API Documentation for Banking Notifications

By VoxBank editorial team · Updated 2026-11-18

This guide walks banking and fintech teams through integrating VoxBank’s text-to-speech API for compliant voice notifications. You will learn to generate audio from text using standard HTTP requests, manage your API key, and handle common edge cases like rate limits and errors.

The documentation covers essential details for production use, including supported audio formats, voice selection among our eight presets, and SDK integration. We focus on clear, practical steps so your team can broadcast natural-sounding updates to millions of users without enterprise overhead.

API Documentation for Banking Notifications

Frequently asked questions

How do I get an API key?

Sign up on the /get-api-key/ page using Google or email and password. Accounts are per site. The dashboard displays your key, balance, trial status, and usage statistics immediately after registration.

Does it work with OpenAI SDK?

Yes. The endpoint matches the OpenAI speech shape. Use the official OpenAI SDKs by changing the base_url to https://api.playbd10.com/v1 and providing your site’s key. No custom library is required.

What is the rate limit?

Limits are 60 requests per minute per key. New accounts start with 10 requests per minute until the first top-up is processed. Requests are processed sequentially, so load may cause queuing delays.

Which audio formats are supported?

Supported formats are mp3, wav, opus, flac, and pcm. Specify the desired format in the response_format field of your POST request to /v1/audio/speech. All formats are generated from the same engine.

How do I handle errors?

Failed requests are free, and the charge is returned in full. Check the response status code. If synthesis fails, no characters are deducted from your balance. Use standard HTTP error handling.

Can I use the same key for multiple teams?

Yes, one active key is issued per account. You can share this key across multiple team members or services. Note that issuing a new key immediately invalidates the old one.

What is the base URL?

The API base URL is https://api.playbd10.com/v1. Use this for all endpoints, including POST /v1/audio/speech, GET /v1/voices, and GET /v1/models. Ensure your SDK configuration points to this domain.

Is there a demo endpoint?

No specific demo endpoint exists. Use the /get-api-key/ page to get a key with $0.50 trial credit. Test directly with the POST /v1/audio/speech endpoint using your preferred HTTP client or SDK.

How do I specify a voice?

Include the voice parameter in your request body. Choose from eight presets: aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice supports all 23 available languages natively.

What happens if I exceed the limit?

Requests may wait in a queue if processing capacity is reached. If you exceed the rate limit, the API returns an error. Failed requests do not consume your character balance.

Do I need to install any libraries?

No specific library is required. You can use standard HTTP clients or the official OpenAI SDK. Simply configure the base URL and send JSON payloads. No mobile or WordPress plugins are available.

Is the API RESTful?

Yes, it uses standard HTTP methods. Send a POST request to /v1/audio/speech with a JSON body. Retrieve voices and models via GET requests. It follows standard RESTful conventions for simplicity.

Can I use this for web apps?

Yes. Use the API key in your backend to generate audio. Since there is no official SDK of our own, you can use plain HTTP or any language with HTTP support. Ensure key security in your infrastructure.

How do I authenticate requests?

Include the Authorization header with your Bearer token. Format: Authorization: Bearer tts-... . Use the key generated on the /get-api-key/ page. One key is active per account at any time.

First request

curl

curl https://api.playbd10.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.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.playbd10.com/v1", api_key="tts-...")

with client.audio.speech.with_streaming_response.create(
    model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
    response.stream_to_file("hello.mp3")

Node.js (openai)

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({ baseURL: "https://api.playbd10.com/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));
voice
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Get your API key

Sound wave illustration for: Get your API key

Accessing the VoxBank API begins with creating an account on the /get-api-key/ page. You can sign in using your Google account for immediate setup or create a standard account with an email and password. Each account is tied to this specific site.

Once registered, you receive a unique API key starting with tts-. This key authenticates your requests to the API base URL and is essential for all subsequent integration steps with your banking notification systems.

Sign up with Google

Sign up with Google

Selecting the Google sign-in option provides a $0.50 free trial credit valid for 7 days. This allows you to test the API with about 50,000 characters of text before committing to a top-up.

This method is the quickest way to start generating audio files for your compliance or alert broadcasts without immediate payment setup.

  • Instant access to trial credit
  • Fast onboarding for development teams

Use email and password

Use email and password

Creating an account with an email and password is suitable for production environments or teams that prefer dedicated credentials. Note that accounts created this way do not receive the initial trial credit.

