Conclave Docs

Conclave

A private transcription service the operator can't read, that never names a voice without consent — and strips regulated data before it's stored. The reference for humans and agents.

Conclave is private transcription that can't read your meetings. It never names a voice without permission, and its redaction is verifiable. Every meeting notetaker keeps a fingerprint of your voice, and nobody asked you. Conclave refuses that: transcription runs inside a confidential enclave the operator can't read, naming is consent-gated, and regulated data is stripped before it is ever stored in the clear.

The system is three cooperating products behind one boundary:

  • Conclave — the intelligence + control plane. The TEE where content lives (transcripts, summaries, insights, knowledge base, audio).
  • Capture — meeting capture + acoustic diarization. Joins online meetings or streams a room mic. Identity-free by design.
  • VFTEE — the voice-identity + consent layer. Turns audio into voiceprints, recognizes speakers scoped and consented.

The load-bearing idea. A trust boundary is an architecture. Logins decide who gets in; only encryption and a measured enclave decide what the vendor can read. Conclave's reads are operator-blind by design, every service runs in a TDX enclave, and every record carries an Ed25519 receipt you can verify offline. The trust model lays out exactly what the architecture proves.

Start here

The tiers

Agent-friendly by construction

Every page is plain MDX you can read straight from the repo. The site also serves /llms.txt (an index of every page) and /llms-full.txt (the entire corpus as one plain-text document), and each page has a Copy as Markdown button. Point your agent at any of these.

One rule for this repo: we document only what is implemented. Planned work lives on the Roadmap, derived from the live issue tracker and clearly labelled as not-yet-built. See Status for what actually ships.

On this page