Frequently asked questions
What is the cost per character for Hindi TTS?
The cost is $0.01 per 1,000 characters for all supported languages, including Hindi. This rate applies uniformly across the API, so Hindi navigation prompts are priced identically to English or German. Spaces and punctuation count toward the character total. There is no language-specific surcharge, ensuring predictable billing for multilingual in-car voice interfaces.
Do I pay for failed synthesis requests?
No, you do not pay for failed requests. If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures you only pay for usable navigation audio outputs, protecting your budget when handling edge cases in voice interface workflows.
How do I top up my balance with USDT?
Top up using USDT on the TRON network (TRC-20) only. Send the transfer to the address provided in your account dashboard. Credits are added automatically within minutes. No other payment methods like cards or PayPal are supported. Ensure you use the correct network to avoid delays in balance updates.
Is there a monthly subscription fee?
No, there are no monthly subscription fees. You pay only for what you use, with no minimum spend or seats. Balances do not expire. You can top up as needed without committing to a recurring plan. This model suits variable traffic patterns in automotive navigation systems.
How long does the free trial last?
The free trial lasts 7 days and includes $0.50 of credit, covering about 50,000 characters. It is available when you sign in with Google. Accounts created with email and password start without this trial credit. Use this period to test voice quality and integration workflows.
Does the balance expire after use?
No, your balance does not expire. Funds remain available until you use them for API requests. There is no expiration date on top-ups or initial credits. This allows you to accumulate credits during low-traffic periods and use them when navigating systems require high-volume voice generation.
What is the minimum top-up amount?
The minimum top-up amount is $5. You can add funds via USDT on the TRON network at any time. There is no maximum limit. This low entry point allows small teams to start testing without significant upfront investment in the API infrastructure.
Are there any hidden fees for API usage?
There are no hidden fees. You pay $10 per million characters generated. Failed requests are free. There are no per-request fees, storage fees, or egress charges. The pricing is transparent and based solely on character count, making it easy to predict costs for navigation audio.
What is the maximum text length per request?
The maximum input text length is 4,096 characters per request. For longer navigation instructions, split the text into parts of this size and join the resulting audio files. This limit applies to all models and voices. Ensure your client-side logic handles chunking for complex route descriptions.
How many requests can I make per minute?
You are limited to 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. This rate limit applies to the API endpoint. Monitor your usage to ensure smooth playback in real-time navigation scenarios without hitting throttling thresholds.
Which languages are supported for navigation?
We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. Set the language parameter for non-English Latin-script text to ensure accuracy.
Can I use the OpenAI SDK with this API?
Yes, you can use the official OpenAI SDKs. Change the base_url to https://api.cph2699.info/v1 and use your NavVoice key. The request shape matches the OpenAI speech endpoint. This allows you to leverage existing SDK code and tools with minimal configuration changes for your automotive projects.
Do I need to split long navigation texts manually?
Yes, you must split texts longer than 4,096 characters into parts. Generate audio for each part and join the files on your end. The API does not handle splitting or stitching. Implement this logic in your client application to ensure seamless playback of complex navigation instructions.
Is there a limit on the number of voices I can use?
No, there is no limit on the number of voices you can use. You can select from 8 presets (e.g., aria, nova, atlas) for different navigation cues. Switch voices freely between requests. Each voice has a distinct tone, allowing you to differentiate between alerts, directions, and system messages.
Cost calculator
Pay-Per-Use Model for Automotive Apps
NavVoice charges $0.01 per 1,000 characters for automotive navigation and infotainment text-to-speech. Spaces and punctuation count toward this limit, ensuring predictable costs for route instructions and system prompts.
$0.01 per 1,000 characters
Billing is precise: every character in your input text, including spaces, contributes to the cost of $0.01 per 1,000 characters. This model works well for navigation systems where text length varies by route complexity.
No monthly subscriptions
You pay only for what you use. There are no recurring fees or mandatory commitments, allowing your team to scale voice synthesis up or down based on active vehicle fleets.
No minimum spend requirements
Start with any volume. Whether you are testing a single voice prompt or deploying to thousands of devices, there is no minimum spend to keep your integration active.
Free Trial for Product Teams
Start testing your navigation prompts immediately with a $0.50 credit when you sign in with Google. This allows your product team to generate roughly 50,000 characters of synthetic speech without entering payment details, helping you validate voice quality and integration workflows before committing to the API.
$0.50 credit for new Google accounts
Sign up on /get-api-key/ using your Google account to receive this trial credit automatically. It is valid for 7 days from creation, giving you ample time to test voice outputs like 'aria' for clear instructions or 'atlas' for neutral updates.
- Valid for 7 days
- Roughly 50,000 characters
- No credit card required
Valid for 7 days
The trial balance expires after one week. If you do not top up, the account remains active but generates no new audio until you add funds. This ensures you can evaluate the API's performance in a realistic timeframe without long-term commitment.
Email accounts start without trial
If you create an account using only an email and password, you start with zero balance. You must top up immediately to generate your first audio file. This option is suitable for teams that prefer direct email authentication over Google sign-in.
Payment via USDT (TRC-20)
Add funds to your NavVoice account using USDT on the TRON network. This method keeps transactions simple and avoids the friction of traditional banking, allowing product teams to focus on building navigation features rather than managing payment gateways.
Minimum top-up of $5
The lowest amount you can add is $5. This low threshold lets teams test integration costs without committing significant capital, while still providing enough volume for substantial testing cycles.
