Frequently asked questions
Which voice is best for product descriptions?
Q: Which voice is suitable for product descriptions? A: Felix offers an energetic, promo-friendly tone, making him ideal for highlighting product features. Aria provides a warm, clear narrator style, while Nova delivers a bright, upbeat vibe. Milo is great for a friendly, conversational approach. Choose the voice that matches your brand’s personality and the specific tone of your product listings.
How long does generation take?
Generation takes roughly real time, about 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request might wait in a queue. This ensures consistent quality without requiring dedicated infrastructure, making it predictable for standard e-commerce traffic volumes.
Can I change the speech speed?
Yes, you can adjust the speed between 0.25 and 4.0. This allows you to slow down complex product details for clarity or speed up simple updates. The speed parameter is part of the JSON request body, giving you precise control over the audio output to match your store’s pacing and accessibility needs.
Which audio formats are supported?
We support mp3, wav, opus, flac, and pcm formats. Choose mp3 for efficient web streaming or wav for high-quality local playback. Opus offers excellent compression for mobile apps. These formats ensure compatibility with most e-commerce platforms and accessibility tools, allowing you to deliver audio seamlessly across different devices and user interfaces.
How do I pay with USDT?
Top up your balance using USDT on the TRON network (TRC-20). The minimum deposit is $5. Credits are added automatically within minutes after the transfer is confirmed. There are no monthly plans or subscriptions. Your balance does not expire, and you only pay for the characters you actually use for speech synthesis.
Is there a free trial account?
Yes, signing in with Google gives you $0.50 of trial credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can test the API’s capabilities and voice quality before committing to a USDT top-up for ongoing production use in your store.
How do I create an API key?
Go to /get-api-key/ and sign up using Google or email plus password. Your account is specific to this site. Once registered, you will see your active API key, balance, and usage stats. You can issue a new key at any time, which immediately invalidates the previous one for security.
What is the base URL?
The API base URL is https://api.ufago.top/v1. You can use the official OpenAI SDKs by setting this as the base URL. Send POST requests to /v1/audio/speech with your JSON body. This ensures compatibility with standard TTS workflows, allowing you to integrate our service into existing codebases with minimal changes.
How do I recognize errors?
Failed requests are free, and the charge is returned in full. Check the HTTP status code and response body for error details. Common issues include invalid keys, rate limits, or input text exceeding 4096 characters. Monitor your dashboard for usage logs to track failures and ensure your integration handles retries or fallbacks appropriately.
Can I scale the API?
The API handles requests sequentially, so under heavy load, requests may queue. The rate limit is 60 requests per minute per key. For higher volume, you can manage multiple keys or split large texts. There is no SLA or uptime guarantee.
Are my input texts stored?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored permanently. We keep request metadata like time, character count, and status for billing purposes. Your product descriptions remain private and are not repurposed for model improvement or other uses.
Is the API accessible?
Yes, the API generates audio in 23 languages, supporting accessibility needs. You can adjust speed and choose voices like Aria or Luna for clear narration. The output formats include mp3 and wav, widely supported by screen readers and audio players. This makes it easy to add voice to product pages, improving accessibility for all users.
Can I create custom voices?
No, we do not offer custom voice cloning or uploading your own voice. You can choose from eight preset voices based on licensed recordings. These include options like Felix for promos or Atlas for news. If you need a specific tone, you can select the preset that best matches your desired brand voice.
Which languages are supported?
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. If the language is not set, it is guessed, but specifying it ensures accuracy for non-English Latin text.
How long is the trial valid?
The trial credit of $0.50 is valid for 7 days after signing in with Google. It covers approximately 50,000 characters. After 7 days, any remaining trial balance expires. This allows you to test the API thoroughly. For long-term use, top up with USDT, as your main balance does not expire.
Is there a rate limit?
Yes, the limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. If you exceed the limit, requests may be delayed or rejected. Monitor your usage on the dashboard. For higher throughput, consider splitting texts or managing multiple keys during peak sales periods.
How does authentication work?
Use the header Authorization: Bearer tts-... with your API key. You get one active key per account. You can issue a new key anytime, which immediately stops the old one. This ensures secure access to your balance and usage data. Keep your key private and include it in every request to the API.
What is a JSON body?
The JSON body contains your request parameters: model, input, voice, response_format, and speed. It is sent via POST to the speech endpoint. For example, {"model": "tts-1", "input": "Hello", "voice": "aria"}. This structure is compatible with the OpenAI SDK, making it easy to integrate into your existing backend.
How do I handle long texts?
Split text into parts of up to 4096 characters per request. Generate audio for each part, then join the files. This ensures you stay within the character limit. You can automate this in your code by chunking product descriptions. The API processes requests sequentially, so plan your splitting logic to optimize for speed and cost.
