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 synthesis requests regardless of the selected voice preset or audio format. The pricing model is straightforward and scales linearly with usage, allowing startups to predict costs accurately based on character volume without complex tiered structures.
Do spaces and punctuation count towards the character limit?
Yes, spaces and punctuation count as characters. Each space, comma, period, or symbol contributes to the total character count billed to your account. This means the 4,096-character input limit and billing calculations include all whitespace and special characters within the input text string submitted via the API endpoint.
What is the free trial amount?
The free trial provides $0.50 of credit, which allows for approximately 50,000 characters of synthesis. This trial is available when you sign in using a Google account. It enables startups to test the API’s capabilities and audio quality before committing to a paid top-up for production workloads.
How long does the trial credit last?
The trial credit is valid for 7 days from the time of account creation via Google sign-in. If the credit is not used within this period, it expires. This timeframe allows startups to evaluate the API’s performance and integration fit without immediate financial commitment or long-term lock-in.
Can I pay with a credit card?
No, credit cards are not accepted. We do not process payments via cards, PayPal, or subscriptions. All payments must be made using USDT on the TRON network (TRC-20). This method allows for borderless top-ups directly to your account balance.
What is the minimum top-up amount?
The minimum top-up amount is $5. You must transfer at least this value in USDT (TRC-20) to add funds to your account. This low threshold allows startups to start with minimal capital while ensuring efficient processing of the blockchain transaction. Funds are credited automatically within minutes of transfer confirmation.
How long does a USDT transfer take?
Top-ups are credited automatically within minutes after the USDT transfer is confirmed on the TRON network. There are no manual reviews or delays. Once the blockchain transaction is validated, your balance updates immediately, allowing you to resume synthesis requests without interruption, which is critical for maintaining development momentum.
Is there a monthly fee for the API?
No, there are no monthly fees, subscriptions, or seats. You pay only for the characters you generate. There is no minimum spend requirement, and unused balance does not expire. This pay-as-you-go model ensures that costs align directly with usage, making it ideal for startups with variable or unpredictable demand patterns.
What happens if a synthesis request fails?
If a synthesis request fails, the charge is returned in full. You are not billed for failed attempts, ensuring you only pay for successful audio generation. This policy protects your budget from unexpected errors during API calls, allowing you to test error handling and retry logic without financial penalty.
Does my balance expire?
No, your balance does not expire. Funds added via USDT top-ups remain available indefinitely until used. This allows startups to top up during periods of lower activity and use the credit later without worrying about expiration dates. It supports long-term planning and reduces the administrative overhead of managing recurring subscription cycles.
How do I check my remaining characters?
You can check your remaining characters, balance, and usage history on the /get-api-key/ dashboard page. The interface displays your current balance, trial status, and character count. This visibility allows you to monitor consumption accurately and plan top-ups accordingly.
Can I issue a new API key if the old one is compromised?
Yes, you can issue a new API key at any time. When you generate a new key, the old one stops working immediately. This ensures that if a key is compromised, access is revoked instantly. You can manage your keys directly from the dashboard, providing tight control over API access security.
Are there any hidden fees for format conversion?
There are no hidden fees for format conversion. The price is consistent across all supported formats: mp3, wav, opus, flac, and pcm. You pay the same rate per character regardless of the output format selected in the response_format field. This simplifies cost estimation for applications requiring multiple audio formats for different devices.
Is there a discount for high-volume startups?
No, there are no volume discounts or tiered pricing. The rate remains $10 per 1 million characters regardless of usage volume. This flat rate ensures predictability and simplicity. High-volume startups pay the same per-character rate as new users.
Cost calculator
Standard Rate Structure
Our infrastructure charges a standard rate of $10 per 1 million characters for text-to-speech synthesis. This linear pricing model eliminates fixed monthly overheads, allowing startups to scale audio production precisely alongside application usage without unpredictable subscription fees.
Cost Per Million Characters
The base cost is $0.01 per 1,000 characters. This flat rate applies uniformly across both the "tts-1" and "tts-1-hd" models, ensuring consistent unit economics whether you are generating brief alert tones or extended narrative content for assistive devices.
Character Count Definition
Character counting includes every individual unit of input text sent to the API, including letters, numbers, and whitespace. The limit is 4,096 characters per request, requiring your application to split longer texts into manageable segments for synthesis.
Punctuation Inclusion
All punctuation marks, such as commas, periods, and question marks, are counted as individual characters toward your total usage. This ensures accurate billing alignment with the exact input payload processed by our synthesis engine.
Trial Credit Allocation
New accounts receive trial credit to verify integration stability before committing funds. The allocation method depends on the authentication provider selected during the sign-up process on the /get-api-key/ page.
This allows startups to validate audio quality without financial risk.
