Frequently asked questions
How much does the API cost per character?
The API costs $10 per 1 million characters, which equals $0.01 per 1,000 characters. This rate applies to all requests regardless of the model chosen.
Does the free trial expire?
The $0.50 free trial credit is valid for 7 days after you sign in with Google. Accounts created with email and password do not receive this trial credit.
Can I pay with a 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 or VAT.
What is the minimum top-up amount?
The minimum top-up amount is $5. You can add funds to your balance at any time using USDT on the TRON network.
How long does USDT top-up take?
Top-ups are credited automatically within minutes after your USDT transfer is confirmed on the TRON network. No manual processing is required.
Are failed requests charged?
No. If a synthesis request fails, the charge is returned in full. You only pay for successfully generated audio files.
Is there a monthly subscription fee?
No. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you use, with no recurring fees.
Do spaces count as characters?
Yes. Spaces and punctuation count toward the character limit. The pricing is based on the total character count of your input text.
Does the audio format (mp3, wav, etc.) affect the price?
No. The price is based on the input character count, not the output format. Formats like mp3, wav, opus, flac, and pcm all cost the same.
What is the character limit per request?
Each request can process up to 4096 characters. For longer texts, you should split the input into parts and join the resulting audio files.
Can I use the API for commercial projects?
Yes. The API is designed for indie developers building voice-enabled IoT products. Input text is not used for training, and generated audio is not stored.
Do I need to pay for voice selection?
No. All 8 voice presets are included in the standard character-based pricing. You can switch between voices like aria, nova, or atlas without extra cost.
Is there a minimum spend to keep my account active?
No. There is no minimum spend or monthly fee. Your account remains active as long as you have a valid API key, regardless of usage.
Does the balance expire after I top up?
No. Your balance does not expire. You can top up with USDT at any time, and the funds remain available for future requests indefinitely.
Cost calculator
Character-Based Pricing Model
The TTS API charges $0.01 per 1,000 characters, making it cost-effective for high-volume IoT device notifications and smart home voice responses. Each request processes up to 4,096 characters, allowing you to generate audio for longer instructions by splitting the text into manageable segments.
$0.01 per 1,000 Characters
Every character in your input text contributes to the total cost. This flat rate applies regardless of the voice model selected (tts-1 or tts-1-hd), ensuring predictable expenses for your application's audio generation needs.
Spaces and Punctuation Count
Spaces, commas, periods, and other punctuation marks are counted as characters. When calculating costs for your IoT scripts, include all whitespace and symbols in your character count to avoid unexpected charges on your balance.
No Hidden Fees or Setup Costs
There are no monthly subscriptions, per-seat fees, or setup charges. You only pay for the characters you successfully convert to speech. Failed requests are free, so you are never charged for unused audio.
To manage longer texts, split your input into chunks of 4,096 characters or fewer. The API returns separate audio files for each chunk, which you can join using standard audio libraries in your IoT project.
Free Trial Credit for Developers
Developers can start testing immediately with a $0.50 free trial credit when signing in with Google. This allows you to verify voice quality and integration without upfront payment. Note that accounts created with email and password do not receive this trial credit.
$0.50 Free Credit on Sign-Up
The trial credit is automatically applied to your account when you sign in with Google. It appears as available balance in your dashboard, ready for immediate use with the TTS API.
Approximately 50,000 Characters
With pricing at $0.01 per 1,000 characters, the $0.50 credit provides approximately 50,000 characters of speech generation. This volume is sufficient to test multiple voices, languages, and speed settings across various device scenarios.
7-Day Validity for Testing
The trial credit expires 7 days after sign-up. Use this window to evaluate audio format options and voice presets. Any unused credit is lost after this period, encouraging rapid validation of your IoT voice integration.
Payment Methods Accepted
We accept USDT on the TRON network (TRC-20) exclusively. This streamlined payment method eliminates the friction of credit cards, PayPal, or bank transfers, keeping our infrastructure simple for indie developers. There are no monthly subscriptions, no recurring invoices, and no VAT complications to manage.
USDT on TRON Network (TRC-20)
Payments are processed entirely on the TRON blockchain using the TRC-20 standard. You can send USDT directly from any compatible wallet.
- Supported currency: USDT (TRC-20)
- No credit cards or PayPal
- No subscription fees or VAT
Minimum Top-Up of $5
The minimum top-up amount is $5. This low threshold allows you to test the API with your first batch of voice generations without committing to a large sum. Once topped up, your balance is yours to use as needed.
Automatic Credit Within Minutes
Credits are added automatically within minutes after your transfer is confirmed on the blockchain. There is no manual review process or waiting for email confirmations. Your account balance updates instantly, allowing you to start generating speech immediately.
Failed Request Refund Policy
When a synthesis request fails, you are not charged for that attempt. Whether the error stems from a temporary network glitch or a server-side timeout, the API ensures you only pay for successfully generated audio files.