Can I use the API offline?
No, this is a cloud API. You must send requests to https://api.ufago.top/v1 over the internet. There is no local SDK. The audio is generated on our servers and returned in the response. You need a stable internet connection to generate speech for your product pages or apps.
Why Use TTS for Online Stores?
Online stores face increasing pressure to meet accessibility standards like WCAG. Providing audio versions of product descriptions and help text ensures your site is usable by visually impaired customers and those who prefer listening while shopping.
Beyond compliance, TTS transforms static content into dynamic experiences. Imagine a shopper in Japan reading German product specs or a user in Brazil listening to English reviews. Our API handles this, removing language barriers without hiring multilingual staff.
Accessibility Compliance
Text-to-speech is a key tool for meeting accessibility requirements. By converting product titles, descriptions, and help articles into audio, you allow users with visual impairments or reading difficulties to consume content independently. This reduces friction and ensures your store is inclusive for all shoppers.
Many jurisdictions now encourage or mandate digital accessibility. Offering audio alternatives demonstrates good faith and reduces legal risk. It also helps users with dyslexia or attention deficits who find large blocks of text challenging to process quickly.
- Convert product descriptions to audio for visually impaired users
- Make help articles accessible to readers with dyslexia
- Reduce legal risk by meeting WCAG guidelines
- Improve content consumption for users on the go
Multi-language Support
Your customers speak many languages, but your team might not. With support for 23 languages, you can serve a global audience without hiring translators for every new market. Our API detects the language automatically or lets you set it explicitly, ensuring accurate pronunciation.
This capability is crucial for e-commerce sites selling internationally. A shopper in India can listen to English product details, while a user in China can hear Mandarin descriptions. You maintain a consistent brand voice across borders without extra operational overhead.
Even within a single country, regional accents matter. Our voices cover diverse linguistic nuances, ensuring that your content sounds natural and professional, regardless of where your customers are located.
- Support for 23 languages including English, Spanish, and Mandarin
- Automatic language detection or explicit setting
- Serve global customers without hiring multilingual staff
- Maintain consistent brand voice across borders
Enhanced User Experience
Audio adds a sensory layer to your store that text alone cannot match. Users can listen to product reviews while cooking, driving, or commuting. This flexibility keeps them engaged longer and increases the likelihood of a purchase.
Short, clear audio snippets can also summarize complex product features. Instead of reading long paragraphs, users get a quick overview in seconds. This reduces cognitive load and helps customers make faster, more confident buying decisions.
Moreover, audio content is often more memorable than text. By integrating TTS, you create a richer, more immersive shopping experience that
- Allow listening while multitasking (driving, cooking)
- Summarize complex features in seconds
- Increase engagement and time on site
- Create a memorable, immersive shopping experience
Preparation
Before writing code, you need credentials to authenticate your requests. Create a dedicated API key through your account dashboard to ensure secure access to the synthesis engine. You can issue a new key at any time, which immediately invalidates the previous one, giving you full control over security without downtime.
Start testing with a free trial account to explore the API’s capabilities without committing funds. This trial provides $0.50 in credit, allowing you to generate approximately 50,000 characters over seven days. It is perfect for validating voice quality and integration logic before scaling up for your store’s product descriptions.
Create Your API Key
Sign up via the /get-api-key/ page using Google or email. Your dashboard displays your active key, current balance, and a ready-to-use cURL example. Keep this key secure, as it authorizes all character usage and billing.
- One active key per account
- Instant invalidation upon issuing a new key
- View usage stats in real-time
Use the Free Trial Account
Google sign-ups automatically receive $0.50 trial credit. Email-based accounts start with zero balance. Use this credit to test voice presets and format options without risk.
- Valid for 7 days
- Approx. 50,000 characters
- No credit card required
Read the Documentation
Review the /docs/ page to understand request shapes, rate limits, and supported parameters. Familiarize yourself with the 8 voice presets and 23 languages.
- Endpoint specifications
- Voice and language details
- Error handling guides
Integration Steps
Integrating Ufago’s TTS API into your e-commerce stack is straightforward because the request shape mirrors the widely adopted OpenAI standard. This means you can connect voice capabilities to your product pages or help centers with minimal code changes.
Start by updating your API client’s base URL to point to our infrastructure. Then, send POST requests to the speech endpoint with your generated audio payloads. We’ve designed this flow to fit seamlessly into existing backend services without requiring complex new middleware.
Set the Base URL
Configure your SDK or HTTP client to use https://api.ufago.top/v1 as the base URL. This single change allows you to reuse familiar OpenAI SDK libraries, directing all calls to our TTS engine instead of their service. Ensure your authentication header includes your unique Bearer token for every request.
- Base URL: https://api.ufago.top/v1
- Auth header: Authorization: Bearer tts-...
