Cloud TTS API: Transparent Pricing & USDT Payments

By Kiriya Editorial Team · Updated 2026-11-19

Kiriya Editorial’s transparent pricing details the cost structure for our cloud Text-to-Speech API, designed specifically for digital agencies building voice-enabled features for online stores. We break down how character usage translates to billing, so you can predict audio production costs before committing to a client project.

This page outlines our straightforward $0.01 per 1,000 characters model, supported by USDT payments on the TRON network. We cover trial credits, rate limits, and integration tips to help you evaluate whether our reliable, OpenAI-compatible API fits your agency’s workflow for e-commerce audio features.

Cloud TTS API: Transparent Pricing & USDT Payments

Frequently asked questions

How is the character count calculated?

We charge $0.01 per 1,000 characters, including spaces and punctuation. The rate is $10 per 1 million characters. Every character sent in the input field counts toward this total, ensuring transparent billing based on the exact text processed.

Does the trial credit expire?

Yes. The $0.50 trial credit is valid for 7 days. It is granted when you sign in with Google. Accounts created with email and password start without this trial credit. The balance does not expire once purchased, but the initial trial credit has a strict seven-day validity period.

Can I pay with a credit card?

No. We accept USDT on the TRON network (TRC-20) only. There are no credit cards, PayPal, or subscriptions. Payments are processed directly via blockchain transfer. This approach eliminates traditional payment gateway fees and allows for immediate, borderless top-ups without requiring a bank account or card details.

Is there a minimum spend?

The minimum top-up amount is $5. There is no minimum spend for using your balance. You can use any amount remaining in your account. We do not require monthly plans or seats, allowing you to pay only for the characters you actually generate for your online store projects.

Do I need to pay VAT?

No. Our pricing model excludes invoices with VAT. The rates listed are final. This simplifies accounting for digital agencies and developers who integrate our TTS API into their client websites. You pay the exact character rate without additional tax calculations or complex invoicing requirements for each transaction.

How long does USDT top-up take?

Top-ups are credited automatically within minutes after the transfer. We monitor the TRON network for incoming TRC-20 USDT transactions. Once confirmed, your balance updates immediately. This ensures you can start generating audio for your e-commerce clients without waiting for manual processing or banking delays typical of traditional payment methods.

What happens if I exceed my balance?

Requests will fail if you do not have sufficient funds. Failed requests are free, so you are not charged for failed attempts. You must top up your USDT balance to resume service. There is no overage charge; you simply stop generating audio until your account balance covers the character cost.

Are failed requests charged?

No. If synthesis fails, the charge is returned in full. You only pay for successfully generated audio files. This protects your budget when testing voices or handling edge cases in your online store’s audio features. The system ensures you are billed only for usable output delivered to your application.

What is the rate limit for requests?

You are limited to 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. These limits apply to your API key. If you exceed the limit, requests may queue or fail. This ensures fair usage for all developers building voice-enabled features for online stores.

Can I rotate my API key?

Yes. You can issue a new key at any time from your dashboard. When a new key is issued, the old one stops working immediately. Each account has one active key at a time. This allows you to secure your integration if a key is exposed or needs rotation for your clients.

Which languages are supported?

We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If a language is not listed, it is not supported. You can specify the language code or let the system guess from the script.

Can any voice speak any language?

Yes. Every voice preset can speak any of the 23 supported languages. You do not need to match the voice to the language. For non-English Latin-script text, you should set the language parameter explicitly. This flexibility allows you to use consistent voice branding across different language versions of your online store.

What audio formats are available?

We support mp3, wav, opus, flac, and pcm formats. You specify the format using the response_format field in your request. These formats cover most use cases for web and mobile applications. Each generated file is returned directly in the API response, allowing immediate playback or storage in your e-commerce platform.

Is there a limit on text length per request?

Yes, each request supports up to 4096 characters. For longer texts, you must split the text into parts and join the resulting audio files. This limit applies to the input field. We recommend chunking long product descriptions or blog posts to ensure reliable generation and proper audio continuity for your users.

Cost calculator

Estimated cost: $2.50

Spaces and punctuation count as characters. $10 per 1 million characters. Failed requests are free.

Simple Character-Based Pricing

Sound wave illustration for: Simple Character-Based Pricing

Cloud text-to-speech billing is calculated strictly by character count, not by audio duration or request volume. The standard rate is $0.01 per 1,000 characters, providing a clear, linear cost structure for agencies managing multiple client projects. This model eliminates the complexity of tiered pricing or varying costs based on voice selection.

