Implement meeting assistant v1

This commit is contained in:
2026-05-20 02:06:16 +02:00
parent 90df1edc03
commit 0297bcc0f6
120 changed files with 11883 additions and 180 deletions
@@ -0,0 +1,37 @@
## Why
Meeting Assistant should provide a meeting capture workflow that is not tied to a specific online meeting provider. The first version needs to establish the platform-independent core: meeting notes, metadata capture, transcription with speaker attribution, generated summaries and next steps, and a project knowledge base that agents can use for later retrieval and controlled project work.
## What Changes
- Create Meeting Assistant as a .NET 10 server application in `Manuel/meeting-assistant`.
- Establish OpenSpec as the source of truth for behavior changes.
- Define the version 1 meeting flow around Obsidian markdown notes created before transcription starts.
- Require the core flow to support in-person meetings and not depend on Teams, Zoom, or similar APIs.
- Add a configurable global hotkey that toggles recording/transcription mode.
- Capture microphone input and computer output into one transcription audio stream.
- Require speech recognition pipelines to accept streamable audio, with FunASR configured for speaker-attributed transcription and local Whisper plus pyannote kept as a fallback pipeline.
- Store the live transcript in a text file under the configured vault folder.
- Add requirements for speaker-attributed transcription, summaries, decisions, and next steps.
- Define project context capture and retrieval as first-class capabilities.
- Define agent tools for project lookup and project file changes in existing projects.
## Capabilities
### New Capabilities
- `meeting-session`: creation and lifecycle of meeting notes and metadata.
- `meeting-recording`: hotkey-controlled recording mode, mixed audio capture, and transcript persistence.
- `meeting-transcription`: platform-independent transcription with speaker attribution.
- `meeting-summary`: generated summaries, decisions, and next steps.
- `project-knowledge`: project context, retrieval, and knowledge base updates from meetings.
- `agent-project-tools`: agent tools for lookup, retrieval, and project file updates.
## Impact
- New .NET 10 solution, service project, tests, README, and OpenSpec structure.
- New recording/transcription services using configurable .NET options.
- NAudio is used for Windows microphone and WASAPI loopback capture.
- FunASR is used as the configured speaker-attribution pipeline, and Whisper.NET plus pyannote remains available as a local transcription fallback.
- Version 1 behavior is documented before feature implementation.
- Future platform integrations remain optional augmentations instead of hard dependencies.