Our Editorial Team and TTS API for Banking Notifications

By Fintech Voice editorial team · Updated 2026-11-19

This page explains how Fintech Voice works and who built it. We provide a simple text-to-speech API designed for banking and fintech product teams. , the open-source licensing of our audio models, and exactly how we handle your data. We focus on clear, reliable notifications for transaction alerts and account updates.

Read on to understand our technical limits, such as the lack of streaming or custom voice cloning. All information is specific to the API available at api.leongto.net. This is not an official OpenAI product, but a practical tool for your mobile and web apps.

Our Editorial Team and TTS API for Banking Notifications

Frequently asked questions

Who runs Fintech Voice?

Fintech Voice is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our team focuses on providing a simple API for fintech product teams to convert transaction alerts into clear audio.

Where do the voices come from?

Our voices are based on licensed recordings from LibriTTS-R, which uses CC BY 4.0 data, and from LibriVox public-domain audiobook readings. We do not use custom voice cloning or upload your own voice. The voices are synthetic, and every generated file carries an inaudible watermark marking it as synthetic speech.

Are the voices licensed?

Yes, the underlying recordings are licensed under CC BY 4.0 from LibriTTS-R and are public-domain audiobook readings from LibriVox. We do not offer custom voice cloning for customers. The generated audio files are returned in the response and are not stored by our service after delivery.

Do you store my data?

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 keep request metadata, including time, characters, and status, specifically for billing purposes. No other personal data is retained beyond what is necessary.

How do I contact support?

Support is available by email only. We do not offer a phone number, live chat, or on-premise install options. You can reach us via the contact page or the email link provided in your account dashboard. We aim to respond to your inquiries as quickly as possible.

Is there a phone number?

No, there is no phone number for Fintech Voice. Support is provided via email only. We do not offer live chat, phone support, or SLA guarantees. For urgent matters, please use the email contact form on our website or reach out through your account dashboard.

Do you offer SLA?

No, we do not offer an SLA or uptime guarantee. There is no enterprise contract or certifications like SOC 2 or HIPAA. Requests are processed one after another, so under load a request may wait in a queue. We strive for reliability but do not guarantee specific uptime percentages.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base_url. However, we are an independent storefront. We do not use OpenAI’s models, and our pricing and voice presets are distinct from theirs.

What is the data retention policy?

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. Request metadata, including time, characters, and status, is kept for billing purposes. We do not retain your input text beyond the generation process.

Can I use the voices commercially?

Yes, you can use the generated audio commercially. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain readings. We do not offer custom voice cloning, but the standard presets are available for your fintech notifications, mobile apps, and web applications without additional restrictions.

How do I report a bug?

You can report a bug by contacting us via email. We do not have a public issue tracker or live chat. Please include details like the request ID, voice used, and the text input. Our team will review your report and address any issues with the API or documentation.

Is the API open source?

No, the API is not open source. We do not provide an official SDK of our own, though you can use the OpenAI SDK or plain HTTP. The underlying voice models and recordings are licensed, but our API infrastructure and codebase are proprietary. We do not publish our source code.

Do you have a privacy policy?

Yes, we have a privacy policy that outlines how we handle your data. Input text is used only to produce audio and is not used for training. We retain request metadata for billing. You can find the full policy on our website, detailing our data retention and processing practices.

How do I verify the license?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. You can verify the CC BY 4.0 license on the official Creative Commons website. Each generated file carries an inaudible watermark marking it as synthetic speech, confirming its origin from our API.

Who We Are

Sound wave illustration for: Who We Are

Fintech Voice operates as a small, independent editorial and engineering group built for clarity and reliability. We do not maintain a large corporate hierarchy; instead, we focus on delivering a straightforward text-to-speech API that integrates cleanly into existing fintech notification pipelines.

Editorial Team

Editorial Team

We are a small, independent group focused on clarity and reliability. Our team consists of engineers and writers who understand the specific needs of banking products, ensuring that every audio notification is precise and professional.

Mission

Mission

Our mission is to provide a simple, reliable API for converting transaction alerts and updates into clear audio for mobile and web apps. We aim to eliminate the complexity of speech synthesis so your product team can focus on user experience rather than audio infrastructure.

Focus on Fintech

Focus on Fintech

We build specifically for fintech product teams who need consistent, multi-language voice notifications. By supporting 23 languages and offering 8 distinct voice presets, we ensure your banking notifications sound natural and trustworthy across different regions and customer bases.

Voice Licensing

Sound wave illustration for: Voice Licensing

Fintech Voice utilizes eight voice presets derived from the LibriTTS-R dataset. These voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), which uses data from LibriVox public-domain audiobook readings, ensuring a transparent and legally sound foundation for our synthetic audio generation.

LibriTTS-R Source

LibriTTS-R Source

Our voices are synthesized from high-quality speech data originally recorded by volunteers. This source material provides the acoustic characteristics that define our eight presets, from the warm narration of Aria to the deep documentary tone of Orion.

CC BY 4.0 License

The underlying LibriTTS-R dataset is distributed under the Creative Commons Attribution 4.0 International license. This allows us to process and repurpose the audio data for our API while maintaining compliance with open licensing standards.

