Frequently asked questions
Who operates Ufago?
Ufago is an independent storefront for a cloud text-to-speech API. We help online store teams turn product descriptions into natural-sounding audio. Our API lets you generate speech in 23 languages with simple code, so you can add voice to your storefront without hiring voice actors. We are not affiliated with OpenAI or other major brands.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file carries an inaudible watermark that marks it as synthetic speech. The voices include female options like Aria and Nova, and male options like Felix and Milo.
Is my data 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. We keep request metadata, such as time, characters, and status, strictly for billing purposes. No long-term storage of your actual content occurs.
Can I use the API commercially?
Yes. The API is designed for commercial use, such as adding voice to your online store storefront. There are no monthly plans, seats, or minimum spend requirements. You pay only for what you use at $10 per 1 million characters, with failed requests free.
Is there a privacy policy?
We do not store generated audio or input text beyond the immediate response. Request metadata is kept for billing. We do not offer specific certifications like GDPR or HIPAA, but we process data solely for synthesis. For more details, please contact us via email.
How can I contact support?
Support is available by email only. We do not have a phone number, live chat, or on-site support team. You can reach us through the /contact/ page. We aim to respond to your inquiries as quickly as possible via email communication.
Is the API accessible?
Yes, our API helps online store teams create accessible audio for product descriptions and help text. You can generate speech in 23 languages. The API returns standard audio formats like MP3, WAV, and FLAC, which are widely supported by accessibility tools and screen readers.
Can I create custom voices?
No, we do not offer custom voice cloning or the ability to upload your own voice. You can choose from eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These voices are based on licensed recordings and cannot be modified or cloned by customers.
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 from the script.
How long is the trial account valid?
The free trial provides $0.50 of credit, valid for 7 days. This allows about 50,000 characters of generation. The trial is given when you sign in with Google. Accounts created with email and password start without this trial credit.
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. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts may take time as they are split and joined.
How does authentication work?
Authentication uses a Bearer token. You must include Authorization: Bearer tts-... in your request headers. Each account has one active key. You can issue a new key at any time, which immediately stops the old one. Keys are managed via your account dashboard.
What is a JSON body?
The JSON body contains your request parameters for the POST endpoint. It includes fields like model, input (text), voice, response_format, and speed. This structure matches the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply changing the base URL to ours.
How do I handle long texts?
Split your text into parts of up to 4096 characters per request. Send each part separately and join the resulting audio files. This ensures compliance with the character limit. Our typical speed is roughly real-time, so processing long texts may take time proportional to the audio length.
Can I use the API offline?
No, this is a cloud API. You must send text to our endpoint https://api.ufago.top/v1/audio/speech to receive an audio file. There is no offline mode or local installation. You need an internet connection and a valid API key to generate speech.
Is there API documentation?
Yes, detailed documentation is available at /docs/. It covers endpoints like POST /v1/audio/speech, GET /v1/voices, and GET /v1/models. You can also find ready curl examples and usage instructions on the /get-api-key/ page to help you integrate the API into your workflow.
How do I create an API key?
Sign up on the /get-api-key/ page using Google or an email and password. The page displays your API key, balance, and usage statistics. You can issue a new key at any time, which invalidates the previous one immediately. Keys are specific to this site.
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. The speech endpoint is POST /v1/audio/speech. Other endpoints include GET /v1/voices for voice details and GET /v1/models for model information.
How do I identify errors?
If synthesis fails, the charge is returned in full. The API returns standard HTTP status codes to indicate success or failure. You can monitor your usage and status via the account dashboard. Failed requests do not consume your character balance.
Can I scale the API?
Yes, there are no monthly plans, seats, or minimum spend limits. You can scale usage by making more requests, limited only by the rate limit of 60 requests per minute per key. For higher throughput, you can manage multiple keys or split text efficiently.
Our Team
Ufago is built by a small, focused team dedicated to making text-to-speech accessible for online stores. We handle the engineering and voice licensing so your product team can add audio to descriptions without hiring voice actors.
Editorial Team
Our editorial staff curates the eight voice presets and manages the 23 supported languages. They ensure the tone matches the needs of e-commerce, from warm narrators to neutral news voices.
Development
Developers maintain the API infrastructure, ensuring reliable endpoints for speech synthesis and voice retrieval. We optimize the pipeline to handle 4096-character requests efficiently, with generation times roughly matching real-time for long texts.
Support
Our support team handles all customer inquiries via email. We are available to help with API integration questions and billing issues, ensuring your store’s audio features run smoothly.
