Transparent Pricing for Game Audio Synthesis

By NPC Audio editorial team · Updated 2026-11-18

NPC Audio uses usage-based billing for game audio synthesis. You pay only for the characters processed, with no minimum spend or balance expiration. This model eliminates fixed monthly costs, making it ideal for indie developers managing variable dialogue volumes across multiple titles.

This page details exactly how character counts are calculated, how to top up via USTRC-20, and what happens when requests fail. It also provides concrete cost examples for NPC dialogue and cutscenes, helping you budget for speech synthesis without licensing overhead.

Transparent Pricing for Game Audio Synthesis

Frequently asked questions

Do spaces and punctuation count towards the character limit?

Yes. Spaces and punctuation count as characters. The price is $10 per 1 million characters, which equals $0.01 per 1,000 characters. This rate applies to the total character count in your input text, including all whitespace and punctuation marks used in the request.

Is there a monthly subscription fee?

No. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you generate. Balances do not expire, and you can top up whenever needed without any recurring billing cycles or subscription commitments.

Can I pay with a credit card?

No. We do not accept credit cards, PayPal, or invoices with VAT. Payments are made exclusively via USDT on the TRON network (TRC-20). You must send the required amount from your wallet to the provided address to credit your account.

What is the minimum top-up amount?

The minimum top-up amount is $5. You can send any amount equal to or greater than $5 using USDT (TRC-20). The balance is credited automatically within minutes after the transfer is confirmed on the blockchain.

How long does the USDT top-up take to process?

Top-ups are credited automatically within minutes after the transfer. Once the USDT transaction is confirmed on the TRON network, your account balance is updated instantly. No manual approval or waiting period is required for deposits.

Do I lose my balance if I don't use it?

No. Your balance does not expire. You can top up and use the credit whenever you need it. There is no expiration date on unused funds, so you can accumulate credit over time without losing it.

Are failed requests charged?

No. If synthesis fails, the charge is returned in full. You are only billed for successful audio generations. Failed requests do not deduct from your balance, ensuring you pay only for usable audio files.

Can I get a refund for unused credit?

Credits remain in your account until used. Refunds for unused balances are not explicitly mentioned, so contact support for specific cases regarding unused funds.

Is there a discount for high-volume studios?

No. The price is a flat $10 per 1 million characters regardless of volume. There are no tiered pricing plans or discounts for high-volume studios. The rate remains consistent for all users, from freelancers to large teams.

Does the price change based on voice model?

No. The model field accepts "tts-1" or "tts-1-hd", both using the same engine and price. There is no price difference between the standard and HD models. All voices and formats are billed at the same character rate.

What happens if I exceed the rate limit?

The rate limit is 60 requests per minute per key. If you exceed this, requests may be processed with delays or rejected. Under load, requests wait in a queue. Exceeding the limit does not incur extra fees, just potential latency.

Is the trial credit valid for all voices?

Yes. The $0.50 trial credit (valid for 7 days) works with all 8 voice presets. You can test any voice, language, or format using the trial balance. It is not restricted to specific models or voices.

Do I need to pay for the API key generation?

No. Generating an API key is free. You only pay for the characters you generate. The key itself does not incur a fee, and you can issue a new key at any time without cost.

Can I invoice my company for the USDT payment?

No. We do not provide invoices with VAT. Payments are made directly via USDT on the TRON network. You are responsible for your own accounting records based on the blockchain transaction, as no official invoice is issued by NPC Audio.

Cost calculator

Estimated cost: $2.50

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

Usage-based billing

Sound wave illustration for: Usage-based billing

NPC Audio bills strictly on usage. You pay $10 per million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. There is no monthly fee, no per-seat license, and no minimum spend. You only pay for the audio you actually generate.

Cost per character count

Cost per character count

Each request processes up to 4,096 characters. If your dialogue exceeds this, split the text and join the resulting audio files. The engine charges for every character sent, including spaces and punctuation marks.

