Frequently asked questions
Who runs Kiriya Editorial?
Kiriya Editorial is an independent editorial resource for digital agencies building voice-enabled features for online stores. We compare the browser Web Speech API with a reliable cloud TTS API to help you choose the right audio experience for your clients.
Are the voices licensed?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures that the synthetic speech generated by our API rests on properly licensed source material for commercial use.
Do you use customer data for training?
No. 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. Only request metadata (time, characters, status) is kept for billing purposes.
Is there an uptime guarantee?
No. We do not offer an SLA or an uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue. We do not provide enterprise contracts or on-premise installation options.
How do I contact support?
Support is by email only. There is no phone number, no live chat, and no dedicated support line. You can reach us via the contact page or by emailing the support team directly for assistance with your account.
What is the API key limit?
You have a rate limit of 60 requests per minute per key. Before the first top-up, this limit is 10 requests per minute. You can issue a new key at any time, which immediately stops the old one.
Can I transfer my balance?
No. The balance is tied to your specific account on this site. There is no mechanism to transfer funds between accounts or to other users. Balances do not expire, but they remain locked to the account that holds them.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, standard refunds are not explicitly mentioned beyond the failed request policy. Payments are made via USDT on the TRON network.
Are the voices human or AI?
The voices are synthetic, generated from licensed recordings of human speakers. Every generated file carries an inaudible watermark that marks it as synthetic speech. They are not real-time human recordings but AI-generated audio based on human source material.
Is the API open source?
No. We do not offer an official SDK of our own, nor is the API code open source. You can use the OpenAI SDK or plain HTTP by changing the base_url. There is no browser extension or WordPress plugin.
Can I use the API commercially?
Yes. The voices are based on CC BY 4.0 licensed recordings and public-domain readings, making them suitable for commercial use in online stores. There are no monthly plans or seats, allowing flexible commercial integration for digital agencies and developers.
Do you have a privacy policy?
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. Request metadata is kept for billing. Specific legal details are not detailed on this page.
How are voices selected?
We offer eight presets: aria, nova, luna, sage, felix, milo, atlas, and orion. These are based on licensed recordings from LibriTTS-R and LibriVox. Any voice can speak any of the 23 supported languages without additional configuration.
What is the watermark?
Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This watermark identifies the audio as AI-generated without affecting the listening experience. It is embedded directly into the audio file upon generation.
Our Mission
Kiriya Editorial bridges the gap between browser-based Web Speech APIs and reliable cloud synthesis for digital agencies. We provide the editorial resources and technical clarity needed to integrate voice-enabled features into online stores without the overhead of managing complex infrastructure.
Our goal is to help teams choose the right audio experience for their clients by comparing capabilities, costs, and limitations transparently.
Simplifying TTS for agencies
Agencies often juggle multiple client projects, each requiring different audio standards. We simplify the decision-making process by offering a clear comparison between local browser synthesis and our cloud API. This allows teams to deliver consistent voice experiences across diverse e-commerce platforms without reinventing the wheel for every integration.
Focus on e-commerce
We specifically target the needs of online stores, where product descriptions, notifications, and accessibility features require high-quality audio. By focusing on this sector, we ensure our technical details and pricing models align with the volume and reliability requirements typical of retail environments.
Editorial approach
Unlike typical vendor pages, we publish an editorial resource that compares features and facts. We avoid hype, focusing instead on concrete data like character limits, pricing per million characters, and supported languages. This approach helps agencies make informed decisions based on actual performance and cost, not marketing promises.
Voice Licensing
Kiriya Editorial’s voice library is built on licensed recordings from LibriTTS-R, providing a transparent foundation for digital agencies. We ensure that the audio your clients hear originates from clear, verifiable sources, allowing you to confidently integrate voice features into online stores without worrying about obscure provenance.
Our approach prioritizes clarity in licensing so agencies can understand exactly what rights accompany the synthetic speech they deliver to end-users.
The voices are derived from LibriVox public-domain audiobook readings, ensuring a broad, accessible base for our eight presets. This origin allows us to offer consistent quality across languages while maintaining legal simplicity for commercial use.
LibriTTS-R, the dataset we utilize, is distributed under the Creative Commons Attribution 4.0 International license. This means the source material is free to use and modify, provided proper attribution is given, which simplifies compliance for agencies building voice-enabled e-commerce features.
The recordings originate from LibriVox, a platform dedicated to public-domain audiobooks. By sourcing from these existing public-domain readings, we ensure that the base vocal performances are free of restrictive copyright encumbrances, allowing us to distribute the resulting TTS audio freely to our API users.