Automatic credit within minutes
Once your TRC-20 transfer is confirmed on the blockchain, your balance updates automatically. You do not need to wait for manual approval or send a support email; the system credits your account within minutes.
No credit cards or PayPal
We do not process credit cards or accept PayPal. By using only cryptocurrency, we eliminate recurring subscription fees, monthly seats, and complex VAT invoice requirements. Your balance never expires, and you only pay for what you generate.
Cost Examples for Navigation Prompts
Pricing is simple: $0.01 per 1,000 characters. Navigation prompts are short and predictable, making budgeting easy for product teams.
Each character, including spaces, counts. Use the free trial credit to test exact costs before integrating into your infotainment system.
Short route instructions cost
A typical turn-by-turn instruction like 'Turn left in 200 meters' is about 30 characters. This costs roughly $0.0003 per prompt.
For a single vehicle generating 100 instructions per hour, the cost is minimal, allowing high-frequency updates without breaking the budget.
- Cost per short instruction: ~$0.0003
Long route text splitting costs
Longer trip summaries may exceed the 4096-character limit per request. Split the text into parts and join the audio files.
Each part is charged separately. Ensure efficient text splitting to minimize overhead while maintaining natural speech flow.
- Max 4096 characters per request
- Split and join for longer texts
Multi-language navigation costs
Support for 23 languages means you can serve diverse markets. Each character is priced at $0.01 per 1,000 characters.
Switching languages does not change the price. Just set the correct language code in the API request for accurate results.
- 23 languages supported
- No additional cost for language switching
Billing for Failed Requests
When a synthesis request fails, you are not charged for the attempt. This ensures that transient network issues or temporary engine unavailability do not inflate your bill. You only pay for successfully generated audio files.
Free if synthesis fails
Failed requests are completely free. If the API returns an error during processing, no characters are deducted from your balance. This protects your budget during initial integration or high-load periods.
Full charge returned
In the rare case a charge is applied to a failed request, the full amount is returned. You can verify this in your account usage logs, ensuring accurate billing for every navigation prompt.
No hidden fees for errors
There are no penalty fees for retrying failed requests. You can safely retry a prompt without worrying about extra costs, as each attempt is billed independently based on its final status.

Volume Considerations for Fleet Apps
For automotive navigation systems, accurate volume estimation prevents unexpected charges during high-frequency updates. Each voice instruction consumes characters based on the text length, so understanding your typical prompt size helps forecast monthly costs.
Estimating character counts
Navigation prompts vary in length. A simple instruction like "Turn left in 200 meters" uses far fewer characters than a detailed lane guidance description. Calculate your average character count per request and multiply by your expected daily request volume to estimate usage.
Costs for high-frequency updates
Fleet apps often send frequent updates. With a rate limit of 60 requests per minute, ensure your app doesn't exceed this threshold, which could delay responses. Since pricing is per character, frequent short updates may accumulate costs faster than less frequent, longer instructions if the total character count remains high.
- - Track average characters per instruction
- - Monitor request frequency against the 60 req/min limit
- - Calculate total monthly cost based on estimated daily volume
Optimizing text for lower costs
Refine your navigation text to be concise without losing clarity. Removing unnecessary words reduces character count, directly lowering costs. For example, "Continue straight for 500 meters" is clearer and cheaper than "Please continue straight for a distance of 500 meters." Optimize your TTS inputs to balance natural sound with cost efficiency.
- - Remove redundant words
- - Use concise phrasing
- - Test different text lengths for clarity vs. cost
No Hidden Costs or SLAs
We keep billing simple by avoiding complex enterprise agreements. You pay only for what you generate, with no long-term commitments or minimum spend requirements. This structure allows product teams to scale their navigation voice interfaces up or down without negotiating contract terms or worrying about unused capacity fees.
No enterprise contracts
Our pricing model is designed for flexibility. There are no monthly plans or seats to manage. You retain full control over your spending, making it easy to integrate TTS into navigation systems without administrative overhead or rigid contractual obligations.
No uptime guarantees
We do not offer Service Level Agreements (SLAs) or uptime guarantees. Requests are processed sequentially, which means under heavy load, a request may wait in a queue. This ensures fair processing but does not come with a promised availability percentage or compensation for downtime.
- No SLA included
- Requests processed sequentially
- Queueing possible under load
No VAT invoices
We do not issue VAT invoices or handle complex tax documentation. Payments are made via USDT (TRC-20), and we keep record-keeping straightforward for global product teams. This avoids the need for multiple regional tax forms and simplifies your accounting process.
Technical Limits for Navigation Systems
Navigation systems demand reliable, low-latency speech synthesis without exceeding API constraints. Understanding these technical boundaries ensures smooth in-car experiences, from turn-by-turn directions to multi-language announcements.
4096 character limit per request
Each API call processes up to 4,096 characters. For lengthy route descriptions, split the text into chunks and join the resulting audio files seamlessly.
Rate limits: 60 requests per minute
Keys allow 60 requests per minute (10 before the first top-up). Requests queue under load, so plan your burst traffic accordingly to avoid delays.
Supported languages and voices
We support 23 languages, including Hindi, with 8 voice presets. Any voice can speak any supported language; set the language field explicitly for non-English Latin text.
- Voices: aria, nova, luna, sage, felix, milo, atlas, orion
- Formats: mp3, wav, opus, flac, pcm
- Speed: 0.25–4.0x
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. A neutral tone works best for factual updates, while warmer tones suit conversational interactions.
23 languages
Any voice speaks any of these languages.