This policy applies to all request types, including those using the high-definition model. If the service returns an error status, the character count remains unchanged, preserving your balance for the next valid attempt.
Full Refund on Synthesis Failure
If the TTS engine fails to produce audio due to internal errors or invalid input handling, the full cost is waived. You do not lose any credits for these unsuccessful attempts.
This ensures that unexpected technical hiccups do not impact your project's budget. The charge is returned in full.
- Applies to all models: tts-1 and tts-1-hd
- Covers network errors and server timeouts
- No manual claim process required
No Charge for Failed Requests
Failed requests are completely free. Unlike standard billing, where usage is counted regardless of outcome, our system verifies successful audio generation before applying the $0.01 per 1,000 characters rate.
This means you can retry robustly without worrying about accumulating costs for errors. Each retry is treated as a fresh request, ensuring accurate billing.
Instant Balance Adjustment
Your account balance updates. When a request fails, the adjustment is reflected instantly in your dashboard, allowing you to monitor your remaining characters accurately.
You can see the reduction in usage immediately, making it easy to track your IoT project's voice generation costs without delay.
No Monthly Plans or Subscriptions
Our pricing model eliminates recurring billing cycles, meaning you only pay for the characters you actually generate. There are no hidden fees or setup costs, and your balance never expires. This structure allows indie developers to scale voice features precisely with their project's growth, avoiding waste on unused capacity.
Pay Only for What You Use
You are charged $0.01 per 1,000 characters based on actual usage. Since you do not lock into a monthly subscription, you avoid paying for idle time when your smart home assistant is not actively speaking.
No Minimum Spend Required
There is no minimum spend required to keep your account active. You can top up with the minimum $5 USDT (TRC-20) whenever needed, making it ideal for low-volume IoT devices that trigger speech occasionally.
No Seats or User Limits
Your API key is not tied to a specific number of users or seats. You can deploy the same key across hundreds of devices or test environments without incurring additional per-seat fees or hitting user caps.

Cost Examples for IoT Projects
Understanding cost implications helps you budget for voice-enabled devices. Our character-based model ensures you pay only for the text actually processed, making it easy to estimate expenses for various IoT use cases.
Short Device Alerts (Low Cost)
Simple notifications like "Battery Low" or "Door Opened" are extremely economical. A 20-character alert costs $0.0002. You can generate thousands of these alerts daily without significant expense, ideal for sporadic smart home notifications.
Long Instruction Narrations
Complex instructions require splitting text into 4096-character chunks. While each chunk incurs a small fee, the total cost remains predictable. For a 500-character weather report, you pay $0.005. This allows for detailed voice guidance without high per-request overhead.
Bulk Generation for Pre-Recorded Content
Pre-recording audio for devices with limited memory is cost-effective. Generating 1 million characters costs $10. You can batch-process large text libraries to create assets for kiosks or industrial interfaces, leveraging the flat rate for any format.
Balance and Billing Details
Your billing balance never expires, allowing you to top up once and use credits whenever your IoT devices need voice generation. There are no monthly fees or subscription cycles to manage, so your funds remain available indefinitely until you choose to spend them.
Balance Never Expires
Unused credit stays in your account permanently. You can top up via USDT on the TRON network at any time, and the funds are credited automatically within minutes. This flexibility suits projects with irregular usage patterns, ensuring you never lose money from expired plans.
- No expiration date for credits
- Instant credit after USDT transfer
Usage Dashboard Available
The dashboard provides a clear view of your current balance, remaining characters, and historical usage. You can monitor character consumption in real-time to ensure your smart home projects stay within budget without unexpected charges.
- Track character consumption
- View current balance instantly
Real-Time Character Counting
Characters are counted precisely as they are submitted, including spaces and punctuation.
- Accurate character counting
- Includes spaces and punctuation
Technical Limits Affecting Cost
Understanding these technical constraints helps you estimate costs accurately. Each API request accepts a maximum of 4096 characters, including spaces and punctuation. For longer texts, split the input into multiple requests and concatenate the resulting audio files.
Rate limits also influence your workflow. You are allowed 60 requests per minute per key (10 per minute before the first top-up). Requests are processed sequentially, so under load, synthesis may wait in a queue, potentially increasing total generation time for bulk tasks.
4096 Character Limit Per Request
Send text up to 4096 characters per request. Longer inputs must be split into chunks, and the resulting audio files joined by your application.
Rate Limits and Queue Times
Each API key allows 60 requests per minute (10 per minute before the first top-up). Requests are processed one after another. Under high load, a request may wait in a queue, extending the time to receive audio but not affecting the character count or cost.
Audio Format Does Not Affect Price
The character count determines the price, regardless of the output format. Whether you choose mp3, wav, opus, flac, or pcm, the cost remains $0.01 per 1,000 characters. Format selection only affects file size and compatibility, not billing.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Beginners can start generating speech in minutes using the provided curl examples or standard HTTP clients.
23 languages
Any voice speaks any of these languages.
