Simple Pay-Per-Character Pricing for Our TTS API

By Playr77 editorial team · Updated 2026-11-18

This page details the transparent pricing structure for the Lumivoice text-to-speech API, designed for indie developers and no-code users who require scalable audio generation without complex infrastructure. You will find exact rates, character counting rules, payment methods via USDT on the TRON network, and details on the free trial available to Google sign-ups. The information is specific to the API’s pay-per-character model, ensuring you understand the cost before integration.

All pricing is usage-based, with no monthly subscriptions, seat limits, or minimum spend requirements. Failed requests are refunded in full, and credits never expire. This page also explains how to manage your balance, rotate API keys, and compare our fixed per-character rate against typical infrastructure costs. Use these facts to estimate your project budget accurately before generating your first audio file.

Simple Pay-Per-Character Pricing for Our TTS API

Frequently asked questions

How are characters counted in the API?

Characters are counted based on the input text sent in the request body. This count includes all letters, numbers, spaces, and punctuation marks. The limit is 4096 characters per request. Longer texts must be split into parts of up to 4096 characters and joined afterwards. Spaces and punctuation count as characters.

Does punctuation count towards the character limit?

Yes, punctuation counts towards the character limit. Spaces also count as characters. The pricing is $0.01 per 1,000 characters, so every symbol contributes to the total usage. Ensure your input text, including all punctuation and spaces, stays within the 4096 character limit per request.

What is the cost per 1,000 characters?

The cost is $0.01 per 1,000 characters. This is equivalent to $10 per 1 million characters. Spaces and punctuation count as characters. Failed requests are free, so you only pay for successful synthesis. This transparent pricing applies to all voice models and response formats.

Can I get a refund if I exceed my budget?

Refunds are not explicitly described for budget overages. However, failed requests are free, and the charge is returned in full. You pay only for successful requests. Ensure you monitor your balance via the dashboard. There are no monthly plans or minimum spend requirements to complicate refunds.

How long does it take for USDT to appear?

USDT on the TRON network (TRC-20) is credited automatically within minutes after the transfer. There are no manual approvals required. The minimum top-up amount is $5. No other payment methods like cards or PayPal are supported. Ensure you send TRC-20 USDT to receive credit.

Is there a minimum balance required?

There is no minimum balance required to use the API. You can use your existing credit until it is exhausted. The minimum top-up amount is $5. Balance does not expire. You can issue a new API key at any time, but the balance remains tied to the account.

Do I pay for failed requests?

No, you do not pay for failed requests. If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures you pay only for usable output. Failed requests do not consume your character allowance or balance.

Can I use multiple API keys for one account?

Yes, you can have one active key per account. A new key can be issued at any time, and the old one stops immediately. You can rotate keys as needed. The account has a rate limit of 60 requests per minute per key. Manage keys via the dashboard.

Does the free trial expire after 7 days?

Yes, the $0.50 free trial credit is valid for 7 days. It is given when you sign in with Google. Accounts created with email and password start without trial credit. The balance does not expire after the trial, but the trial credit itself is time-limited.

Are there discounts for high volume?

There are no volume discounts mentioned. The price is flat at $10 per 1 million characters regardless of usage. There are no monthly plans or seats. Pricing is consistent for all users. You pay exactly $0.01 per 1,000 characters for every request.

Can I mix USDT with other payment methods?

No, you can only top up using USDT on the TRON network (TRC-20). There are no cards, PayPal, or other payment methods supported. No invoices with VAT are available. All balance additions must come from TRC-20 transfers. The balance does not expire.

How do I check my current balance?

You can check your balance on the /get-api-key/ page. The dashboard shows your key, balance, trial status, characters left, and usage history. You can also see a ready curl example. Log in with your Google account or email/password to access this information.

What happens to my unused credit?

Your unused credit does not expire. The balance remains available for future requests. There are no monthly plans or subscriptions that would cause forfeiture. You can use the credit until it is exhausted. Failed requests are refunded, preserving your balance.

Is there a limit on the number of top-ups?

