Privacy Policy

01Overview

Lirovo is the structured-extraction layer for video. We turn a video you point us at into typed JSON that matches a schema you define, and we serve that result through a developer API. This policy explains what data we collect when you use Lirovo, why we collect it, and the choices you have.

It applies to our website at lirovo.ai, the Lirovo API, and the SDKs and tools we publish. By using Lirovo, you agree to the practices described here. If you do not agree, please do not use the service.

02Information we collect

We collect three kinds of information.

• Account information. The details needed to create and run your account, such as your name, email address, organization, and the API keys we issue to you. We store a one-way hash of each API key, never the key itself.
• Content you submit. The video sources you ask us to process (a link or an uploaded file), the schemas you register, the destinations you configure, and the structured results we produce from your videos.
• Technical data. Request metadata that every API generates: timestamps, request identifiers, IP address, the endpoint called, status codes, latency, and the model and token counts for each extraction. We use this to operate, secure, and bill the service.

03How we use information

We use the information above to:

• Run the extraction pipeline and return your results.
• Authenticate requests and enforce per-tenant limits.
• Meter usage, calculate costs, and process payments.
• Detect, investigate, and prevent abuse, fraud, and security incidents.
• Diagnose errors and improve reliability and accuracy.
• Send service messages about your account, security, and material changes to the product.

We do not sell your data. We do not use the content of your videos or your extraction results to train foundation models.

04Video content and derived data

To produce a result, Lirovo fetches or receives your source video, normalizes it, transcribes the audio, samples and analyzes frames, builds an intermediate knowledge graph, and then reasons over that to fill in your schema. Each step writes artifacts (for example, a transcript, sampled frames, and the final JSON) that we store so you can retrieve them and trace every value back to the moment in the video it came from.

These artifacts belong to you. They are scoped to your tenant and are never combined with another customer's data. You can delete a job and its artifacts at any time through the API.

05Service providers and sub-processors

Lirovo runs on infrastructure and services operated by third parties. We share only the data each one needs to perform its function:

• Cloudflare hosts the entire platform: compute, object storage, the metadata database, queues, and the AI Gateway that routes model calls.
• Model providers handle transcription, vision, and reasoning. Calls are routed through Cloudflare AI Gateway or, for audio, sent directly to the transcription provider. Lirovo is model-agnostic and does not lock you to a single vendor.
• Stripe processes payments. Lirovo never sees or stores your full card details.
• Sentry receives error and performance telemetry, tagged with a request identifier so we can resolve issues quickly.

We require each provider to protect your data and to use it only to provide their service to us.

06Data retention and deletion

We keep your account information for as long as your account is open. We keep job artifacts until you delete them or close your account. When you delete a resource, we apply a soft delete that immediately removes it from your view and severs it from active processing, then purge the underlying data on a rolling schedule.

We take periodic encrypted backups for disaster recovery. Deleted data may persist in a backup for a limited window before it ages out. We may also retain limited records where the law requires it, for example for tax and accounting.

07Security

Protecting your data is foundational to how Lirovo is built. Data is encrypted in transit and at rest, every tenant is isolated in code, API keys are hashed, outbound fetches are screened, and webhooks are signed. For the full picture, see our security page.

No system is perfectly secure. If you discover a vulnerability, please report it to security@lirovo.ai.

08Your rights and choices

Depending on where you live, you may have the right to access, correct, export, or delete your personal data, and to object to or restrict certain processing. You can exercise most of these directly through the API, or by contacting us.

To make a request, email privacy@lirovo.ai. We will respond within the time frame the applicable law requires. We will not discriminate against you for exercising any of these rights.

09International data transfers

Lirovo runs on a global network, so your data may be processed in countries other than your own, including Canada and the United States. Where data crosses a border, we rely on the safeguards our infrastructure providers put in place, such as standard contractual clauses, to protect it to the standard described in this policy.

10Cookies and tracking

The Lirovo API does not use cookies. On our website we use only the cookies needed to remember your theme preference and to keep the site secure and running. We do not run third-party advertising trackers.

11Children's privacy

Lirovo is a developer tool, not intended for anyone under 16. We do not knowingly collect personal data from children. If you believe a child has provided us data, contact us and we will delete it.

12Changes to this policy

We may update this policy as the product and the law evolve. When we make a material change, we will update the date at the top and, where appropriate, notify you by email or in the product. Continued use after a change means you accept the updated policy.

13Contact us

Questions about this policy or your data can go to privacy@lirovo.ai. Lirovo is based in Montreal, Canada.