Frequently asked questions
What is a female voice text-to-speech API?
It is a cloud API that converts text into audio files. You send a POST request with your text and receive an audio file in return. Female voices like Aria, Nova, Luna, and Sage are available as presets. The API handles the synthesis, allowing you to integrate clear audio notifications directly into your fintech applications without managing infrastructure.
Which female voice is best for banking notifications?
Aria (warm, clear narrator) and Sage (calm, instructional) are suitable for banking notifications. Luna is soft and storytelling-focused, while Nova is bright and upbeat. Since no voice is objectively "best," you can test all options via the /v1/voices endpoint to determine which fits your specific notification tone best.
How much does it cost to generate audio?
The price is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you successfully process.
Can I use this API for Hindi text-to-speech?
Yes, Hindi is one of the 23 supported languages. You must specify the language code in the request body to ensure correct pronunciation. Any of the 8 voice presets can speak Hindi. If you do not set the language, the system guesses it, which may default to English for Latin script text.
Does the API support real-time streaming?
No, the API does not support streaming, WebSocket, or real-time partial audio. You send a request and receive the complete audio file in the response. Requests are processed sequentially, so longer texts may take time. You must wait for the full file before playing it in your application.
What audio formats are available for download?
You can request audio in mp3, wav, opus, flac, or pcm formats. Specify your preferred format in the response_format field of the JSON body. The API returns the audio file directly in the response, allowing you to save or play it immediately in your mobile or web app.
How many characters can I send in one request?
Each request supports up to 4096 characters of input text. If your message exceeds this limit, you must split it into parts. Generate audio for each part separately and join the resulting audio files. This ensures reliable synthesis and avoids truncation or errors in your transaction notifications.
Is the audio file stored after generation?
No, generated audio is returned in the response and not stored by the API. Input text is used only to produce the audio and is not used for training. Request metadata like time and status is kept for billing purposes. You are responsible for storing the audio files you receive.
Can I clone my own voice for branding?
No, the API does not offer custom voice cloning or uploading your own voice. You must choose from the 8 available presets. The voices are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark marking it as synthetic speech.
Do you offer a free trial?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up using USDT on the TRON network to continue using the API after the trial expires.
How do I handle long transaction messages?
Split the text into chunks of up to 4096 characters. Send each chunk as a separate POST request to the speech endpoint. Receive the audio files for each part and join them in your application. This ensures all content is synthesized correctly without exceeding the character limit per request.
What happens if the API request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or split the text if it was too long. Check the response status to confirm failure and ensure your application handles retries gracefully without double-charging your balance.
Are there any hidden fees for high volume?
No, there are no hidden fees. The price is strictly $10 per 1 million characters. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters processed. Failed requests are free, and balance does not expire. Top-ups are processed automatically via USDT.
How does the speed parameter affect audio quality?
The speed parameter adjusts playback speed from 0.25 to 4.0. It changes how fast the voice speaks but does not alter the fundamental voice characteristics. The engine quality remains consistent. Faster speeds may make speech harder to understand, while slower speeds are clearer. Adjust based on your user's listening context.
First request
curl
curl https://api.leongto.net/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 Fintech Teams Choose Female Voices
The Fintech Voice API leverages high-quality voice presets to deliver clear, professional audio for banking notifications. By using female voices like Aria and Luna, product teams can ensure their transaction alerts and updates are delivered with a tone that feels approachable and trustworthy.
Clear Narrator Tone
The API uses licensed recordings from LibriTTS-R. This foundation provides a natural speech quality without robotic artifacts, ensuring that critical financial information is delivered clearly.
High Comprehension Rates
Clear articulation ensures users grasp transaction details. The distinct vocal profiles minimize cognitive load, allowing customers to quickly understand balance updates or payment confirmations without re-listening.
Consistent Brand Identity
Using a consistent voice across all notifications reinforces brand recognition. Whether it is a warm narrator or a calm instructional tone, the same audio style is applied to every alert, creating a cohesive user experience.
You can select from eight presets to match your app’s aesthetic. This consistency helps users instantly identify the source of the audio, improving engagement and trust in your fintech platform.
Our Voice Catalog for Banking
Our voice catalog is designed for clarity and trust in financial contexts. Each preset is optimized for specific notification types, ensuring your users receive messages that match the tone of the transaction. We use licensed recordings from LibriVox, providing a consistent and professional sound across all languages.
The four female voices cover the primary needs of fintech applications: from urgent alerts to detailed account updates. Selecting the right voice helps maintain brand identity.
Aria: Warm Narrator
Aria offers a clear, warm tone ideal for general notifications. Her voice ensures that transaction details are heard clearly without sounding robotic. This preset works well for standard payment confirmations where clarity is the priority.