  • No trial credit included
  • Standard credential management

Manage keys in dashboard

Your dashboard displays your active API key, current balance, and usage statistics. You can issue a new key at any time, which immediately invalidates the previous one, ensuring tight security for your notification pipelines.

The dashboard also shows your character consumption, helping you track costs against your $0.01 per 1,000 characters pricing model.

Requests are authenticated using the Authorization: Bearer header with your key.

  • One active key per account
  • Immediate key rotation

First request with cURL

Sound wave illustration for: First request with cURL

Once you have your API key, sending your first notification is straightforward. Use cURL to POST JSON to the speech endpoint. This method works for any programming language or automation tool your team already uses.

The request body defines the text, voice, and format. You send the text payload along with your authentication header. The system returns the audio file directly, allowing immediate playback or storage in your notification pipeline.

Basic POST request

Send a POST request to https://api.playbd10.com/v1/audio/speech. Include your Bearer token in the Authorization header. The endpoint accepts standard JSON bodies and returns the audio file or errors.

  • Method: POST
  • Endpoint: /v1/audio/speech
  • Auth: Bearer tts-...

JSON body structure

The JSON body requires the model, input text, and voice. You can optionally specify response_format and speed. Ensure the text does not exceed 4096 characters per request.

Use tts-1 or tts-1-hd for the model. Select one of the eight voices, such as atlas for neutral news updates or nova for upbeat promos. The input field holds your notification string.

  • model: "tts-1" or "tts-1-hd"
  • input: string (max 4096 chars)
  • voice: e.g., "atlas", "nova"
  • response_format: mp3, wav, opus, etc.
  • speed: 0.25–4.0

Response format

On success, the response contains the audio file in your requested format. You can save this file directly or play it to your users. Failed requests return an error code but do not charge your balance.

If the synthesis fails, the charge is returned in full. This ensures you only pay for delivered audio. Use the response headers to check content type and length.

Using the OpenAI SDK

Sound wave illustration for: Using the OpenAI SDK

To integrate VoxBank into your banking infrastructure, you simply redirect the official OpenAI SDKs to our API endpoint. This allows your existing codebase to leverage familiar tools without learning a new library, ensuring rapid deployment for your fintech notification systems.

You configure the base URL to point to our service and use your unique API key for authentication. This approach maintains standard request shapes while delivering high-quality synthetic voice notifications tailored for large-scale customer communications.

Change base URL

Update your SDK configuration to use https://api.playbd10.com/v1 as the base URL. This single change routes your requests to VoxBank’s infrastructure, allowing you to use standard OpenAI-compatible endpoints for speech synthesis without modifying your core logic.

Use official SDKs

The official OpenAI SDKs work directly with our API. By changing the base_url, you can use the same client libraries you already trust, ensuring consistent behavior and reliable integration for your banking and fintech teams.

Standard endpoints

We support the standard speech endpoint for generating audio files. You send a POST request with your text, voice selection, and format preferences, receiving a direct audio response. Additional endpoints like /v1/voices help you manage voice presets efficiently.

Supported audio formats

Sound wave illustration for: Supported audio formats

VoxBank supports multiple audio formats to fit your banking infrastructure. Choose the right format for your delivery channel, balancing quality, file size, and compatibility with your existing notification systems.

MP3 for web players

MP3 is the standard for web-based notifications and mobile apps. It offers broad compatibility with most media players and ensures smooth playback across different devices.

  • Compatible with most web and mobile players
  • Small file size reduces bandwidth usage
  • Ideal for push notifications and in-app audio

WAV for high quality

WAV provides uncompressed audio. Use this format when audio quality is critical, such as for official banking statements or regulatory compliance recordings.

Note that WAV files are larger than MP3, which may increase storage and transfer costs for large-scale broadcasts.

  • Uncompressed quality for critical communications
  • No compression artifacts
  • Best for archival or high-priority alerts

OPUS for efficiency

OPUS offers excellent compression with good quality. It is ideal for reducing bandwidth costs while maintaining clear speech, especially for high-volume notifications.

Use OPUS when you need to balance quality and file size for efficient delivery to millions of users.

Rate limits and quotas

Sound wave illustration for: Rate limits and quotas

VoxBank enforces a rate limit of 60 requests per minute per API key. This cap ensures stable performance for large banking teams broadcasting notifications to millions of users, preventing sudden spikes from degrading service quality for other customers.

