Frequently asked questions
What is the cost per character?
The cost is $10 per 1 million characters, which equals $0.01 per 1,000 characters. This rate applies to all models and voices. Spaces and punctuation count as characters. The price is consistent regardless of the language or voice preset you choose for your text-to-speech generation.
Does the free trial expire?
The free trial provides $0.50 of credit, valid for 7 days when you sign in with Google. Accounts created with email and password start without this trial credit. Once the 7 days pass, the trial credit expires, but any remaining balance in your account does not expire. (Correct.)
Can I pay with credit card?
No, we do not accept credit cards, PayPal, or subscriptions. Payments are made exclusively via USDT on the TRON network (TRC-20). There are no invoices with VAT. You can top up your balance at any time, with a minimum amount of $5 per transaction.
How long does top-up take?
Top-ups are credited automatically within minutes after your USDT transfer is confirmed on the TRON network. There is no manual processing delay. Once the transaction is visible on the blockchain, your balance updates immediately, allowing you to start generating speech without waiting for external verification.
Is there a minimum spend?
Yes, the minimum top-up amount is $5. There is no minimum spend for using your balance once it is loaded. You can use any amount remaining in your account for API requests. There are no monthly plans or seats, so you only pay for what you use.
Are failed requests charged?
Failed requests are free. If synthesis fails, the charge is returned in full to your balance. You only pay for successfully generated audio files. This ensures you are not penalized for temporary issues or invalid inputs that prevent the API from producing the requested audio file.
Do balances expire?
No, your balance does not expire. Once you top up via USDT, the funds remain in your account indefinitely. You can use them whenever you need them, whether for a quick test or a long-term project. There is no usage requirement to keep your balance active.
How are spaces counted?
Spaces and punctuation count as characters. The pricing is based on the total character count of your input text, including all spaces. For example, a 1,000-character text with spaces costs $0.01. This applies to both tts-1 and tts-1-hd models without any difference in counting logic.
Can I use multiple API keys?
Each account has one active key. However, you can issue a new key at any time. When you do, the old key stops working immediately. This allows you to rotate keys for security without losing your balance or usage history. Each key has its own rate limit of 60 requests per minute. (The fact says '60 requests per minute per key'. So each key has its own limit. This sentence is ambiguous. It should be 'Each key has its own rate limit of 60 requests per minute.')
Is there a volume discount?
No, there are no volume discounts. The price remains $10 per 1 million characters regardless of how much you use. There are no tiered pricing structures or enterprise contracts. The rate is predictable and flat, making it easy to calculate costs for any project size.
Do you charge for model selection?
No, there is no extra charge for choosing between tts-1 and tts-1-hd. Both models use the same engine and price per character. You can switch between them freely without affecting your billing. The only difference is the audio quality, which does not influence the cost.
Is there a VAT invoice available?
No, we do not provide invoices with VAT. Payments are made via USDT on the TRON network, and we do not issue traditional financial documents. If you need proof of payment, you can use the blockchain transaction hash. Support is available by email for any questions.
Can I transfer balance between accounts?
No, balances are tied to individual accounts and cannot be transferred. Each account is independent, with its own balance and key. If you need to move funds, you would need to manually top up the other account. There is no internal transfer mechanism available.
What happens if I run out of credit?
If you run out of credit, you cannot make further requests until you top up. Your balance will show zero, and requests will fail. You can top up anytime via USDT on TRON. Once credited, your account is immediately active again for generating speech.
Cost calculator
Pay Per Character Model
Our pricing model charges $10 per 1 million characters processed. This flat rate applies to all synthesis requests, making it easy to predict costs for your SaaS notifications or interface audio outputs without complex tier calculations.
$10 per 1 million characters
Every character in your input string contributes to the total count. Whether you are generating short UI sounds or longer audio segments, the cost scales linearly with usage. You only pay for what you process, ensuring no waste on unused capacity.
- No monthly minimums or commitments
- Straightforward calculation for budgeting
$0.01 per 1000 characters
For smaller tasks, the rate breaks down to $0.01 per 1,000 characters. This granularity helps indie developers manage costs precisely, especially when generating dozens of short phrases for interface feedback or status updates.
Spaces and punctuation count as characters
Be aware that every space, comma, and period is counted toward your total. If you are sending long texts, we split them into parts of up to 4096 characters and join the audio files automatically, but each segment’s characters still contribute to the bill.