Google Sign-In Bonus
Accounts created via Google authentication receive $0.50 in trial credit. This amount supports approximately 50,000 characters of synthesis, sufficient for initial integration tests.
Email Sign-Up Credit
Users registering with an email address and password start with zero trial credit. Balance must be established via USDT top-up before the first API call, unless a trial credit is available.
Trial Duration Limits
The $0.50 trial credit remains valid for 7 days from account creation. Unused credit expires after this period, requiring a new account or top-up to continue service.
Payment Methods
CalmVoice utilizes a direct cryptocurrency top-up system to maintain a simple, subscription-free payment structure. Users deposit funds directly into their account balance, which remains valid indefinitely until consumed by API requests.
USDT TRC-20 Top-Ups
All deposits are processed exclusively via USDT on the TRON network (TRC-20). We do not accept credit cards, PayPal, or traditional bank transfers, eliminating currency conversion fees and intermediary banking delays.
Minimum Deposit Amount
The minimum top-up amount is set at $5. This threshold ensures efficient processing of on-chain transactions while allowing startups to test the service with a manageable initial commitment.
Processing Time
Funds are credited automatically to your CalmVoice account within minutes of the blockchain confirmation. Once the transaction is verified, the balance is immediately available for generating speech via the API.
Volume Cost Examples
CalmVoice charges $10 per million characters, with spaces and punctuation counted. Failed requests incur no charge, ensuring you pay only for delivered audio.
Short Alert Messages
Alerts under 100 characters cost $0.001 each. A 50-character voice instruction costs $0.0005. High-frequency triggers remain economical at scale.
Medium Instruction Sets
Standard commands average 400 characters, costing $0.004 per generation. Complex multi-step prompts remain predictable. Batch processing reduces per-unit latency.
Long Narrative Content
Long texts split into 4096-character segments. Each segment generates independently. Audio files are joined by the client application for continuous playback in assistive devices.

Failure Refund Policy
Synthesis failures result in a full, immediate refund of the character cost. The system returns the charge to your balance without delay, ensuring that billing reflects only successful audio generation.
Failed Request Handling
When a request fails, the charge is returned in full. You are billed only for completed audio files delivered successfully.
Balance Restoration
Refunded amounts are restored to your account balance immediately. You can verify this in the account dashboard alongside your usage history.
Retry Mechanisms
Failed requests can be retried without additional cost if the failure was transient. Simply resend the same text payload to the API endpoint.
Account Management
Account security and financial transparency are managed directly through the /get-api-key/ dashboard. Each account maintains a single active API key.
Key Rotation Process
A new key can be issued at any time via the dashboard. The previous key stops working immediately upon generation, allowing for zero-downtime transitions in assistive device fleets.
Balance Monitoring
The dashboard displays the key, balance, trial status, characters left, and usage. This visibility supports accurate budgeting for high-volume elderly care audio generation without hidden fees.
No Expiration Policy
Top-up credits do not expire. This allows startups to accumulate funds during funding rounds without losing balance due to quarterly or annual renewal cycles.
Comparison with Traditional Models
Traditional voice-over models often lock capital into monthly subscriptions regardless of actual usage. CalmVoice eliminates this overhead, ensuring you pay only for the audio your application generates. This structure aligns operational costs directly with your product’s activity, reducing fixed expenses for startups with variable demand.
There is no minimum spend requirement, allowing small teams to start with minimal capital. You retain full control over your budget without the risk of paying for unused capacity during low-traffic periods.
No Monthly Subscriptions
Unlike legacy platforms that require recurring fees, we do not charge monthly retainers. Your balance is drawn down strictly as requests are processed, removing the obligation to pay for idle time.
This approach prevents budget leakage, ensuring every dollar contributes to actual character synthesis rather than covering baseline service availability.
No Minimum Spend
There is no minimum spend threshold, allowing you to top up with any amount above the $5 USDT minimum. This flexibility supports startups that manage cash flow carefully or experience irregular usage spikes.
You can scale your spending directly in proportion to your user base without committing to long-term contracts or volume commitments.
Pay-As-You-Go Structure
The per-character model at $10 per million characters ensures precise cost predictability. You know the exact expense for any given text volume before generation begins.
Failed requests are refunded, meaning you never pay for unused output. This accuracy simplifies financial forecasting for assistive device applications with variable trigger frequencies.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. You pay per character processed, not per voice type, ensuring predictable expenses as your user base grows.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- curl documentation
- LibriVox public-domain audiobooks
- Creative Commons Attribution 4.0
- openai-python on GitHub
- IETF RFC 7845: Ogg Opus
- Python documentation
- MDN: Web Speech API
- TRON developer hub: TRC-20
- LibriTTS-R paper (arXiv 2305.18802)
- Node.js documentation
