Frequently asked questions
How is the character count calculated for audio generation?
Characters include spaces and punctuation. Each API request handles up to 4,096 characters. You must split the text into parts of up to 4,096 characters and join the audio files manually. You are charged based on the total character count across all parts processed.
Do spaces and punctuation count towards the character limit?
Yes, spaces and punctuation count as characters. The pricing is strictly based on the total character count of your input text. This includes every space, comma, and period included in your request payload, ensuring accurate billing for the exact amount of data processed by the API.
Is there a minimum amount I must spend to use the API?
There is no minimum spend. We do not offer monthly plans or require a minimum balance. You can use any amount of credit. The only constraint is the minimum top-up amount of $5 when adding funds via USDT on the TRON network.
Do I lose my balance if I don't use it for a long time?
Your balance does not expire. You can store credits indefinitely without any usage requirements. There are no monthly fees or subscription costs that would deduct from your account. Your remaining credit remains available whenever you are ready to generate your next synthetic speech dataset.
How long does it take for USDT payments to credit my account?
Top-ups are credited automatically within minutes after the transfer is confirmed on the blockchain. We only accept USDT on the TRON network (TRC-20). Once the transaction is visible, your balance updates immediately, allowing you to start generating audio files without waiting for manual processing.
Can I use both Google and email sign-ups for the trial?
No. The $0.50 free trial credit is only given when you sign in with Google. Accounts created using an email address and password start without any trial credit. This distinction applies to each site account independently, so choose your sign-up method carefully to access the trial.
What happens if I exceed my balance during a request?
Failed requests are free, so no charge is applied. If your balance is insufficient before the request starts, the request will likely fail. We recommend monitoring your balance via the dashboard to ensure continuous generation for your data pipelines.
Are there any additional fees for using different audio formats?
No, there are no additional fees for different formats. The price is $10 per 1 million characters regardless of whether you choose mp3, wav, opus, flac, or pcm. The format selection does not affect the character count or the cost of the API request.
Is there a discount for high-volume data generation?
We do not offer volume discounts or tiered pricing. The rate remains $10 per 1 million characters for all usage levels. There are no monthly plans or enterprise contracts. You pay exactly for the characters you generate, making it predictable for large-scale synthetic speech dataset projects.
Can I cancel my account and keep my remaining balance?
Your balance does not expire. While we do not specify a formal cancellation process, your credit remains associated with your account details. You can use your key later, as there are no subscriptions or minimum spend requirements. Accounts are per site, so ensure you use the same site domain to access your existing balance and key.
Do I get a receipt or invoice for my payments?
We do not provide invoices or receipts with VAT. Payments are made via USDT on the TRON network. You can verify your balance, usage, and character counts on the dashboard, but there is no formal billing document generated. This keeps our process simple and direct for developers.
How do I check my current balance and usage?
Visit /get-api-key/ to view your key, balance, trial status, and characters left. The page displays your usage and provides a ready curl example. This allows you to monitor your synthetic data generation costs accurately. Note that while request metadata is kept for billing, the interface specifically shows current usage metrics rather than a detailed historical log.
Is the trial credit available for all new accounts?
No. Only accounts signed in with Google receive the $0.50 trial credit. Accounts created with an email and password start without any trial credit. Both types of accounts are valid, but the trial benefit is exclusive to Google sign-ins on this specific site instance.
Can I top up my account multiple times?
Yes, you can top up your account as many times as you need. There is no limit on the number of transactions. Each top-up must meet the minimum $5 requirement via USDT on the TRON network. Credits are added automatically and do not expire.
Cost calculator
Character-Based Cost Structure
Our pricing model charges $0.01 per 1,000 characters generated. This linear structure ensures that costs scale directly with your dataset volume, allowing precise budget forecasting for large-scale synthetic speech projects without unexpected overages.
$0.01 per 1,000 characters generated
Each character in your input text contributes to the final bill. This includes spaces, punctuation, and special symbols, ensuring that character counts reflect the actual processing load. You pay only for the text that enters the synthesis engine, making cost estimation straightforward for data ingestion pipelines.
- $10 per 1 million characters
- Spaces and punctuation count as characters
Spaces and punctuation count as characters
When calculating costs, every character in your input string is counted. This means that natural language text with common punctuation marks incurs the same per-character rate as plain text. Accurate character counting allows you to predict exact expenses for your training datasets.
Predictable costs for budgeting data projects
Because costs are tied directly to character volume, you can forecast expenses accurately. This predictability supports financial planning for ML teams generating large datasets, ensuring that budget constraints are met without hidden fees or subscription surprises.
No Hidden Fees or Subscriptions
SynthCode’s pricing model is designed for transparency, eliminating the complexity often found in enterprise software billing. There are no recurring monthly plans to manage or seat limits to track, ensuring your costs align directly with your data generation needs. This structure allows product teams to scale their synthetic speech datasets without worrying about unexpected overhead or administrative friction.
No monthly plans or seat limits
Unlike traditional SaaS platforms that charge per user or require annual commitments, SynthCode operates on a pure usage basis. You pay only for the characters you generate, making it ideal for teams with fluctuating workloads. Whether you are processing a few hundred files or millions, your billing remains simple and predictable.
- No recurring subscription fees
- Unlimited API keys per account
- No per-seat licensing costs
No minimum spending requirements
There is no minimum spend or entry threshold to start generating audio. This flexibility allows small teams to begin with minimal capital and scale as their dataset grows. You retain full control over your budget, paying only for what you actively use without being locked into long-term contracts.
Balance does not expire
Your credit balance remains valid indefinitely, providing long-term stability for your data projects. You can top up when convenient and use the funds over months or years without fear of forfeiture. This ensures that your investment in synthetic speech generation is never wasted due to time-based expiration policies.