Use Aria for routine updates that need to be heard and understood quickly. Her delivery is steady and professional, suitable for daily balance checks or low-value transaction alerts.
- Best for: Standard payment confirmations
- Tone: Clear and warm
- Language support: All 23 languages
Nova: Bright Upbeat
Nova brings a bright and energetic quality to your notifications. She is well-suited for promotional updates or successful transaction alerts where a positive tone is desired. Her upbeat nature makes financial news feel less sterile.
Nova works effectively for marketing-related banking notifications or rewards updates. Her voice adds a layer of engagement to your app without sacrificing the clarity of the spoken text.
- Best for: Promotional updates
- Tone: Energetic and bright
- Use case: Rewards and bonuses
Luna: Soft Storytelling
Luna’s soft, storytelling voice is designed for longer updates or detailed explanations. If you need to convey account history or multi-step instructions, Luna’s pacing helps users follow along comfortably.
This preset is ideal for monthly statements or educational content within your fintech app. Her gentle tone reduces listener fatigue during longer audio segments.
- Best for: Monthly statements
- Tone: Soft and gentle
- Length: Optimized for longer texts
Sage: Calm Instruction
Sage provides a calm, instructional tone perfect for guiding users through processes. Her voice is neutral yet reassuring, making her suitable for verification steps or security alerts.
Use Sage for two-factor authentication notifications or step-by-step onboarding guides. Her consistent delivery ensures that instructions are followed accurately without emotional distraction.
Sage’s voice is particularly effective for non-urgent but important updates where precision matters more than emotion.
- Best for: Security alerts
- Tone: Calm and instructional
- Precision: High clarity
Multi-Language Support
Our API supports 23 languages, ensuring your banking notifications reach users in their preferred dialect. Whether you are sending transaction alerts to English-speaking customers or payment confirmations to Hindi users, the system handles synthesis.
For texts using Latin script that are not English, you must explicitly set the language parameter. The API guesses the language from the script by default, but explicit configuration prevents errors for languages like Dutch or Danish that share the Latin alphabet.
Hindi Text-to-Speech
Generate clear, natural-sounding audio for Hindi notifications. Our engine supports Hindi alongside 22 other languages, allowing fintech teams to localize their app experience without managing separate voice providers.
- Supports Devanagari script
- Consistent voice quality across all 8 presets
- No separate model required
English Notifications
English is the default for Latin-script text if no language is specified. This makes it easy to start sending transaction alerts and balance updates immediately after integration.
Global Customer Reach
Reach customers in 23 languages including Arabic, Chinese, French, German, Japanese, Korean, Spanish, and more. Every voice can speak any of these languages, giving you full flexibility to match your user base.
- 23 supported languages
- Any voice can speak any language
- Vietnamese, Thai, and Ukrainian are not supported
Technical Integration
Integration is straightforward because the API accepts the same JSON body as the OpenAI Speech endpoint. You can use the official OpenAI SDKs by simply changing the base_url to https://api.leongto.net/v1 and providing your unique API key.
The endpoint POST /v1/audio/speech accepts model, input, voice, response_format, and speed. This simplicity allows fintech product teams to drop the library into existing backend services without learning a new protocol.
OpenAI SDK Compatible
Leverage existing infrastructure by pointing your OpenAI SDK client to our base URL. This ensures you get the same request shape and response handling, requiring only a configuration change to switch providers.
No custom client libraries are needed. Standard HTTP clients work just as well if you prefer to avoid the SDK dependency entirely.
- Change
base_urltohttps://api.leongto.net/v1 - Use standard OpenAI Python/JS/Go SDKs
- Identical JSON request structure
Simple JSON API
Send a single POST request with your text and voice preference. The API returns the audio file directly in the response body, ready to be played by your mobile app or web frontend.
You can control generation speed between 0.25x and 4.0x. If the input text exceeds 4096 characters, split it into chunks and join the resulting audio files on your end.
POST /v1/audio/speech- JSON body with
model,input,voice - Return audio directly in response
Multiple Audio Formats
Choose the format that best fits your delivery channel. MP3 is ideal for web players, while WAV and FLAC offer lossless quality for archival. OPUS and PCM are available for efficient playback or raw processing.
Selecting the right format ensures compatibility with your existing media pipelines without needing extra conversion steps on the server side.
- mp3, wav, opus, flac, pcm
- Optimize for web or archival
- No additional conversion needed
Pricing Model
Fintech teams pay only for what they use, with billing calculated at $0.01 per 1,000 characters. Failed requests incur no charge, and your balance never expires, making it easy to forecast costs for transaction alerts or account updates without unexpected overages.