60 requests per minute

Each active API key is allowed a maximum of 60 API calls every minute. Since requests are processed sequentially, high-volume notification campaigns may experience slight delays if the queue fills up. Plan your batch sizes accordingly to maintain smooth delivery.

  • Limit applies per key, not per account
  • Sequential processing may cause brief waits under load

10 requests before top-up

New accounts starting with the free trial credit are limited to 10 requests per minute until the first top-up is processed. Once you add USDT via TRON, the limit immediately increases to the standard 60 requests per minute.

  • Trial accounts start with a 10 req/min limit
  • Limit lifts automatically after USDT transfer confirmation

Queue handling

Requests are processed one after another. If you exceed the per-minute limit or send a burst of requests, they will wait in a queue. Longer texts take more time to synthesize, so plan your API calls to avoid unnecessary queuing delays.

Rate limits and quotas

Error handling

Sound wave illustration for: Error handling

When synthesis fails, the API returns a standard error response and the character charge is refunded in full. This ensures you only pay for successfully generated audio files, protecting your budget during unexpected outages or invalid inputs.

Failed request refunds

Failed requests are free. If the service cannot generate audio due to server issues or invalid parameters, the cost is returned to your balance automatically.

Common error codes

Use standard HTTP status codes to diagnose issues. 400 indicates invalid JSON or missing fields. 401 means your API key is incorrect or expired. 429 signals you have exceeded the rate limit of 60 requests per minute.

  • 400: Bad Request (invalid input)
  • 401: Unauthorized (bad key)
  • 429: Too Many Requests (rate limit)

Retry logic

Implement exponential backoff for transient errors like 429 or 500. Since requests are processed sequentially under load, short delays between retries help avoid queue congestion. Retries for 400 errors should check the input format first.

Voice selection

Sound wave illustration for: Voice selection

Choosing the right voice is critical for banking notifications where clarity and trust matter. Our API provides eight distinct presets, allowing you to match the tone of your alerts—whether it’s a transactional update or a security warning—without needing complex configuration. Each voice is engineered for natural comprehension across multiple languages, ensuring your customers hear clear, professional audio every time.

You can select any of the eight voices for any language, giving your team the flexibility to maintain brand consistency or vary tones for different notification types. All voices are generated from licensed recordings, ensuring a high standard of audio quality right out of the box.

8 presets available

The API offers eight distinct voice presets designed for clarity and natural flow. You can assign any voice to any language supported by the system, allowing for consistent branding across different regions or notification types. Whether you need a warm narrator for account summaries or a neutral voice for security alerts, the right tone is always one parameter away.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional
  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Male and female voices

The selection includes four female and four male voices, providing balanced options for diverse communication needs. Female voices range from the bright and upbeat Nova to the soft, storytelling Luna. Male voices offer energetic options like Felix or the deep, documentary-style Orion. This variety allows banking teams to create distinct audio profiles for different user journeys, such as using Atlas for neutral news updates or Milo for friendly conversational reminders.

Voice characteristics

Each voice is built on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech. When selecting a voice, consider the context of the notification; for example, Sage’s calm instructional tone works well for step-by-step banking guides, while Atlas’s neutral delivery is ideal for factual transactional updates.

Model details

Sound wave illustration for: Model details

VoxBank provides two model variants for your banking notifications. Both utilize the same underlying synthesis engine, ensuring consistent voice quality across your broadcast campaigns regardless of your choice.

tts-1 model

The tts-1 model offers standard generation speed, ideal for high-volume, real-time notifications where latency matters less than throughput.

tts-1-hd model

Choose tts-1-hd for enhanced audio fidelity. This variant is suitable for premium customer communications where subtle vocal nuances improve clarity.

Same engine price

Both models cost $0.01 per 1,000 characters. You pay the same rate regardless of whether you select the standard or high-definition variant, simplifying your cost forecasting.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Her steady pace helps customers follow multi-step instructions without feeling rushed.

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. ISO 639 language codes
  3. Creative Commons Attribution 4.0
  4. curl documentation
  5. LibriVox public-domain audiobooks
  6. openai-node on GitHub
  7. openai-python on GitHub
  8. LibriTTS-R corpus (OpenSLR 141)
  9. TRON developer hub: TRC-20
  10. MDN: Web Speech API
  11. OpenAI API reference: create speech
  12. FFmpeg documentation

More on this site