  • $10 per 1,000,000 characters
  • $0.01 per 1,000 characters
  • Spaces and punctuation count

No minimum spend

You can generate a single line of dialogue for a few cents or thousands of hours of narration. There are no tiered plans, no required commitments, and no hidden fees. Your balance covers exactly what you use.

No expiration of balance

Your account balance does not expire. Top-ups via USDT on the TRON network are credited automatically, and the funds remain available indefinitely. You can pause development and resume later without losing your prepaid credit.

Character counting rules

Sound wave illustration for: Character counting rules

The API charges based on the exact character count of the input text, including spaces and punctuation. This predictable model ensures you know exactly what each line of dialogue costs before synthesis begins.

Spaces count as characters

Every space between words is counted toward your total. For example, a simple sentence with ten words contains nine spaces, bringing the total character count to eleven.

Punctuation counts

Commas, periods, exclamation marks, and quotation marks all add to the character count. Special characters and em-dashes are also included in the calculation, so design your text efficiently.

4096 char limit per request

Each API call accepts a maximum of 4096 characters. If your script exceeds this, split it into multiple requests and join the resulting audio files to maintain seamless NPC dialogue.

Short phrases take a few seconds to process, but longer texts may queue under load. Plan your batch sizes accordingly to avoid delays during peak usage.

Character counting rules

Payment methods

Sound wave illustration for: Payment methods

Payments are processed exclusively via cryptocurrency. We use the TRON network, ensuring your balance updates automatically within minutes after the transfer. This approach eliminates the friction of recurring billing cycles or manual approval processes.

There are no monthly subscriptions, seats, or minimum spend requirements. You top up as needed, and your balance never expires. This model suits indie developers and small studios who prefer predictable, pay-as-you-go costs without the overhead of traditional invoicing.

USDT on TRON network

We accept USDT (TRC-20) on the TRON blockchain. Transfers are processed automatically, and your account balance is credited within minutes. The minimum top-up amount is $5, which covers a substantial volume of dialogue generation for prototyping or small-scale projects.

You can transfer funds directly from any wallet supporting TRC-20 tokens, making it easy for global developers to pay regardless of their location.

  • Supported token: USDT (TRC-20) only
  • Automatic credit within minutes
  • Minimum top-up: $5
  • No expiration of balance

No credit cards

We do not store credit card details or process payments through Stripe, PayPal, or similar gateways. This reduces overhead costs and allows us to keep the per-character rate at $10 per million characters. You avoid annual fees or subscription traps.

Without credit card processing, there are no chargeback disputes or monthly billing statements.

No PayPal or invoices

We do not issue invoices or accept PayPal. This streamlined approach is designed for developers who want immediate access to credits without administrative delays. Simply send the USDT, and your API key is ready to use.

There are no VAT invoices or complex tax forms to manage, keeping the integration of billing as simple as the API itself.

Free trial details

Sound wave illustration for: Free trial details

New accounts created via Google sign-in receive an immediate $0.50 trial credit, equating to approximately 50,000 characters. This allows immediate integration testing without payment setup. The credit is valid for 7 days from account creation.

$0.50 credit for Google sign-ins

Google-authenticated accounts start with $0.50 of usable credit. Email-and-password accounts begin with zero balance. Both require a top-up to continue generating audio after the trial is exhausted.

  • Credit amount: $0.50
  • Approximate volume: 50,000 characters
  • Eligible via Google sign-in only

7-day validity period

The trial credit expires exactly 7 days after account creation. Any unused balance is forfeited. This timeframe is sufficient for prototype development and API integration verification.

Email sign-ups start with zero

Users registering with email and password receive no initial credit. A top-up via USDT on the TRON network is required to begin synthesis. This distinction ensures trial credits are tied to verified Google identities.

Free trial details

Refund policy

Sound wave illustration for: Refund policy

Refunds are automatic and immediate. If synthesis fails due to server errors, your balance is restored in full. No manual claim is required.