Use the Speech Endpoint
Send a POST request to /v1/audio/speech with a JSON body containing the model, input text, voice, and response_format. Keep text under 4096 characters per request. The API returns the audio file directly in the response, which you can save for later use.
For longer product descriptions, split the text into chunks, generate audio for each part, and join the files. This ensures consistent quality and avoids hitting character limits while maintaining a natural listening experience for your customers.
- Endpoint: POST /v1/audio/speech
- Max input: 4096 characters
- Returns: Audio file
Handle Errors Gracefully
If synthesis fails, the request is free, so you won’t be charged for wasted credits. Always check the HTTP status code and handle errors like rate limits (60 requests per minute) by implementing exponential backoff. This prevents your storefront from freezing when traffic spikes during sales events.
Log error details for debugging but keep the user experience smooth by showing a fallback message or retrying the request automatically. Our API is designed to be reliable, but network issues can happen, so resilient error handling is key for a professional store.
- Failed requests are free
- Rate limit: 60 req/min
- Implement backoff strategies
Choosing Voices
Choosing the right voice sets the tone for your product descriptions and help text. Ufago provides eight presets, each with a distinct character, so you can match your brand’s personality without hiring voice actors.
Our voices are based on licensed recordings from LibriTTS-R and LibriVox, ensuring natural-sounding audio that supports accessibility across your storefront.
Female Voices: Aria, Nova, Luna, Sage
Aria offers a warm, clear narration style ideal for standard product descriptions. Nova brings a bright, upbeat energy suitable for promotional content. Luna provides a soft, storytelling tone for detailed guides, while Sage delivers a calm, instructional voice perfect for help text.
These voices ensure consistent quality across English and other supported languages, helping you maintain a professional yet approachable brand voice.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male Voices: Felix, Milo, Atlas, Orion
Felix is energetic and great for promo content, while Milo offers a friendly, conversational tone for customer support. Atlas provides a neutral, news-style delivery for straightforward information, and Orion adds a deep, documentary feel for premium or detailed content.
Each male voice supports the same 23 languages as the female presets, allowing for consistent branding in international markets.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Test Voices for Your Brand
Use the free trial to test how each voice sounds with your actual product copy. Generate short clips to see which tone resonates best with your audience.
Remember that all generated files carry an inaudible watermark, marking them as synthetic speech. This helps maintain transparency while delivering high-quality audio.
Configuring Languages
Ufago supports 23 languages, allowing your store to reach global customers without hiring local voice talent. From Arabic to Turkish, every voice preset handles all supported languages natively.
Accurate pronunciation depends on correctly identifying the input text. You can either specify the language explicitly or rely on automatic detection, which defaults to English for Latin scripts.
Support for 23 Languages
Our API covers Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
This broad coverage ensures your product descriptions and help texts sound natural in the customer’s native tongue, improving accessibility and engagement.
Explicitly Set the Language
For non-English text in Latin script, always set the language field. Without it, the system guesses English, which may cause pronunciation errors.
Pass the ISO code (e.g., language: "fr") in your request to ensure the voice renders the text correctly in the target language.
Automatic Language Detection
If you omit the language parameter, the API attempts to detect the script. Latin text defaults to English.
Use explicit language codes for mixed-language content or languages outside the Latin alphabet to guarantee accurate synthesis every time.
Selecting Audio Formats
Choosing the right audio format is a balance between quality, file size, and compatibility. Most modern web browsers handle compressed audio seamlessly.
MP3
MP3 is the most universally supported format for web playback. It offers a good balance between file size and audio quality, ensuring fast load times for customers on mobile devices or slower connections.
WAV
WAV provides uncompressed, high-fidelity audio. Use this format if you need pristine quality for accessibility standards or if your audio player requires lossless input. Note that WAV files are significantly larger than MP3s.
OPUS, FLAC, and PCM
OPUS offers superior compression efficiency for web delivery. FLAC provides lossless compression, reducing file size without quality loss. PCM is raw, uncompressed audio data, ideal for direct processing but resulting in large files.
Understanding Costs
Pricing is straightforward: $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, ensuring you only pay for successful audio generation. Your balance does not expire, and there are no monthly subscriptions or hidden fees.
$10 per Million Characters
The API charges based on character count, including spaces and punctuation. For example, generating a 4,000-character product description costs $0.04. Short phrases may take a few seconds to generate, while longer texts process at roughly real-time speed.
Cost Calculation Examples
If your store has 100 products with average 2,000-character descriptions, monthly usage would be approximately 200,000 characters, costing $2.00. Even with high traffic, costs remain predictable and low compared to hiring voice actors for each update.
Payment Methods: USDT Only
Top-ups are processed via USDT on the TRON network (TRC-20). The minimum top-up amount is $5, and credits are added automatically within minutes of transfer. We do not accept credit cards, PayPal, or issue invoices with VAT.
