Terms of service

The service

eloqnt/studio translates and reviews your app's messages with AI: the CLI analyzes your project locally and the hosted engine performs translations and source text reviews. We continuously improve the service, which means features can change over time.

Your account

You log in with GitHub and are responsible for activity under your account, including session tokens and API keys you create. Keep keys secret and revoke any key you believe is exposed.

Plans and billing

Both plans are billed through our merchant of record, Polar, who handles payment and tax.

The "Hosted model" plan is a recurring subscription. A trial period lets you evaluate the service first. You can cancel anytime from the billing portal—access continues until the end of the period you paid for, and there are no partial refunds for unused time.

The "Bring your own model" plan is a single payment that grants you access for as long as the service exists, including all future CLI and SDK releases. Refunds are available within 7 days of purchase—after that, the plan is non-refundable.

Switching from "Hosted model" to "Bring your own model" starts the "Bring your own model" plan immediately and schedules your "Hosted model" subscription to cancel at the end of the current period. "Hosted model" features stay available until then. "Bring your own model" grants are independent of any "Hosted model" subscription, so cancelling "Hosted model" never removes a "Bring your own model" entitlement you already paid for.

Included usage ("Hosted model" only)

The "Hosted model" plan includes a monthly amount of AI usage that resets with each billing cycle and doesn't roll over. During a trial, a quarter of that monthly amount is available. When the included usage is used up, translation and source review through the hosted engine pause until the next cycle—you're never charged extra. The "Bring your own model" plan doesn't include hosted usage: translations and reviews run on your own AI provider with your own API key.

Bring your own model

With "Bring your own model", translations and reviews run on the AI provider, model, and credentials you configure, not on ours. You're responsible for choosing a provider and model you're authorized to use, and for staying within that provider's terms and usage policies. That includes any restriction a provider places on automated or programmatic use of a consumer subscription. eloqnt/studio fetches the engine prompt to your machine and runs your model locally. We don't control your provider's availability, output, costs, or terms, and we're not responsible for them.

Your content

Your source code and messages remain yours. Strings you translate or review through the engine are processed to produce translations or suggested fixes and are not used to train models.

Fair use

Don't abuse the service: no attempts to circumvent usage limits, probe or disrupt the infrastructure, or resell access. We may suspend accounts that do.

Availability and liability

We aim for the service to be reliable but provide it "as is", without warranties. AI translations can contain mistakes—review them as you would a human translator's work. To the extent permitted by law, our liability is limited to the amount you paid in the twelve months before a claim.

Changes

We may update these terms as the service evolves. For meaningful changes we'll give notice (e.g. by email). Continuing to use the service after a change means you accept the updated terms.

Contact

Questions about these terms? Write me at jan@amann.work.