Failed requests incur zero cost. This ensures you only pay for successfully generated audio files, protecting your development budget from API hiccups.

Failed requests are free

When the API cannot complete a request, the charge is reversed automatically. You are not billed for failed attempts, ensuring accurate billing.

  • Automatic reversal of charges
  • No manual claim needed
  • Billing updates in real-time

Full credit return

The entire amount for the failed request is returned to your account balance. You retain your full credit for future synthesis tasks.

No partial refunds

We do not issue partial refunds for partially generated audio. The refund policy applies strictly to requests that fail entirely before completion.

Cost examples for games

Sound wave illustration for: Cost examples for games

NPC dialogue is often repetitive, making character counting predictable. Pricing is transparent: $0.01 per 1,000 characters, with no minimum spend. Balance never expires, so unused credit carries over indefinitely between projects.

This model eliminates upfront licensing fees for voice actors. You pay only for what you generate, scaling costs directly with your game’s content volume.

Dialogue for 10 NPCs

Assume 500 characters of unique dialogue per NPC. For 10 NPCs, total input is 5,000 characters. At $0.01 per 1,000 characters, the cost is $0.05. This covers all 8 voice presets.

If each NPC has 5 variations, total characters rise to 25,000. Cost: $0.25. No extra fees for switching voices or languages.

  • 500 chars/NPC × 10 NPCs = 5,000 chars
  • Cost: $0.05
  • Includes all 8 voices

Cutscene voiceovers

Cutscenes require precise timing. Generate up to 4,096 characters per request. A 2-minute scene might need 3 requests. Total characters: ~6,000. Cost: $0.06.

Speed varies from 0.25 to 4.0. Faster speeds reduce generation time but not character count. Failed requests are free, so retrying failed lines costs nothing.

  • Max 4,096 chars/request
  • Typical scene: 3 requests
  • Cost: ~$0.06

In-game notifications

Short alerts (e.g., 'Quest complete') are ~20 characters. Generate 1,000 notifications: 20,000 characters. Cost: $0.20. High volume, low cost.

Use speed parameter to match urgency. No per-request fee, only character-based billing. Ideal for dynamic, on-the-fly audio generation.

  • 20 chars/notification
  • 1,000 notifications: $0.20
  • No per-request fee
Cost examples for games

Rate limits and scaling

Sound wave illustration for: Rate limits and scaling

NPC Audio operates on a standard rate limit of 60 requests per minute for each active API key. This throughput is sufficient for most game development workflows, including batch generation of dialogue lines during pre-production or runtime synthesis for non-critical ambient cues. If you exceed this limit, additional requests will be rejected until the window resets.

60 requests per minute

Each API key is capped at 60 requests per minute. New keys start with a lower limit of 10 requests per minute until the first top-up is processed. This baseline handles typical dialogue generation needs without requiring complex batching logic.

  • Limit: 60 requests/minute per key
  • New keys: 10 requests/minute initially
  • Limits reset every 60 seconds

Queue handling

Requests are processed sequentially. If your application sends requests faster than the engine can synthesize them, they will wait in a queue. This ensures deterministic output but means that under heavy load, generation time may exceed the typical real-time speed of 25 characters per second.

No enterprise SLA

We do not offer Service Level Agreements, uptime guarantees, or dedicated priority queues. If the API is busy, your requests may experience variable latency. This model keeps costs low and transparent, suitable for indie developers and small studios who do not require mission-critical 99.99% uptime guarantees.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The game developer hired a freelancer to voice the quirky NPCs in their new fantasy title.

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. Tether (USDT)
  3. W3C WAI: making audio and video accessible
  4. FFmpeg documentation
  5. LibriTTS-R corpus (OpenSLR 141)
  6. IETF RFC 7845: Ogg Opus
  7. Node.js documentation
  8. TRON developer hub: TRC-20
  9. curl documentation
  10. openai-node on GitHub
  11. MDN: Web Speech API
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site