Frequently asked questions
How much does narrator text to speech cost?
The cost is $10 per 1 million characters, which equals $0.01 per 1,000 characters. This rate applies to both the tts-1 and tts-1-hd models. The price is consistent regardless of the voice selected or the audio format generated.
Do I have to pay a monthly subscription fee?
No, there are no monthly plans or subscriptions. You pay only for the characters you consume. There are no seats or minimum spend requirements. This pay-as-you-go model allows tourism startups to scale audio production costs directly in line with their content output without fixed overheads.
What is the minimum top-up amount?
The minimum top-up amount is $5. This applies when adding funds via cryptocurrency. There is no minimum spend for using your balance, so you can use small amounts for testing or small museum audio guide batches without committing to large upfront investments.
Which cryptocurrency is accepted for payment?
We accept USDT on the TRON network (TRC-20) only. No other cryptocurrencies, credit cards, or PayPal are supported. This single payment method simplifies the billing process for international tourism startups, avoiding multiple currency conversion fees and reducing administrative complexity for your accounting team.
Are failed requests charged to my balance?
No, failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successfully generated audio files. It protects your budget during peak usage when queueing might cause temporary delays.
Does my balance expire after 7 days?
No, your balance does not expire. Only the $0.50 free trial credit, valid for 7 days, has an expiration date. Top-up funds remain available indefinitely. This allows museum curators to pause audio production projects without losing their prepaid credit for future audioguide updates.
How are characters counted in the text?
Spaces and punctuation count as characters. The limit is 4096 characters per request. Longer texts must be split into parts and joined. This precise counting method ensures accurate billing. For example, a 1,000-character script costs exactly $0.01, including all spaces and punctuation marks.
Is there a volume discount for large museums?
No, there is no volume discount. The price is a flat $10 per 1 million characters regardless of usage volume. There are no tiered pricing structures or enterprise contracts. Large museums pay the same per-character rate as small tourism startups, ensuring consistent cost predictability.
Can I switch payment methods after top-up?
We accept only USDT on the TRON network. There are no other payment methods to switch to. Once you top up, your balance is credited automatically. You cannot switch to credit cards or PayPal later because they are not supported options for this API.
What happens if I exceed the rate limit?
The limit is 60 requests per minute per key (10 per minute before the first top-up). Requests are processed sequentially, so exceeding the limit may cause your requests to wait in a queue. You are not charged extra for waiting; you simply wait for processing.
Do I get a refund if the audio is silent?
Refunds are issued only if the request fails. If the audio is generated successfully but is silent due to your input or voice settings, it is not considered a failure and is charged. The system returns the charge in full only upon synthesis failure.
Can I use my own API key for billing?
Each account has one active API key. You can issue a new key at any time, which stops the old one immediately. Billing is tied to your account balance, not the specific key. You can rotate keys for security without affecting your billing history or balance.
Is there a VAT invoice available?
No, there are no invoices with VAT. We do not provide traditional billing invoices. Payment is made via cryptocurrency, and the transaction record serves as proof of payment. This simplifies accounting for international tourism startups that may not require local tax documentation.
How long does it take for USDT to appear?
Funds are credited automatically within minutes after the transfer. We do not offer manual review. Once the TRON network confirms your USDT transaction, your balance updates immediately. This ensures rapid availability of funds for your tourism audio production workflows.
Cost calculator
Standard Pay-Per-Character Model
Tourism startups and museum curators can predict audio production costs with precision using our standard pay-per-character model. The rate is fixed at $0.01 per 1,000 characters. A standard 30-second audioguide typically contains about 750 characters and costs approximately $0.0075. This linear pricing eliminates uncertainty for budgeting large-scale audio content projects.
Cost Breakdown: $0.01 Per 1,000 Characters
Our API charges strictly by volume, not by request count or voice model complexity. Whether you choose the standard "tts-1" or high-definition "tts-1-hd," the price remains identical. This consistency allows you to allocate budget across multiple languages without worrying about premium voice tiers.
Character Count Includes Spaces and Punctuation
Every character in your input text contributes to the final cost, including spaces, commas, and periods. For example, a 10,000-character script for a museum tour description incurs a base cost of $0.10. You can estimate your budget by counting characters in your draft scripts before sending them to the API.
No Hidden Fees for Format Conversion
The base price covers audio generation regardless of your chosen output format. You can request MP3, WAV, Opus, FLAC, or PCM files without any additional surcharge. This flexibility ensures you get the right format for your specific platform, whether it is a web player or a native mobile app.
Free Trial for Tourism Startups
Tourism startups can begin testing the narrator API immediately by signing in with Google. This method grants $0.50 of trial credit, equivalent to 50,000 characters. It is ideal for generating initial audioguide drafts or testing voice presets without financial commitment.
Sign Up with Google for $0.50 Credit
Creating an account via Google authentication instantly activates the trial balance. You can start generating audio files for museum exhibits or tour scripts right away. This allows quick validation of voice quality and language support before committing to larger production runs.
- Instant account creation via Google
- $0.50 trial credit included
- Approximately 50,000 characters available
Trial Validity and Expiration Rules
The $0.50 trial credit remains valid for 7 days from the moment of account creation. After this period, the credit expires regardless of usage. Plan your initial testing phase accordingly to ensure you can evaluate the API before the trial ends.
Email Sign-Up Accounts Start Without Credit
Accounts created using only an email address and password do not receive the trial credit. To access the $0.50 bonus, you must use the Google sign-in option. This distinction ensures that the trial incentive is reserved for specific onboarding flows.
Payment Methods and Currency
The API supports only one payment method: USDT on the TRON network (TRC-20). This approach eliminates the need for credit card processing fees or third-party payment gateways, keeping overhead low for tourism startups and museum curators. You can top up your account balance directly using any standard TRON-compatible wallet.