Pay Per Character
Usage is measured by character count, including spaces and punctuation. At $10 per million characters, long voice notifications remain cost-effective, while short transaction pings add minimal expense to your operational budget.
- $0.01 per 1,000 characters
- Failed requests are free
- Balances do not expire
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You can scale from a few hundred notifications to millions without changing your billing structure, paying only for the volume you actually process.
- No monthly plans
- No seats or minimums
- USDT (TRC-20) top-ups only
Free Trial Available
Sign in with Google to receive $0.50 in credit, valid for seven days. This covers approximately 50,000 characters, allowing you to test voice quality and integration speed before committing to a top-up via the TRON network.
- $0.50 trial credit
- 7-day validity
- Email/password accounts start without credit

Use Cases
Fintech teams use the API to convert raw transaction data into clear audio notifications for mobile and web apps. By replacing text-heavy alerts with synthetic speech, you ensure critical financial updates are heard and understood instantly, even when users are multitasking or have visual impairments.
The API handles high-volume bursts efficiently, splitting longer updates into seamless audio segments. This reliability ensures that balance warnings or payment statuses are delivered without delay, maintaining trust in your notification system.
Transaction Alerts
Convert debit and credit events into immediate audio cues. For example, a $50 coffee purchase triggers a concise voice message confirming the amount and merchant. The system supports multiple languages, ensuring alerts are clear for international customers regardless of their primary language.
- Instant voice confirmation for purchases
- Multi-language support for global users
- Clear audio for low-attention moments
Account Balance Updates
Notify users of significant balance changes via voice. A drop below a threshold can trigger a calm, instructional voice using Sage, while a deposit might use a brighter tone like Nova. This adds an emotional layer to routine financial data.
- Threshold-based voice triggers
- Context-aware voice selection
- Accessible balance reporting
Payment Confirmations
Send audio confirmations for successful transfers or bill payments. The API generates short, clear files that load quickly on mobile devices. Users receive a definitive audio signal that their payment went through, reducing support calls regarding failed or pending transactions.
- Audio proof of payment
- Fast mobile loading times
- Reduced support ticket volume
Reliability & Limits
Reliability is managed through clear limits and transparent processing. Requests are processed sequentially, meaning your audio generation waits in a queue during high load. Understanding these constraints helps you plan your notification delivery effectively.
Rate Limits
Each API key allows 60 requests per minute once funded. Before your first top-up, the limit is 10 requests per minute. This ensures stable performance for your fintech applications.
Queue Processing
Requests are processed one after another. Under heavy load, a request may wait in a queue before synthesis begins. Typical speed is roughly real-time, but short phrases may take a few seconds.
Character Counting
Split long texts into parts of up to 4096 characters per request. Spaces and punctuation count as characters. Longer texts are generated by joining the resulting audio files seamlessly.
Data Privacy
Input text is used exclusively to generate the audio file for your request and is not retained for model training. This ensures that your transaction data is not leveraged to improve the underlying voice engine.
Generated audio files are returned directly in the API response and are not stored on our servers. Only request metadata—such as timestamp, character count, and status—is kept for billing purposes.
No Training Use
Your input text is processed solely to produce the requested audio and is not used for training or improving the TTS model. This keeps your customer data distinct from the training dataset.
No Audio Storage
The generated audio file is delivered in the response and is not permanently stored on our infrastructure. Once the audio is returned to your application, it is not kept for later retrieval or analysis.
Secure Transmission
All API requests and responses are transmitted over HTTPS, ensuring data integrity during transit. We retain only essential metadata for billing and do not store the actual audio content or text after delivery.
Get Started
Start by signing up on the /get-api-key/ page using your Google account. This grants immediate access to a free trial credit of $0.50, valid for seven days and approximately 50,000 characters.
Sign Up with Google
Visit the signup page and authenticate via Google. Unlike email/password accounts, this method instantly activates the free trial credit. You receive a unique API key and can view your balance immediately.
- Instant trial activation
- No credit card required
- 7-day validity period
Generate API Key
Your dashboard displays your active API key starting with tts-. Use this key in the Authorization: Bearer header. You can issue a new key at any time, which instantly invalidates the old one.
- Single active key per account
- Instant revocation on regeneration
- Secure Bearer token format
First Request Example
Send a POST request to https://api.leongto.net/v1/audio/speech. Use the tts-1 model with the aria voice for clear transaction notifications. The endpoint accepts JSON and returns an MP3 file directly.
- Endpoint: /v1/audio/speech
- Method: POST
- Format: JSON body
- Auth: Bearer token
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. User testing reveals how different voices affect engagement and clarity in banking contexts, allowing you to select the tone that best fits your brand identity.
23 languages
Any voice speaks any of these languages.
