Trust & transparency
Where your data goes
Minuta captures audio on your computer and uses cloud AI for transcription, summaries, diarization, translation, and copilot answers. Internet access is required for these features.
What stays on your machine
These records are stored in the desktop app. Audio or text excerpts are still sent to cloud providers when you use the related AI features:
- Audio capture — Minuta records system audio locally on the desktop app.
- Transcript database — every transcript is stored in a local SQLite database on your computer.
- Meeting summaries — generated summaries are saved locally, not server-side.
- Copilot answers — suggested answers during the meeting are stored in the local database.
- Exports — any file you export (text, PDF, etc.) stays on your machine until you choose to send it.
- Attached context documents — the source files stay local; relevant text excerpts can be sent to the cloud copilot for grounding.
What we send to the cloud, and why
To deliver transcription, summaries, speaker identification, copilot answers, and optional translation, Minuta sends audio or text excerpts to cloud providers. Diarization can use a temporary private audio staging object. Provider handling follows the applicable service terms and configuration.
Transcription
Deepgram (primary ASR)
OpenAI Whisper (fallback)
Groq Whisper (last resort)
Summaries & copilot
OpenAI gpt-4.1-mini (primary)
Anthropic Claude Haiku 4.5 (fallback)
Groq (last resort)
Speaker diarization
Modal / pyannote — staged audio uploaded to a private short-lived S3 object
Translation (optional)
DeepL — transcript text only, never audio
Subprocessors
All subprocessors are listed here and in our Privacy Policy. We update this table whenever the provider chain changes.
| Provider | Purpose | Retention note |
|---|---|---|
| Deepgram | Automatic speech recognition (transcription, primary) | Handled under the configured account and current provider terms |
| OpenAI | Transcription fallback (Whisper); summaries and copilot answers (primary) | Handled under the configured account and current provider terms |
| Anthropic | Summaries and copilot answers (fallback) | Handled under the configured account and current provider terms |
| Groq | Transcription and LLM inference (last-resort fallback) | Handled under the configured account and current provider terms |
| Modal / pyannote | Speaker diarization — identifies who spoke when | Uses temporary audio staging for diarization; cleanup and storage lifecycle apply |
| AWS (S3, Lambda, API Gateway, Cognito, DynamoDB, CloudFront) | API hosting, auth, account metadata, short-lived audio staging, CDN | Stores account and service metadata; temporary audio staging follows its configured lifecycle |
| DeepL | Real-time translation (optional, when enabled) | Transcript text is handled under the configured account and current provider terms |
| Stripe | Payment processing and subscription management | Stripe holds card data; we store only the Stripe customer ID and subscription state |
| Google reCAPTCHA v3 | Anti-bot on site forms | Handled according to the configured site integration and provider terms |
| Google Analytics 4 and Google Ads | Consent-controlled site analytics and advertising campaign attribution | Consent-controlled site analytics; retention follows the configured analytics properties |
| Sentry (optional) | Error diagnostics when configured | Diagnostic events follow the configured Sentry project settings |
| Plausible (optional) | Site pageview analytics when configured | Analytics data follows the configured Plausible project settings |
How the product handles meetings
- We do not use a meeting bot — Minuta joins no meeting as a participant; it captures audio locally on your computer.
- Meeting records such as transcripts, summaries, and copilot answers are stored in the local desktop database.
- Cloud AI features require internet access and send the audio or text excerpts needed for the requested operation.
- Speaker diarization can temporarily stage meeting audio in private cloud storage before processing completes.
- Provider retention and model-training controls depend on the configured accounts and their current service terms.
Have a question?
If you have questions about how Minuta handles your data, reach us directly.