Free Failures Protect Your Budget
Synthetic speech generation is not always instantaneous, especially under load. Requests may queue or fail due to transient issues.
Failed requests are fully refunded
When synthesis fails, the charge is returned in full. This ensures that transient errors do not impact your budget.
Requests are processed sequentially, so under load a request may wait in a queue before being rejected or completed.
No charge for unsuccessful synthesis
You are not charged for audio that does not successfully generate. This applies to all failure modes, including timeouts or server errors.
Failed requests are free, so you only pay for valid output.
Ensure you only pay for valid audio
Since audio is returned as a file in the response and not via streaming, there is no concept of an incomplete stream.
You only pay when the full audio file is successfully generated and returned.
Payment via USDT (TRC-20)
SynthCode streamlines procurement for synthetic speech datasets by accepting USDT on the TRON network (TRC-20). This approach eliminates traditional banking delays and international transaction fees, allowing product teams to fund their data generation pipelines efficiently.
Minimum top-up of $5
The minimum top-up amount is $5, making it accessible for small-scale dataset projects without requiring large upfront capital commitments.
Automatic credit within minutes
Once the transfer is confirmed on the TRON blockchain, your account balance is credited automatically within minutes. This near-instant availability ensures your data ingestion workflows can resume immediately without waiting for manual invoice processing.
No credit cards or PayPal required
We do not store credit card details or require PayPal accounts. This reduces administrative overhead and keeps your payment infrastructure simple, focusing solely on the API usage needed for model training.
- Direct blockchain transfers only
- No recurring subscriptions
- No VAT invoices required

Free Trial for Evaluation
The free trial provides $0.50 of credit, valid for 7 days, when you sign in with Google. This allows product teams to evaluate the API without financial commitment. Email-based accounts do not receive this trial credit.
$0.50 credit for Google sign-ups
Accounts created via Google sign-in receive $0.50 of trial credit immediately. This amount covers approximately 50,000 characters of text synthesis. Email and password accounts start without any trial credit.
- Google sign-in provides $0.50 credit
- Approximately 50,000 characters included
- Email accounts start with zero credit
Valid for 7 days
The trial credit expires after 7 days. Use this period to verify integration steps and confirm the API meets your dataset generation requirements before purchasing top-up balance.
Test integration before committing
Use the trial to test response formats including mp3, wav, opus, flac, and pcm. Verify voice compatibility and assess the 8 presets. Confirm the 60 requests per minute rate limit aligns with your batch processing needs.
- Test mp3, wav, opus, flac, pcm formats
- Verify 60 requests/minute rate limit
- Assess 8 voice presets
Cost Examples for Dataset Projects
For synthetic speech dataset generation, predictability is critical. At $10 per million characters, you can accurately forecast the cost of large-scale audio corpora before ingestion begins. Spaces and punctuation count toward the limit, ensuring precise budgeting for every project phase.
1 million characters cost $10
This fixed rate simplifies financial planning for ML teams. Whether generating voiceovers for thousands of product descriptions or training data for acoustic models, the cost remains consistent regardless of voice selection or format.
Ideal for small to medium dataset sizes
Small teams or those running initial experiments can start with minimal volume. The absence of minimum spend requirements means you only pay for what you generate, making it easy to validate data quality without significant upfront commitment.
Scale costs linearly with volume
As your dataset grows, so do your costs proportionally. There are no tiered pricing jumps or volume discounts that complicate forecasting. This linear relationship allows for straightforward extrapolation of expenses as you scale from hundreds to millions of characters.

Account Management
The SynthCode dashboard provides a clear overview of your account status, including current balance and character consumption. You can issue a new API key at any time, which immediately invalidates the previous one for seamless rotation in production environments.
This management layer ensures your data ingestion pipelines remain secure and auditable without requiring complex infrastructure changes.
View balance and usage in dashboard
The account page displays your current credit balance, remaining trial validity, and total characters processed. This visibility helps product teams monitor consumption against project budgets without needing external billing tools.
Request metadata, including timestamps and character counts, is retained for accurate billing reconciliation.
Issue new API key instantly if needed
Generate a new API key with a single click. The old key stops working immediately, allowing you to revoke access for compromised or legacy integration keys without waiting for propagation delays.
Each account maintains one active key at a time, simplifying permission management for your dataset generation workflows.
Track characters used per request
Monitor character consumption directly from your API responses and dashboard logs. Since pricing is strictly character-based, tracking usage per request ensures precise cost allocation for individual dataset samples.
This granularity helps you optimize text preprocessing to stay within the 4096-character limit per request while minimizing waste.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. High quality synthetic speech data enhances the accuracy and naturalness of our machine learning models.
23 languages
Any voice speaks any of these languages.
