Skip to content
coralmesh
all products
productivity · beta

CoralNote

Meeting records for the organisation: a bot attends, diarization attributes every line, and the archive answers questions about itself.

Overview

A meeting-record platform that removes the two failure points of note-taking — remembering to record, and finding anything afterwards. Calendar orchestration runs in the backend rather than on the recorder, dispatching a bot to the meetings marked for capture across the organisation's calendars. Transcription separates speakers so the record is attributable rather than a wall of text. Records land in a shared workspace behind a FastAPI service, stored in PostgreSQL with pgvector, and a multilingual embedding model makes the whole archive searchable by meaning and answerable in conversation. Access is through corporate single sign-on restricted to the organisation's own tenant.

Specifications

Audience
productivity
Platforms
macOS · iOS · Web
Status
beta
Built with
STT + diarization

Capabilities

Calendar orchestration in the backend

Dispatch was moved out of the recorder and into the service, so one central component decides which meetings are captured across the organisation. Capture no longer depends on any individual remembering to start it.

Speaker-attributed transcription

Diarization separates speakers on GPU, turning a continuous transcript into an attributable record that can be skimmed by who spoke rather than read end to end.

Semantic search across the archive

A multilingual embedding model indexes every record into pgvector, so the archive is searched by meaning rather than keyword — including across meetings held in different languages.

Conversational retrieval over meetings

Questions are answered from the record set itself, so a decision taken three months ago can be recovered without knowing which meeting it was taken in.

Corporate single sign-on

Authentication runs through Microsoft Entra with authorisation code and PKCE, restricted to the organisation's tenant. Signing in is itself the proof of membership; there is no separate user directory to maintain.

Isolated from the capture infrastructure

The platform runs on its own host, separate from the media-capture bot, reaching the recorder and the inference services over the internal network. Fragile capture infrastructure stays isolated from the service people actually use.

Self-contained deployment

Database, API, web client, reverse proxy and embedding service ship as a Docker Compose stack, so the whole platform runs inside the organisation's own network.

Engineered independently. Priced transparently.

No per-seat licensing, no vendor lock-in, no unpredictable invoicing. Our teams are available to scope an evaluation for any product in the portfolio.