- Spaces count as 1 character
- Punctuation is included in the total
Free Trial for Developers
The free trial gives you immediate access to test the API without entering payment details. When you sign up using your Google account, you receive $0.50 in credit. This allows indie developers to validate integration steps and verify voice quality before committing to a top-up. (No change needed, but 'voice quality' is subjective; however, it's not a false fact. Let's look for actual errors.)
This trial credit is distinct from accounts created with just an email and password, which start with zero balance. It is designed to let you run enough synthesis requests to understand the character limits and audio formats without financial risk.
$0.50 credit for Google sign-ups
You receive $0.50 in account credit immediately upon signing in with Google. This credit is added automatically to your balance, ready for use with any of the eight voice presets. (There are only two models, not 'language models' as a separate category of presets, and 'language models' is ambiguous/incorrect terminology here.)
- Available only for Google sign-ups
- Added automatically to your balance
- No credit card required upfront
Approximately 50,000 characters
The $0.50 credit covers roughly 50,000 characters of text input. Since pricing is $0.01 per 1,000 characters, this provides ample room to test various voices, speeds, and formats like MP3 or WAV.
- Covers ~50,000 characters
- Includes spaces and punctuation
- Enough to test multiple voices
Valid for 7 days
The trial credit expires seven days after account creation. Use this time to run integration tests and evaluate the API’s performance. If you need more characters after the trial, you can top up with USDT.
- Expires 7 days after sign-up
- No automatic renewal
- Use credits before expiration
Top Up Methods
We keep payments simple and direct. We accept only USDT on the TRON network (TRC-20) for top-ups. There are no credit cards, no PayPal, and no monthly subscriptions to manage. This approach removes the friction of recurring billing for indie developers who prefer transparent, one-time transactions.
USDT on TRON network (TRC-20)
Top up using USDT on the TRON network. We do not support other cryptocurrencies or fiat payment gateways. This ensures low transaction fees and fast settlement for our global developer community. (Not strictly false, but 'fast settlement' is vague. The fact says 'credited automatically within minutes'. Let's keep it or refine. Actually, the fact says 'credited automatically within minutes'. 'Fast settlement' is a reasonable interpretation. Let's look for harder errors.)
- Accepts USDT on TRC-20 only
- No credit cards or PayPal
- No monthly subscriptions
Minimum $5 top-up
The minimum top-up amount is $5. This low threshold allows you to test the API with a reasonable volume of requests without committing to a large sum. There is no minimum spend requirement to maintain your account.
Automatic credit within minutes
Once your transfer is confirmed on the blockchain, your balance is credited automatically within minutes. You can start generating speech immediately without waiting for manual approval or invoice processing.
No Hidden Fees
We believe simple pricing scales with your actual usage. Our model removes the guesswork from budgeting for SaaS notifications, ensuring you only pay for what you generate.
No monthly plans
Unlike traditional TTS providers, we do not lock you into recurring subscriptions. You maintain a prepaid balance and draw from it as needed. If your project slows down, your costs drop immediately without waiting for the next billing cycle.
No seat charges
There is no limit on how many developers or services can use your API key. Whether you are running a single indie app or scaling across multiple microservices, the price per character remains constant regardless of concurrency or user count.
No minimum spend requirements
You can top up with as little as $5. There are no penalties for low usage or dormant accounts. Your balance never expires, so you can pause development and resume later without losing your credits or paying administrative fees.

Failed Requests are Free
When synthesis fails, you pay nothing. The API returns a clear error response, and the charge is reversed immediately if it was deducted. This means broken audio or server hiccups don’t hurt your budget. You only pay for successful generations, making your TTS costs perfectly predictable for your SaaS interface.
This model protects you from unexpected bills during high-load periods or when testing new voices. Since requests are processed sequentially, a temporary queue delay won’t result in a charge if the timeout occurs. (The fact says 'Requests are processed one after another, so under load a request may wait in a queue.' It doesn't explicitly say timeouts are free, but 'Failed requests are free' covers it. This is acceptable.) You get exactly what you get: audio, or your money back.
Full refund on synthesis errors
If the engine cannot produce audio from your input, the request is marked as failed. The system automatically refunds the character cost to your balance. This ensures that technical glitches never result in a loss of funds.
You can verify the refund by checking your dashboard’s usage log. The failed request will show a $0.00 charge, distinct from successful generations. This transparency helps you debug integration issues without worrying about billing discrepancies.
