Privacy Policy

Introduction

VoiceTrail ("we", "our", or "us") operates a desktop-native AI meeting assistant application and related services. This Privacy Policy explains what information we collect, how we use it, and the choices you have.

VoiceTrail is built on a local-first, privacy-focused model: audio is captured and processed on your device wherever possible. We only send data to external services when required to deliver specific features you explicitly use.

Information We Collect

Account information. When you create an account we collect your email address. We use magic-link authentication — no passwords are stored.

Meeting data. This includes raw audio recorded locally on your device, transcripts synced to our servers, AI-generated summaries and action items, and speaker voice samples used to identify speakers across meetings.

Device & usage information. Device name, platform, app version, basic usage events, and error logs to help us diagnose issues and improve the product.

Calendar data (optional). If you connect Google Calendar, we access event metadata to pre-populate meeting context. We do not store your full calendar.

How We Use Your Information

We use your information to provide and improve the service, generate transcriptions and AI-powered insights, identify speakers, sync your data across devices, and send billing and support communications. We do not sell your personal data to third parties. We do not use your meeting content to train AI models.

Third-Party Services

AssemblyAI — When you request cloud transcription, your audio is sent securely to AssemblyAI for speech-to-text processing. Audio is not retained beyond the processing window. See their Privacy Policy.

OpenRouter — Transcript text is sent to OpenRouter's API to generate meeting summaries, action items, and AI assistant responses. Your data is not used to train AI models. See their Privacy Policy.

Google Calendar (optional) — If you connect Google Calendar, we use Google's OAuth 2.0 flow and read only the calendar event metadata required for meeting context.

Data Storage & Retention

VoiceTrail uses a hybrid audio model. By default, transcription happens on-device and raw audio never leaves your machine. When cloud processing is used, audio is encrypted in transit and deleted immediately after transcription completes.

Transcripts, summaries, and notes are retained for the lifetime of your account or your workspace's configured retention policy. Speaker voice samples are retained until you delete them or close your account. Account data is deleted within 30 days of account closure upon request.

Security

All data in transit is encrypted using TLS 1.2+. Authentication tokens are hashed before storage and plain tokens are never persisted. Access tokens expire after 1 hour; refresh tokens after 30 days. If you discover a vulnerability, please disclose it responsibly to [email protected].

Your Rights

Depending on your jurisdiction you may have the right to access, correct, delete, or export your personal data, or to object to certain processing. To exercise these rights, contact us at [email protected]. We will respond within 30 days.

Cookies & Analytics

We use session cookies required for authentication and CSRF protection, and collect basic anonymised usage data to understand how the product is used. We do not use advertising cookies or cross-site tracking.

Children's Privacy

VoiceTrail is not directed at children under 13 (or 16 in the EU). If you believe a child has provided us with personal data, contact us and we will delete it promptly.

Changes to This Policy

We may update this policy from time to time. For material changes we will notify you by email or in-app notification. Continued use of VoiceTrail after changes constitutes acceptance of the updated policy.

Contact Us

Questions about this Privacy Policy? Email us at [email protected].