There is no limit on the number of top-ups. You can top up as often as needed. The minimum top-up amount is $5. Credits are added automatically within minutes. You can manage your balance and issue new keys via the dashboard at any time.

Cost calculator

Estimated cost: $2.50

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

Cost Structure

Sound wave illustration for: Cost Structure

The API charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. This usage-based model ensures you pay only for the audio generated, with no monthly subscriptions or minimum spend requirements.

Pay Per Character Rate

Pay Per Character Rate

Each request is billed based on the character count of the input text. The rate remains consistent regardless of the voice selected or the response format chosen.

Character Counting Rules

Character Counting Rules

Spaces and punctuation are counted as characters. Input text is limited to 4096 characters per request. For longer texts, split the input into valid chunks and join the resulting audio files.

Failed Request Credits

Failed Request Credits

If synthesis fails due to technical errors, the charge is returned in full. You are not billed for audio that is not successfully delivered.

Payment Methods

Sound wave illustration for: Payment Methods

Payments are processed exclusively via USDT on the TRON network (TRC-20). We do not accept credit cards, PayPal, or traditional bank transfers. This method ensures direct, low-friction funding for your API account without intermediary banking delays or currency conversion fees.

USDT on TRON Network

Send USDT using the TRC-20 standard to the address provided in your dashboard.

  • Accepted currency: USDT (TRC-20)
  • No credit cards or PayPal

Minimum Top-up Amount

The minimum top-up amount is $5. There is no monthly spend requirement or mandatory subscription tier. You fund the account only when you need capacity for your next batch of audio generations.

  • Minimum deposit: $5
  • No minimum monthly spend

Instant Credit Activation

Credits are activated automatically within minutes after your blockchain transfer is confirmed. Once credited, the balance is immediately available for API requests. Your balance does not expire, allowing you to top up whenever convenient.

Free Trial

Sound wave illustration for: Free Trial

Developers can begin testing immediately with a free trial account. Signing up via Google grants $0.50 in credit, sufficient for approximately 50,000 characters. This allows verification of voice quality and API integration without requiring a payment method upfront.

Google Sign-up Bonus

Upon creating an account through our Google authentication flow, users receive an automatic credit of $0.50. This balance is applied instantly and can be used to generate audio files using any of the eight available voices or formats.

  • Automatic credit application upon Google login
  • Sufficient for ~50,000 characters of synthesis
  • No credit card required to start

Trial Duration and Limits

The trial credit remains active for seven days from the time of account creation. After this period, any remaining unused balance expires. This timeframe is designed to allow developers enough time to validate the API’s performance during a standard integration sprint.

  • 7-day validity period from sign-up
  • Unused balance expires after 7 days
  • Standard API limits apply during trial

Email Sign-up Balance

Accounts created using an email address and password do not receive the initial trial credit. These accounts start with a zero balance, requiring an immediate top-up via USTRC-20 to begin generating audio.

Volume Efficiency

Sound wave illustration for: Volume Efficiency

Lumivoice processes long texts by splitting them into parts of up to 4096 characters. The system joins the resulting audio files seamlessly, allowing you to generate full-length content without manual intervention.

Bulk Text Processing

Requests are processed sequentially. Under heavy load, a request may wait in a queue. This linear processing ensures consistent output quality regardless of the total volume.

Cost per Minute Estimate

At $0.01 per 1,000 characters, generating one minute of audio costs approximately $0.25, based on the typical speed of 25 characters per second. This rate applies uniformly across all eight voice presets and language combinations.

No Minimum Spend

There is no minimum spend requirement. You pay only for the characters you consume. Short phrases may take a few seconds to generate, while longer texts take roughly real-time duration.

Volume Efficiency

No Hidden Fees

Sound wave illustration for: No Hidden Fees

Our pricing model eliminates recurring financial commitments. You pay only for the characters you actually process, ensuring your costs scale directly with your usage. There are no mandatory monthly subscriptions or recurring fees to maintain access to the API.