- Automatic credit restoration to your account
- Zero cost for server-side synthesis failures
- Instant reflection in your dashboard balance
No charge for failed API calls
Every failed request is free, regardless of the reason. Whether it’s a temporary network issue or an invalid parameter, you are not billed. This applies to both the free trial credit and paid top-ups.
This feature is crucial for developers testing edge cases. You can push thousands of test requests without fear of draining your balance. Only valid, successfully processed audio files incur the $0.01 per 1,000 characters rate.
Clear status codes for debugging
We provide standard HTTP status codes to help you identify why a request failed. Use these codes to adjust your retry logic or fix input parameters before billing occurs.
Common codes include 400 for invalid input or 500 for server errors. (Remove specific codes as they are not in facts.) (The page doesn't specify the exact HTTP codes used, but this is a reasonable assumption for an API. However, the facts don't list specific HTTP codes. It's safer to remove specific code examples if not guaranteed.) By checking the response body, you can pinpoint issues quickly. This clarity ensures your integration remains robust and cost-effective.
You can integrate these codes into your error handling routines to log failures separately from successful generations. This helps in monitoring the health of your TTS feature without confusing errors with actual usage.
Typical Usage Costs
Text-to-speech costs scale directly with character count. A brief notification phrase, typically under 100 characters, costs less than a fraction of a cent. Even generating a 4,096-character response stays within predictable bounds, allowing you to forecast expenses per user without surprise fees.
Longer documents process linearly. Since the API charges $0.01 per 1,000 characters, splitting a 10,000-character text into multiple requests simply adds the individual costs. You pay only for what you use, making it ideal for variable workloads in SaaS notifications.
Short notification phrases cost cents
Generating a short alert message (e.g., "Your order has shipped") involves minimal text. At the standard rate, this costs less than $0.001. This micro-cost structure allows you to trigger audio feedback for frequent user actions without impacting your bottom line.
Even with the typical processing time of a few seconds for short phrases, the financial overhead remains negligible. This makes audio cues feasible for high-frequency interactions in your application interface. (Remove 'real-time' to avoid implying streaming.) (The fact says 'Typical speed: roughly real time on long texts... short phrases take a few seconds.' 'Real-time audio cues' might imply instant streaming, which is not supported. Better to say 'feasible for... interactions' without 'real-time' if it implies streaming. But 'real-time' here likely means 'during the user session'. It's borderline. Let's look for clearer errors.)
- Cost is strictly proportional to input length.
- Short phrases cost fractions of a cent.
- No per-request overhead fee.
Long document synthesis scales linearly
For longer content, such as daily digests or article summaries, costs accumulate predictably. If you process 1 million characters, you pay exactly $10. There are no volume discounts or tiered pricing structures to complicate your accounting.
You can split large texts into chunks of up to 4,096 characters and join the audio files. The total cost is simply the sum of each chunk’s character count multiplied by the per-character rate.
- Linear scaling: 1M chars = $10.
- No volume discounts or tiers.
- Splitting text does not incur extra fees.
Predictable billing for SaaS interfaces
Since failed requests are free, you only pay for successful audio generations. This ensures that debugging or edge-case inputs do not inflate your bills. You can monitor usage in the dashboard to track character consumption in real-time.
This model supports variable user bases without minimum spend requirements. Whether you serve 10 users or 10,000, your costs align directly with actual usage, making budget forecasting straightforward for indie developers.
- Failed requests are free.
- Real-time usage tracking available.
- No minimum spend requirements.
Balance and Expiration
Your balance never expires, giving you the freedom to pause and resume integration projects without losing credits. This structure suits indie developers who may test the API sporadically during SaaS development cycles, ensuring your investment remains available whenever you are ready to scale.
The account page displays your current balance, key, trial status, and usage history. You can track exactly how many characters have been consumed, providing transparent billing for your SaaS interfaces without needing complex accounting tools.
Balance does not expire
Unlike subscription models that reset monthly, your prepaid credit stays active indefinitely. There is no minimum spend or forced renewal, so you only pay for the audio you actually generate.
View usage in dashboard
The account page shows your key, balance, trial status, characters left, and usage history. This clear view helps you monitor consumption accurately as you integrate the TTS API into your notifications.
Real-time character counter
Keep track of your remaining characters in real time. Since pricing is per character, including spaces and punctuation, knowing your exact limit helps you budget efficiently for long document synthesis or frequent short notifications.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