Licenses
Our voices are built from licensed recordings, ensuring clear legal foundations for commercial use. We selected high-quality source material to maintain natural audio characteristics across all 23 supported languages.
LibriTTS-R
The core of our voice library comes from the LibriTTS-R dataset. This collection provides diverse, high-fidelity speech samples that form the basis for our eight distinct voice presets.
CC BY 4.0
We utilize data licensed under Creative Commons Attribution 4.0. This allows us to process and adapt the audio while respecting the original creators' rights.
Public Domain
Some source material originates from LibriVox public-domain audiobook readings. These contributions ensure broad accessibility and legal clarity for generated audio files.
Data Policy
When you send text to our API, we process it to generate speech and return the audio file directly in the response. The input text is used solely for this immediate synthesis task. We do not retain the audio files after delivery, ensuring your product descriptions or help text remain transient and private.
We do not use your input data to train our models. The voices are based on licensed recordings from LibriTTS-R and LibriVox. Your content stays yours, used only for the specific audio generation you requested, without becoming part of our training corpus.
Text Not Stored
Generated audio is returned in the response and not stored on our servers. Your input text is processed on-demand to create the audio file and is not kept long-term for other purposes.
This ensures that your product descriptions, help text, or marketing copy remain confidential and are not archived in our database after the synthesis is complete.
- Audio files are transient and returned immediately.
- Input text is not retained after synthesis.
No Training
We do not use your input text to train or improve our TTS engine. The voices are derived from specific licensed sources, and your data does not contribute to model development.
This means your unique content remains distinct from the training data, preserving the originality of your store's voice assets.
- Input text is not used for model training.
- Your data does not influence future voice models.
Transparency
We keep request metadata—such as time, character count, and status—strictly for billing purposes. This ensures accurate charging based on our $0.01 per 1,000 characters rate.
You can view this usage data directly in your dashboard, providing full visibility into how much text you have processed and how much you have spent.
- Metadata kept only for billing.
- Full usage visibility in your dashboard.
Limitations
Ufago delivers reliable, straightforward speech synthesis without the complexity of real-time streaming or advanced markup. We focus on precise, on-demand audio generation that fits seamlessly into your e-commerce workflow, whether you are creating product descriptions or help articles.
Understanding what we do not offer helps you plan your integration correctly. We prioritize stability and clarity over experimental features, ensuring your text-to-speech output is consistent and easy to manage.
No Streaming
We do not offer WebSocket or streaming endpoints. You send a text request and receive the complete audio file once synthesis finishes. This model ensures every request is processed accurately and billed correctly, without the overhead of partial audio chunks.
No SSML
Our API does not support Speech Synthesis Markup Language (SSML). You control speed through the speed parameter (0.25–4.0) and voice selection. This keeps the integration simple and reduces parsing errors for product teams using standard text inputs.
No Voice Cloning
We do not offer custom voice cloning or the ability to upload your own voice samples. Your choices are limited to our eight licensed presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). This ensures consistent quality and avoids the legal complexities of voice rights for each client.

Contact
Ufago is built by a small editorial and development team. We handle voice selection, code integration, and daily operations. Our focus is keeping the API stable and the pricing clear for online store teams.
Email Support
We respond to all questions by email. Send your request to [email protected]. We aim to reply as quickly as possible. This is our only support channel, so please include your API key and a clear description of the issue.
No Phone
We do not offer a phone number. Without a direct line, you can avoid hold times and voice queues. Written emails create a clear record of your problem and our solution, which is helpful for debugging API integration issues.
No Live Chat
There is no live chat widget on this site. This keeps our operational costs low and allows us to offer $0.01 per 1,000 characters. You get the same support quality without the distraction of real-time pop-ups.
Imprint
Ufago is an independent text-to-speech API provider helping online store teams turn product descriptions into natural-sounding audio. We operate as a standalone service, distinct from major tech brands, focusing on simple code integration for accessibility and learning.
Our service generates speech in 23 languages using licensed voices, allowing you to add voice to your storefront without hiring voice actors. We provide a straightforward API with clear pricing and no hidden fees.
Address
Ufago TTS API Independent Storefront Remote Operations
Responsible Person
The editorial and development team manages content. For legal inquiries, contact our support email.
Liability
We strive for accuracy in our API documentation and pricing. However, we do not guarantee uninterrupted service. Generated audio is synthetic and not a substitute for professional legal or medical advice.
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.