$0.01 per 1,000 characters

$0.01 per 1,000 characters

Each character in your input text contributes directly to the final charge. This includes letters, numbers, punctuation marks, and spaces. The API processes up to 4096 characters per request.

  • Standard rate: $0.01 per 1,000 characters
  • Applies to all models (tts-1 and tts-1-hd)
  • No volume discounts or tiered brackets

Spaces count as characters

Spaces count as characters

Unlike some speech synthesis services that ignore whitespace, our API counts every character in the input string. A space between words, a comma, or a newline character all contribute to the total character count. This ensures that the billed amount accurately reflects the exact input processed by the synthesis engine.

  • Spaces, punctuation, and symbols are billable
  • Exact input length determines cost
  • No hidden character exclusions

Predictable costs

Agencies can forecast audio production expenses with precision. By counting characters in your content strategy, you know the exact cost before sending a request. There are no surprise fees for processing time or server load, making budgeting for e-commerce voice features straightforward.

  • Linear pricing model
  • Easy to estimate per-project costs
  • No hidden usage fees

Trial Credit for Agencies

Sound wave illustration for: Trial Credit for Agencies

New agency accounts can immediately test the API quality without financial commitment. Upon signing in with Google, the system automatically issues a $0.50 trial credit, equivalent to approximately 50,000 characters of text synthesis.

$0.50 free trial credit

The trial balance covers standard generation requests, allowing you to experiment with different voices and formats. You can generate up to 50,000 characters to assess how the API handles product descriptions or customer service scripts within your client’s online store interface.

Google sign-in required

To receive this initial credit, you must create an account using Google authentication. Accounts established via email and password do not receive this trial balance. This method ensures a quick, verified setup for agencies ready to start testing immediately.

Valid for 7 days

The trial credit expires seven days after account creation, regardless of whether you have used it. If the credit remains unused after this period, it is removed from your account. This timeframe is designed to encourage rapid evaluation and integration decisions.

Payment with USDT

Sound wave illustration for: Payment with USDT

Top-ups are processed exclusively via the TRON network using the TRC-20 USDT standard. This single-network approach keeps transaction fees low and ensures that your agency’s payment infrastructure remains simple without requiring support for multiple cryptocurrency chains or complex exchange conversions.

TRON network only

Only USDT on the TRON blockchain is accepted for funding your account. There are no options for credit cards, PayPal, or other fiat gateways, which eliminates currency conversion delays and third-party payment processor fees.

  • USDT on TRON (TRC-20) only

Minimum $5 top-up

The minimum deposit amount is $5. This low threshold allows small agencies to test the API with a modest initial investment before scaling up their voice-enabled features for online store clients.

Automatic credit

Once the blockchain transaction is confirmed, the balance is credited automatically within minutes. There is no manual invoice review or waiting period, so your team can immediately begin generating audio files without administrative delays.

No Hidden Fees

Sound wave illustration for: No Hidden Fees

The API charges strictly per character processed, with no recurring subscription fees or mandatory monthly commitments. You pay only for the audio generated during active usage, making it easy to align costs directly with your agency’s output volume.

No monthly plans

Unlike traditional SaaS products, there are no base fees for maintaining an account or access to the API. Whether you generate 1,000 characters or 1 million, the rate remains constant at $0.01 per 1,000 characters. This model eliminates the risk of paying for idle capacity during quiet periods.

  • No recurring subscription fees
  • Pay only for actual usage
  • Cost scales linearly with volume

No minimum spend

There is no required minimum balance or minimum monthly usage threshold. Agencies can top up with small amounts if needed, though the minimum USDT transfer is $5. This flexibility allows you to test the API with minimal upfront commitment before scaling up for larger client projects.

  • No minimum monthly usage requirement
  • No mandatory annual contracts
  • Flexible top-up amounts

No VAT invoices

Payments are processed directly via cryptocurrency, so standard VAT invoices are not issued. This simplifies the billing process for digital agencies operating internationally, as there is no need to manage tax documentation for recurring software subscriptions. The balance in your account does not expire, ensuring your funds are available whenever you need them.

  • No VAT invoices
  • No tax documentation for subscriptions
  • International payment simplicity

Cost Examples

Sound wave illustration for: Cost Examples

Predictable costs enable agencies to budget voice features accurately. Our character-based model charges $0.01 per 1,000 characters, including spaces and punctuation. This simplicity removes ambiguity from client invoices.