Public Domain Origins

Many of the source recordings come from LibriVox, a platform dedicated to public-domain audiobooks. This heritage ensures that the base audio material is free from restrictive copyright claims, providing a stable license for your fintech applications.

Data Policy

Sound wave illustration for: Data Policy

Fintech Voice processes input text solely to generate the requested audio file. We do not use your transaction alerts, user data, or notification content to train or improve our speech synthesis models. Your data is transient and functional, used only for the immediate task of conversion.

Generated audio is returned directly in the API response and is not stored on our servers. This ensures that sensitive banking communications remain ephemeral, reducing the attack surface for data retention breaches while maintaining strict data minimization principles for product teams.

No Training Use

Input text is used exclusively for production. It is not ingested into our training datasets. This ensures that proprietary transaction formats or user-specific language patterns from your fintech app do not inadvertently influence future model generations.

No Audio Storage

Once the audio file is delivered to your client or application, we do not retain a copy. The audio exists only in the request-response cycle.

Metadata Retention

We retain request metadata, including timestamp, character count, and status, strictly for billing accuracy and troubleshooting.

This minimal metadata allows us to reconcile usage charges and diagnose API failures without storing the actual audio content or user text.

Billing records are kept until the account is closed and final charges are settled.

Limitations

Sound wave illustration for: Limitations

Fintech Voice provides a straightforward text-to-speech API designed for reliability rather than real-time interactivity. Understanding what the service does not offer helps you plan your integration architecture correctly, especially when building notification flows for banking apps.

No Streaming

The API returns fully synthesized audio files after processing is complete. There is no WebSocket or streaming endpoint to receive partial audio chunks as they are generated. For transaction alerts, this means a brief delay while the server processes the text, but it ensures consistent audio quality without network jitter.

No SSML

We do not support Speech Synthesis Markup Language (SSML) for fine-grained control over pauses, emphasis, or pronunciation. Voice rendering is controlled through the eight preset voices and the speed parameter. This simplifies integration for product teams who prefer simple text inputs over complex XML structures.

No Voice Cloning

The service uses eight fixed voices derived from licensed LibriTTS-R recordings. We do not offer custom voice cloning for your brand or employees, nor do you upload your own voice samples. Each generated file includes an inaudible watermark to identify it as synthetic speech.

Limitations

Contact & Support

Sound wave illustration for: Contact & Support

We handle all inquiries via email to ensure every message is logged and tracked accurately. You can reach our support team at [email protected] for any technical questions, billing issues, or API integration help.

Email Support

All requests are assigned a unique ticket ID for reference, ensuring you can track the status of your inquiry without needing to chase updates.

No Phone

We do not offer a phone number or live chat. This allows us to maintain asynchronous communication, providing detailed written responses with code snippets or API logs that are often clearer than verbal explanations.

Response Time

During high-volume periods, response times may extend slightly, but we prioritize fintech integration issues to keep your notification pipelines running smoothly.

Technical Details

Sound wave illustration for: Technical Details

The API endpoint is POST https://api.leongto.net/v1/audio/speech. It accepts JSON bodies with model, input, voice, response_format, speed, and optional language fields. Use the OpenAI SDK by changing the base URL to https://api.leongto.net/v1.

Authentication uses a Bearer token sent in the Authorization header. Each account has one active key. Issuing a new key instantly invalidates the previous one, ensuring secure access control for fintech integrations.

API Architecture

Send a POST request to the speech endpoint with your JSON payload. The API returns the audio file directly in the response body. Ensure your text input does not exceed 4096 characters per request.

For longer notifications, split the text into chunks and concatenate the resulting audio files. The system processes requests sequentially, so high volume may introduce slight queuing delays.

  • Base URL: https://api.leongto.net/v1
  • Endpoint: POST /v1/audio/speech
  • Auth: Bearer token in header

Rate Limits

Each API key is limited to 60 requests per minute. New accounts start with a limit of 10 requests per minute until the first top-up is processed.

This limit ensures stable performance for transaction alert pipelines. If you exceed the rate, subsequent requests will be delayed or rejected until the window resets.

  • Standard limit: 60 req/min
  • Initial limit: 10 req/min
  • Resets per minute window

Audio Formats

Supports mp3, wav, opus, flac, and pcm formats. Choose based on your app’s requirements: mp3 for web delivery, wav for high-quality archival, or pcm for raw processing.

All formats are generated from the same engine with identical quality. The speed parameter (0.25–4.0) applies uniformly across all supported formats.

  • mp3
  • wav
  • opus
  • flac
  • pcm

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.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. LibriVox public-domain audiobooks
  3. IETF RFC 7845: Ogg Opus
  4. OpenAI API reference: create speech
  5. Node.js documentation
  6. Creative Commons Attribution 4.0
  7. W3C WAI: making audio and video accessible
  8. LibriTTS-R corpus (OpenSLR 141)
  9. openai-node on GitHub
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. MDN: Web Speech API
  12. TRON developer hub: TRC-20

More on this site