Skip to main content
StageWhisper processes real conversations. This page covers what data is collected, where it goes, and what controls you have.

​
What StageWhisper captures

During a listening session, StageWhisper captures:
  • System audio from your call application (the conversation both sides hear)
  • The resulting transcript (generated on your device using local speech recognition)
  • AI-generated signals and insights
  • Tone analysis data (if enabled on your plan)

​
What StageWhisper does not do

  • It does not record or store raw audio files. Audio is transcribed on your device and then discarded.
  • It does not run in the background when you’re not in a session. When you stop a session, capture stops.
  • It does not share data with the person on the other end of your call.
  • It does not send audio to third-party services. Speech recognition runs entirely on your computer. Audio leaves your device only when tone analysis is on, and then it goes to StageWhisper’s EU servers, which process it in memory and never store it.

​
Local processing

Speech recognition, prompt construction, and result processing all run on your device. The desktop app handles:
  • On-device transcription using a local ASR model (no cloud speech APIs)
  • Building analysis prompts from your transcript, playbook, and session context
  • Parsing AI responses into signals, checklists, and tasks
  • Screen capture analysis and document retrieval
The backend provides authentication, session metadata storage, and AI transport. It processes audio only for tone analysis, when that’s on.

​
Where your data lives

StageWhisper infrastructure runs in the EU. Session metadata, account data, and hosted-mode analysis results are stored on European servers.

​
At-rest encryption

Local data stored on your device is encrypted with a per-device key kept in your system’s credential store (Keychain on macOS, Credential Manager on Windows):
  • Screen reading database (SQLCipher)
  • Screenshots and compacted video
  • Reference file storage, text chunks, embeddings, and summaries
  • Outlook and Google Calendar sign-ins
  • The token that connects StageWhisper to your paired assistant
Temp files containing plaintext are cleaned up when a session ends. When a Signals session keeps its transcript on our EU servers, each line is encrypted at rest with XChaCha20-Poly1305. This covers every transcript we store, including those saved before encryption was added. The same encryption covers what we write about a call: the summary and notes, the signals and insights, the summary of what was on your screen, and the in-call chat, including suggested questions. Each piece is tied to the call it belongs to, so it can’t be read back as part of another call. Anything saved since October 21, 2026 is encrypted when it’s written, and we’re encrypting what was saved before that date too. A few details stay readable on our servers: the call title, start and end times, the playbook you picked, which checklist topics you covered, and the tone scores. The StageWhisper service holds the key and keeps it outside the database. The backend decrypts this content only to show it in the app, to search your calls, to write your summary and notes, or to answer a question you ask. Because we hold the key, this protects your calls in storage, but it isn’t end-to-end encryption.

​
BYO mode and end-to-end encryption

When you connect your own AI and switch to BYO (Bring Your Own) reasoning mode, StageWhisper adds end-to-end encryption between your desktop and your AI assistant plugin. The backend is a blind relay: it passes encrypted messages between the two sides but cannot read the content. In BYO mode, the backend can see:
  • Session ID, timestamps, and connection status
  • Task status (pending, approved, completed) and action type
  • Envelope metadata (message IDs, content type labels)
  • Error codes and retry counts
The backend cannot see:
  • Transcripts
  • Analysis prompts and AI responses
  • Signal content and evidence
  • Task descriptions, request text, and replies
  • Reasoning payloads
The encryption uses XChaCha20-Poly1305 with X25519 key agreement. Keys are exchanged during the pairing process and never leave the two endpoints. See BYO AI setup for setup details.

​
Screen-share privacy

The desktop overlay has a privacy toggle. When you switch to “Private” mode (it’s the default mode), the StageWhisper overlay is hidden from screen recording and screen sharing applications. This means:
  • If you’re sharing your screen on Zoom, the other participants won’t see your coaching signals.
  • If you’re recording your screen, the overlay won’t appear in the recording.
Toggle between Private and Visible using the button on the control panel.

​
AI assistant data sharing

If you connect an AI assistant, what gets shared depends on your reasoning mode: BYO mode: All content is end-to-end encrypted between your desktop and your AI assistant plugin. The backend relays encrypted envelopes and cannot read them. Hosted mode: Your desktop sends analysis prompts to the backend, which calls the AI model and returns results. The backend does not log prompt content or AI responses. Raw audio never goes to a third-party service in either mode. With tone analysis on, it goes only to StageWhisper’s EU servers, where it’s processed in memory and not stored. See AI agents for details on the architecture.

​
Reference files

You can attach documents to Playbooks. See the Playbooks guide for details. Privacy specifics: Deleting a file from a Playbook removes the original, text chunks, embeddings, index entries, and summary. All of it, immediately.

​
Connected apps

With Signals, you can connect ClickUp so your insights can use what your team tracks there. See the ClickUp guide for details. Privacy specifics:

​
Data retention

Your session data persists in your account until you delete it. You can delete individual sessions from the web dashboard. If you delete your account, all associated data is removed.

​
GDPR

StageWhisper is designed for GDPR compliance. You can:
  • Access all your stored data through the web dashboard
  • Delete individual sessions or your entire account
  • Export session transcripts
The tone analysis pipeline measures conversational dynamics at the interaction level, not individual emotions. This means it does not generate personal emotional profiles of the other person on your call.
If you’re using StageWhisper in a context where recording consent is required by your local laws, you are responsible for obtaining that consent. StageWhisper does not notify call participants that it is running.