LibriTTS-R source
Kiriya Editorial’s voice library is built on licensed recordings from LibriTTS-R, providing a transparent foundation for digital agencies. We ensure that the audio your clients hear originates from clear, verifiable sources, allowing you to confidently integrate voice features into online stores without worrying about obscure provenance.
CC BY 4.0 license
LibriTTS-R, the dataset we utilize, is distributed under the Creative Commons Attribution 4.0 International license. This means the source material is free to use and modify, provided proper attribution is given, which simplifies compliance for agencies building voice-enabled e-commerce features.
Public domain origins
The recordings originate from LibriVox, a platform dedicated to public-domain audiobooks. By sourcing from these existing public-domain readings, we ensure that the base vocal performances are free of restrictive copyright encumbrances, allowing us to distribute the resulting TTS audio freely to our API users.
Data Policy
We use your input text solely to generate the requested audio file. Your source text is not ingested into our training datasets, ensuring that your copy remains private and is not used to improve the underlying voice models.
No training on input
Unlike some consumer-grade services, we do not retain your text for long-term model training. The input is processed to produce the audio output and is discarded immediately after synthesis.
No storage of audio
Generated audio files are returned directly in the API response and are not permanently stored on our servers. Once you receive the file, we do not keep a copy of the synthesized speech.
Metadata retention
We retain request metadata, including timestamp, character count, and status, strictly for billing purposes. This data allows us to accurately calculate costs and verify that charges match the characters processed, ensuring transparency in your usage history.
Technical Limits
Kiriya Editorial operates a reliable cloud API, but it is not an enterprise-grade platform with guaranteed uptime. Understanding the technical boundaries helps agencies set realistic expectations for their clients' voice-enabled features.
60 requests per minute
Each API key is limited to 60 requests per minute. Before the first top-up, this limit drops to 10 requests per minute. Requests are processed sequentially, so heavy loads may cause queuing delays.
4096 character limit
A single request can process up to 4,096 characters. For longer texts, you must split the input into parts and join the resulting audio files.
No SLA
We do not offer an official Service Level Agreement (SLA) or uptime guarantee. While the API is designed for stability, there is no contractual obligation for specific availability percentages.

Support and Contact
Kiriya Editorial operates with a lean support structure designed to keep overhead low and pricing competitive for digital agencies. We handle all inquiries exclusively through email.
There is no phone number listed on this site. We do not offer live chat, voice support, or dedicated account managers for standard plans. This approach allows us to maintain the simple, flat rate of $0.01 per 1,000 characters.
Email support only
We handle all inquiries exclusively through email. This ensures every question about the API, billing, or integration gets a documented response without the noise of phone trees.
There is no phone number listed on this site. We do not offer live chat, voice support, or dedicated account managers for standard plans. This approach allows us to maintain the simple, flat rate of $0.01 per 1,000 characters without hidden support premiums.
No phone support
We do not maintain a call center or offer voice support. If you need to speak to someone, you can email us, and we will respond as quickly as possible via text.
This limitation is intentional. By avoiding the costs of telephone infrastructure, we keep our infrastructure costs low, which directly benefits your bottom line when scaling voice features for your clients.
Response times
Our team aims to reply to all support emails within 24 hours during business days. During high-volume periods, response times may vary slightly, but we prioritize clear, written solutions over quick verbal fixes.
For urgent billing issues, please include your API key in the subject line for faster tracking. We do not guarantee a specific response time, as we are a small editorial team managing both content and support.
- Include your API key in the subject line for urgent billing issues.
- Expect replies within 24 hours during business days.
- No guaranteed SLA for support response times.
Network of Sites
Kiriya Editorial operates as a network of independent storefronts, each serving the same reliable cloud TTS API. This structure allows us to maintain distinct editorial voices while ensuring that every site delivers consistent technical performance and pricing for digital agencies building voice-enabled features for online stores.
Independent storefronts
Each site in our network functions as a self-contained storefront with its own branding and audience focus. You can sign up for an account on any site, and while your key and balance are specific to that domain, the underlying API behavior remains identical across all of them.
Same API core
Regardless of which site you use, you are accessing the same core API infrastructure. The endpoint structure, voice presets, language support, and rate limits are uniform. This ensures that if your agency scales across different client projects, your integration logic remains stable even if you switch storefronts.
Distinct branding
While the technical foundation is shared, each site maintains its own editorial identity. This allows us to tailor the narrative and examples to specific agency workflows without confusing the user experience. You can explore different perspectives on the same product, all backed by the same reliable engine.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The following examples illustrate how to implement each approach using standard tools available to modern web developers.
23 languages
Any voice speaks any of these languages.