- Minimum top-up: $5
- Network: TRON (TRC-20)
- No credit cards or PayPal
- Instant automatic credit

Testing and Debugging
Testing your integration ensures audio files generate correctly and errors are handled gracefully. Start with simple cURL commands to verify connectivity, then move to full SDK integration for production workflows. Understanding response codes helps you troubleshoot issues like rate limits or invalid inputs before they impact customers.
This section covers practical debugging steps specific to our API.
Use cURL Examples
Begin testing with direct HTTP requests using cURL. Send a POST request to the speech endpoint with your API key and sample text. This method confirms your key works and helps isolate network or authentication issues before building complex application logic.
- Replace
YOUR_API_KEYwith your actual key. - Adjust
inputandvoiceparameters to match your use case. - Check the response status code for immediate feedback.
Integrate with OpenAI SDKs
Since our API follows the same request shape as OpenAI, you can use official OpenAI SDKs by simply changing the base_url to https://api.ufago.top/v1. This allows you to leverage familiar code structures and error handling mechanisms already known to your development team.
Understand Error Codes
Monitor response headers and body for error details. Failed requests are free, so a charge reversal confirms a synthesis error. Common issues include invalid voice IDs, text exceeding 4096 characters, or rate limit exhaustion (60 requests/minute).
Use these codes to adjust retry logic or notify users of temporary service delays.
Production Readiness
Getting your TTS integration into production requires balancing speed with reliability. By respecting rate limits and handling long texts correctly, you ensure your storefront remains responsive even during peak shopping hours.
Proper monitoring and caching strategies help you stay within budget while delivering consistent audio quality to your customers.
Respect Rate Limits
Your API key allows 60 requests per minute. If you exceed this, requests may queue or fail. Start with a lower limit if you are unsure.
Failed requests do not count against your character balance, so retrying after a brief pause is safe.
- Limit: 60 requests/minute per key
- First 10 requests/minute before first top-up
Split Long Texts
Each request supports up to 4096 characters. For longer product descriptions, split the text into chunks and join the resulting audio files.
This ensures every segment generates quickly and accurately without truncation.
- Max 4096 characters per request
- Join audio files programmatically
Monitor Usage
Track your character consumption and request status via the dashboard. This helps you anticipate when to top up your USDT balance.
Regular monitoring prevents unexpected outages during high-traffic sales events.
- Check balance in dashboard
- Review request logs for errors
Optimization Tips
Refining audio output parameters can enhance the user experience without increasing costs. By adjusting speech speed and varying voice styles, you create a more dynamic and engaging listening environment for your customers.
Implementing caching for static content like product descriptions reduces unnecessary API calls, saving both time and money.
Adjust Speech Speed
You can control the playback rate between 0.25 and 4.0 using the speed parameter. Faster speeds work well for quick updates, while slower rates improve clarity for complex product details.
Mix Voices for Variety
Distribute different voices across your catalog to keep content fresh. Use warm narrators for stories and clear instructional voices for help text, ensuring each product feels unique without hiring new talent.
Implement Caching
Store generated audio files for static descriptions since the API does not retain them. This prevents redundant requests for unchanging product info, reducing latency and keeping your character usage efficient.
Support
For assistance, you can contact us via email for integration questions or billing details. We do not offer live chat or phone support, so please allow a bit of time for a detailed reply.
For immediate answers, consult the documentation or browse common questions below.
Email Support
Send your questions to our support email address. Since we do not have phone or live chat options, email is our primary channel for resolving issues related to API keys, usage, or technical details.
- No live chat or phone support
- Email is the only support channel
- Detailed responses provided for complex queries
Documentation
Our documentation covers all endpoints, parameters, and error codes. You can find ready-to-use cURL examples and SDK integration tips to help you get started quickly.
FAQ
Common questions about rate limits, character counting, and payment methods are answered here. If your question is not listed, please contact us via email.
- Rate limits and queue behavior
- Character counting and pricing
- USDT payment details
Conclusion
Integrating Ufago’s TTS API allows online store teams to enhance accessibility and engagement without hiring voice actors. By converting product descriptions and help text into natural-sounding audio, you support customers in 23 languages using simple code.
Summary
You now have a clear path to add voice to your storefront. With straightforward integration and transparent pricing, your team can add voice to your storefront.
Next Steps
Create your API key on our get-api-key page to start generating audio. Test the free trial credit to verify quality, then switch to USDT top-ups for production volume.
- Generate your key
- Test with free credit
- Top up with USDT
Resources
Dive deeper into technical details or find answers to common questions in our documentation and FAQ sections.
- API Reference
- Pricing Details
- Support Email
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. OPUS offers superior compression efficiency for web delivery.
23 languages
Any voice speaks any of these languages.