Short product descriptions

A typical product description of 500 characters costs $0.005. Even with multiple voices for variety, costs remain negligible per item.

Long audio books

Splitting texts into 4,096-character chunks ensures reliable processing. At roughly real-time speed, long narratives generate predictably.

High-volume campaigns

For large-scale notifications, batch processing keeps expenses linear. With 60 requests per minute, you can scale efficiently without overpaying for idle capacity.

Cost Examples

Failed Requests Are Free

Sound wave illustration for: Failed Requests Are Free

Synthesis errors do not cost you. If the API returns an error status, the charge is returned in full. You pay only for successful audio generation.

This protects your budget during development or when processing edge-case inputs. You are never charged for failed requests, ensuring accurate billing based on actual output.

Full charge return

Every failed request triggers a refund. This applies to any error returned by the speech endpoint.

The refund is automatic and reflects in your balance.

  • Automatic credit for any failed request
  • Immediate reflection in your account balance
  • No manual claim required

No character deduction

Characters consumed by a failed request are not deducted from your total. Only characters in successfully generated audio files count against your limit.

This ensures your usage statistics remain accurate and you never pay for audio that wasn’t delivered.

Error handling

Implement standard retry logic for transient errors. Since failed requests are free, you can retry safely without inflating costs.

Use the response status to distinguish between temporary issues and permanent failures, optimizing your integration workflow.

Balance Management

Sound wave illustration for: Balance Management

Managing your API key and balance ensures uninterrupted service for your agency’s voice-enabled features. Since balances never expire, you can top up once and use the credit whenever needed, regardless of project timelines.

Usage tracking allows you to monitor character consumption and request volumes. You can rotate keys instantly to invalidate the current one, ensuring precise control over billing and access.

No expiration of balance

Your account balance does not expire, allowing you to top up and use credits at your own pace. There is no monthly plan or minimum spend requirement, so unused funds remain available indefinitely.

This structure suits agencies with variable project cycles, ensuring capital is not wasted on unused subscription periods.

  • Funds remain valid indefinitely

Real-time usage tracking

The dashboard provides visibility into your balance, characters remaining, and recent request history. This transparency helps agencies forecast costs accurately without waiting for end-of-month reports.

Usage data includes request timestamps and status, allowing you to identify patterns or anomalies in character consumption.

Key rotation available

You can issue a new API key at any time from the dashboard. The previous key stops working immediately, providing instant security control if a key is exposed or no longer needed.

This feature allows for seamless key management.

Agency Integration

Sound wave illustration for: Agency Integration

Agencies building voice features for online stores can integrate using the OpenAI SDK. By simply updating the base_url to https://api.kiriya.info/v1, your existing code works immediately without needing a custom library or browser extension.

This compatibility ensures your developers use familiar patterns while accessing our reliable cloud TTS API. You get predictable costs and a straightforward workflow for generating audio files for product descriptions or customer support prompts.

OpenAI SDK compatible

Use the standard OpenAI SDK by pointing it to our API base. No custom client libraries are required, making integration fast for teams already familiar with the OpenAI ecosystem.

  • Same request shape as OpenAI
  • Update base_url only
  • No custom SDK needed

Rate limits per key

Each API key is limited to 60 requests per minute. Before your first top-up, this limit is 10 requests per minute. This ensures fair usage while allowing your agency to scale as your clients grow.

Requests are processed sequentially, so under heavy load, synthesis may queue slightly. Plan your audio generation schedules accordingly for large campaigns.

  • 60 requests/minute after top-up
  • 10 requests/minute initially
  • Sequential processing

Multi-voice support

Select from 8 distinct voices, including female options like Aria and Nova, and male options like Felix and Milo. Each voice can speak any of the 23 supported languages, allowing you to localize content without managing multiple audio files.

Specify the voice and optional language in your JSON body to tailor the audio experience for different regions or brand tones.

  • 8 preset voices
  • 23 languages supported
  • No voice cloning needed

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The following examples illustrate how to implement each approach using standard tools available to modern web developers.

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. Node.js documentation
  3. Tether (USDT)
  4. openai-node on GitHub
  5. ISO 639 language codes
  6. IETF RFC 7845: Ogg Opus
  7. Creative Commons Attribution 4.0
  8. MDN: Web Speech API
  9. LibriVox public-domain audiobooks
  10. W3C WAI: making audio and video accessible
  11. OpenAI API reference: create speech
  12. TRON developer hub: TRC-20

More on this site