The structure is designed for indie developers who prefer predictable, usage-based expenses without the overhead of flat-rate plans that may charge for unused capacity.

No Monthly Subscriptions

We do not require any monthly subscription to keep your account active. Your access remains open as long as you have sufficient balance, allowing you to pause or resume usage without penalty or loss of integration setup.

No Seat Limits

There are no limits on the number of team members or developer seats who can use your API key. Whether one developer or ten are integrating the TTS API, the rate per character remains consistent regardless of team size.

No VAT Invoices

We do not issue invoices with VAT. This simplifies accounting for small teams and indie studios that may not have dedicated finance departments to manage complex tax documentation or reconcile recurring subscription bills.

Balance Management

Sound wave illustration for: Balance Management

Monitor your account status via the dashboard, which displays your current balance, remaining characters, and usage history. This transparent view allows you to manage consumption without guessing or waiting for end-of-cycle reports.

Real-time Usage Tracking

The dashboard provides immediate visibility into your account state. You can view your current balance, characters remaining, and a log of past requests. This data is available in your account history, ensuring you always know your exact standing.

  • View current balance and character count
  • Access detailed usage history
  • Track request status in real time

Expiration of Credits

Your main balance does not expire. Once topped up with USDT, the funds remain available indefinitely until used. This ensures you can pause usage without losing your investment, ideal for long-term projects with irregular audio generation needs.

  • Main balance has no expiration date
  • Funds remain available indefinitely

Key Rotation Impact

You can issue a new API key at any time. When a new key is generated, the old key stops working immediately. All usage history and balance remain tied to your account, so switching keys does not affect your stored data or remaining credits.

  • Old key invalidates instantly
  • Balance persists across key rotations
  • Usage history remains intact

Comparison to Alternatives

Sound wave illustration for: Comparison to Alternatives

Competing platforms often impose monthly minimums or tiered subscriptions. Our model charges strictly per character processed, ensuring you pay only for what you generate.

By aligning with the OpenAI SDK format, we allow the use of official OpenAI SDKs. Developers can switch providers or integrate existing tools without rewriting code, reducing initial setup time and ongoing maintenance overhead.

Fixed vs. Usage-Based Pricing

Subscription models require paying for capacity you may not use, especially during low-traffic periods. Our pay-per-character structure scales linearly with demand. If you process zero requests, your cost is zero, eliminating the risk of wasted monthly spend.

This approach is particularly efficient for indie developers whose audio generation needs fluctuate. You avoid the overhead of maintaining a premium tier during quiet months, paying only when your application actively synthesizes text.

  • No monthly minimums or commitment periods
  • Cost scales directly with character volume
  • Ideal for variable traffic patterns

SDK Compatibility Savings

Our API mirrors the OpenAI speech endpoint structure. This allows direct usage of official OpenAI SDKs by simply changing the base URL. Developers avoid the engineering cost of building and maintaining a proprietary client library.

Standardized request shapes mean that integrating our TTS service into existing Python, Node.js, or Go applications requires minimal code changes. This reduces developer hours spent on debugging custom transport layers or authentication handlers.

  • Compatible with official OpenAI SDKs
  • No custom client library required
  • Standard JSON request/response format

Infrastructure Costs

Unlike self-hosted solutions, we manage the inference servers, storage, and scaling infrastructure. You do not need to provision GPU instances or manage server uptime for each language variant.

Generated audio is returned directly in the response and not stored by us, reducing your long-term storage costs. You retain full control over where you save the final MP3, WAV, or OPUS files.

  • No GPU instance management
  • No server maintenance overhead
  • Direct response audio delivery

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

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. Python documentation
  3. MDN: Web Speech API
  4. Creative Commons Attribution 4.0
  5. FFmpeg documentation
  6. IETF RFC 7845: Ogg Opus
  7. Tether (USDT)
  8. LibriTTS-R corpus (OpenSLR 141)
  9. curl documentation
  10. W3C WAI: making audio and video accessible
  11. openai-node on GitHub
  12. Node.js documentation

More on this site