Automatic Balance Crediting
Once your transfer is confirmed on the blockchain, the credit is added to your account automatically within minutes. There are no manual invoice approvals or waiting periods for accounting teams. Your usable balance updates immediately, allowing you to generate audioguides or video voiceovers without interruption.
No Credit Cards or PayPal Options
We do not accept Visa, Mastercard, American Express, or PayPal. There are no monthly subscriptions or minimum spend requirements. This model suits teams that prefer crypto settlements or want to avoid recurring billing cycles. Balances do not expire, so you can top up when convenient.
- TRC-20 (USDT) only
- No credit cards
- No PayPal
- No monthly plans
Cost Examples for Museum Audioguides
TTS APIs enable tourism startups to produce scalable audio content without hiring voice actors for every language. By evaluating narrator APIs, you can generate high-quality audioguides and video voiceovers efficiently. This approach ensures consistent quality across all your audio assets while keeping production costs predictable and transparent.
Understanding the cost structure is crucial for budgeting your audio projects. With a pay-per-character model, you only pay for what you use. This transparency helps you plan your expenses accurately, ensuring that your audio content remains affordable even as your library grows.
Average Cost for a 5-Minute Audio Guide
A 5-minute audio guide typically contains around 750 words, which translates to approximately 3,750 characters. Note that generation speed is roughly real-time (25 characters per second), so 3,750 characters of text will take approximately 150 seconds (2.5 minutes) to generate. At $0.01 per 1,000 characters, the cost for this length of content is roughly $0.0375. This low cost makes it feasible to produce multiple variations of your guide without significant financial burden.
- - Average length: 750 words
- - Character count: ~3,750
- - Cost: ~$0.0375
Budgeting for a 50-Exhibit Museum Tour
For a museum with 50 exhibits, assuming an average of 150 characters per exhibit description, the total character count would be around 7,500 characters. The cost for this entire tour would be approximately $0.075. This budget-friendly approach allows you to create comprehensive audio tours without exceeding your financial limits.
- - Total exhibits: 50
- - Total characters: ~7,500
- - Total cost: ~$0.075
Scaling Costs for Multi-Language Versions
If you plan to create multi-language versions of your audioguide, the cost scales linearly with the number of languages. For example, producing the same 5-minute guide in 10 languages would cost around $0.375. This scalability ensures that you can reach a global audience without incurring exponential costs.
- - Number of languages: 10
- - Total cost: ~$0.375
Refund Policy for Failed Requests
For tourism audio production, failed synthesis requests are fully refunded. If the API cannot convert your text into audio due to a server error or timeout, the character count is not deducted from your balance. This ensures you only pay for successfully generated audio files, protecting your budget during high-volume audioguide exports.
Full Refund on Synthesis Errors
Any request that returns a non-200 status code or fails to deliver the audio file triggers an automatic credit return. The system reverses the charge instantly, so your available balance remains accurate without manual intervention. This applies to all requests regardless of the rate limit tier.
- Refunds are applied to your USDT balance automatically.
How to Identify Failed Requests in Logs
Monitor your request logs for HTTP error codes (e.g., 400, 500) or missing audio data in the response body. Each failed request retains a timestamp and character count in your billing metadata, allowing you to verify that the charge was reversed. Check your dashboard to confirm the refunded amount appears in your balance history.
Billing for Partially Generated Audio
If a request completes but returns a truncated audio file due to a network interruption, it is still considered a successful synthesis and is billed normally. The API charges per character of input text submitted, regardless of whether the output audio is short or full-length. Partial generation does not trigger a refund unless the request explicitly fails.
No Minimum Spend or Subscriptions
Pay only for the audio you actually generate. There are no mandatory monthly plans, no minimum spend requirements, and no hidden fees for format conversions. If your museum project pauses, you stop paying immediately; you are never charged for idle time or reserved capacity.
Pay Only for What You Use
Our model charges strictly by character count. You do not pay for API uptime or server maintenance. This structure allows tourism startups to scale audio production up or down without financial commitment, paying only when they generate audioguides or video voiceovers.
No Monthly Seat Fees for Teams
One API key supports your entire team’s integration efforts. There are no seats or per-user fees. Whether one person or ten developers are hitting the endpoint, the cost remains based solely on the volume of text synthesized, keeping overhead predictable for small museum teams.
Balance Does Not Expire
Your funded balance remains available indefinitely. You can top up when convenient and use the credit months later without fear of expiration. This flexibility is ideal for seasonal tourism projects or museums that produce content in batches, ensuring your investment in audio infrastructure remains usable long-term.
Rate Limits Affecting Production
Rate limits directly impact how you scale audio guide generation. With a cap of 60 requests per minute per key, you must plan your batch processing windows carefully to avoid throttling during high-volume production runs.
New accounts start with a stricter limit of 10 requests per minute until the first top-up is processed. This ensures initial stability but requires patience when generating large catalogs of museum narrations.
60 Requests Per Minute Per Key
Each API key is capped at 60 requests per minute. Since each request handles up to 4,096 characters, this limit allows for substantial throughput but requires you to monitor usage if you are generating many short clips simultaneously.
- Limit applies per active API key, not per account.
Initial Limit of 10 Requests Per Minute
Before your first top-up, your key operates at 10 requests per minute. This lower threshold helps prevent abuse during the trial phase but means generation will be slower for initial testing or small batches.
Queueing Behavior Under Load
Requests are processed sequentially. If you exceed the rate limit or send too many concurrent requests, additional requests may wait in a queue. This can increase total generation time, especially for longer texts that take several seconds to synthesize.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This clarity helps developers quickly prototype audio guides for museums or tourist apps without guessing parameter formats or encoding requirements.
23 languages
Any voice speaks any of these languages.
