generating the audio response. Unlike many competitors, we do not ingest your text into our training datasets. This means your unique notification templates, alert phrasing, and customer instructions are not used to refine our voice models, keeping your intellectual property and communication style distinct.
- Input text is used only to produce the audio.
No audio storage
Generated audio files are delivered via the API response and are not persisted on our infrastructure. Once the audio is sent to your client or application, we do not keep a copy. This zero-retention approach reduces liability and ensures that sensitive financial alerts or fraud notifications are not sitting in our storage buckets after delivery.
- Audio is returned in the response and not stored.
Metadata kept for billing
We retain minimal request metadata, including timestamp, character count, and status, strictly for billing and usage tracking purposes. This data allows us to accurately charge you based on the $0.01 per 1,000 characters rate and provides transparency in your usage dashboard. No personal identifiers or audio content are linked to this metadata for other uses.
- Request metadata (time, characters, status) is kept for billing.
Performance
VocalLedger generates audio at roughly real-time speed, producing approximately 25 characters of text per second. Short phrases take a few seconds to synthesize, ensuring timely delivery for fraud alerts and balance updates.
Real-time generation
Longer texts are processed efficiently, maintaining a pace that matches spoken delivery. This ensures that critical notifications are delivered without excessive delay, keeping your users informed in near real-time.
Rate limits management
Each API key is limited to 60 requests per minute. New accounts start with 10 requests per minute until the first top-up. This structure prevents sudden spikes from overwhelming the service while allowing steady volume.
- Limit: 60 requests/minute per key after top-up
- Initial limit: 10 requests/minute
- No burst allowances beyond standard limits
Queue handling
Requests are processed sequentially. Under heavy load, a request may wait in a queue before synthesis begins.

Customer Support
VocalLedger provides email support for all technical and billing inquiries. This focused channel ensures that your questions are handled by engineers who understand the API's specific constraints and integration patterns, rather than generalist agents.
We maintain a self-service model to keep overhead low and pricing transparent. You can resolve most issues quickly by checking our documentation or testing the API directly with your own credentials.
Email support only
Send your questions to our support email address. We respond to all messages promptly, ensuring you get accurate answers regarding rate limits, voice selection, or billing discrepancies without unnecessary delays.
No phone or live chat
We do not offer phone lines or live chat windows. This approach avoids scheduling bottlenecks and ensures that every interaction is documented and traceable, which is valuable for audit trails in fintech environments.
Self-service documentation
Our guides cover every endpoint, including the /v1/voices list and authentication steps. You can copy ready-made cURL examples and adapt them to your banking notification workflows immediately.
- Clear API reference for all endpoints
- Ready-to-use cURL examples
- Detailed error code explanations
Technical Limits
Understanding the technical boundaries ensures your fintech notification system remains stable. VocalLedger’s API imposes specific constraints on input length, request volume, and delivery mode that product teams must account for in their architecture.
4096 character limit
Each API request accepts up to 4,096 characters. For longer alerts, split the text into chunks, generate audio for each, and concatenate the files. This ensures consistent quality and avoids truncation.
60 requests per minute
The rate limit is 60 requests per minute per key. New accounts start at 10 requests per minute until the first top-up. Under load, requests queue sequentially, which may delay generation for high-volume bursts.
No streaming support
The API returns complete audio files rather than streaming partial audio. This means you must wait for the full synthesis to finish before playing the notification. It simplifies implementation but prevents real-time audio playback.
Payment Methods
VocalLedger uses a straightforward payment model designed for transparency and simplicity. We process top-ups exclusively via USDT on the TRON network, ensuring that your account balance updates quickly without the friction of traditional banking delays or currency conversion fees.
USDT on TRON network
Payments are made using USDT (TRC-20), the only accepted method. The system automatically credits your balance within minutes of confirming the transfer on the blockchain.
- Accepts USDT on the TRON network (TRC-20) only
- Automatic credit within minutes of transfer confirmation
No credit cards or PayPal
We do not store credit card details or link to PayPal accounts. This reduces your administrative overhead and avoids recurring subscription locks. There are no monthly plans, seats, or minimum spend requirements attached to your payment method.
Fast top-up process
With a minimum top-up of $5, you can maintain a steady supply of characters for your notification pipelines. Since balances do not expire, you can top up when convenient without worrying about unused credits disappearing after a billing cycle.
- Minimum top-up amount is $5
- No expiration on your account balance
Trial Options
VocalLedger offers a straightforward trial to help fintech product teams evaluate our text-to-speech API without financial commitment. This option is specifically designed for teams testing alert systems for fraud warnings or balance updates, allowing you to verify voice clarity and integration speed before scaling up.
$0.50 free trial for Google users
Accounts created via Google sign-in receive an automatic $0.50 credit, equivalent to approximately 50,000 characters. This trial credit is not available for accounts created with email and password, ensuring a clear distinction between trial and paid tiers.
7-day validity
The trial credit expires exactly seven days after account creation. This timeframe provides sufficient window to run integration tests, generate sample audio files, and assess performance under typical load conditions without pressure.
Test before committing
You can test voice presets like Atlas for news or Sage for instructional alerts using real-world notification text. Since failed requests are free, you can experiment with different models and speeds to find the optimal balance for your specific use case.

Why Choose This API
VocalLedger offers a straightforward API designed specifically for fintech product teams who need reliable voice notifications. Our per-character pricing model ensures you only pay for what you use, with transparent costs that scale with your volume. There are no hidden fees or surprise charges, making budgeting predictable for fraud alerts and balance updates.
Simple and transparent
Our API follows a standard REST structure compatible with OpenAI SDKs, making integration quick and familiar for your engineering team. You can start sending requests and receiving audio files immediately without navigating complex proprietary systems.
- Standard REST API endpoints
- OpenAI SDK compatibility
- Clear documentation and examples
No hidden fees
Pricing is strictly $10 per million characters, with spaces and punctuation counting toward the total. Failed requests are free, and there are no monthly subscriptions or minimum spend requirements. You can manage your account and top-up via USDT on TRON with automatic crediting.
- $10 per 1 million characters
- Failed requests are free
- No monthly plans or minimums
Built for fintech needs
We provide neutral, professional voices like Atlas for news-style alerts and Sage for instructional updates, ensuring clarity in critical notifications. The API handles text splitting and queue management automatically, delivering reliable audio for fraud warnings and account updates without compromising on data privacy.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Secure your funds instantly with our new real-time fraud alerts and smart transaction monitoring features.
23 languages
Any voice speaks any of these languages.
