Structure

meetings/
├── bin/
│   ├── meeting-start        # starts recording + live transcription
│   ├── meeting-stop         # stops recording, asks for meeting name, renames files
│   ├── meeting-follow       # follow transcript while it is being written
│   └── summarize-meeting    # create post-meeting summaries
│
├── lib/
│   ├── paths.sh             # creates session dirs + defines file paths
│   └── whisper.sh           # whisper.cpp binary, model, ASR parameters
│
└── recordings/
    └── 2025-03-24_1930/     # session directory (created on meeting-start)
        ├── audio.wav        # raw system audio recording
        ├── transcript.txt  # live transcript (grows during meeting)
        ├── meta.env        # session metadata (PIDs, language, timestamps)
        ├── 2025-03-24T1930_project-sync_transcript.txt
        ├── 2025-03-24T1930_project-sync_audio.wav
        └── summary.md      # created by summarize-meeting

Description of Paths and Scripts

Paths

Paths

Path: meetings/bin/

• Executable scripts. 

Path: meetings/lib/

• Scripts to be used by the executable scripts. 

Path: meetings/recordings/

• Subdirectories (ISO timestamp format) containing:
  • Audio files (to be deleted after the transcript has been written)
  • transcript.txt (renamed and timestamped after the meeting's end by the meeting-stop script)
  • meta.env (Meeting information)
    • PIDs
    • language used
    • the meeting's timestamps
  • summary.md (meeting summary in Markdown format)

Scripts (current architecture)

TranscriptOMatic is implemented as a small set of composable shell scripts. Each script has a clearly defined responsibility within the session lifecycle. No script relies on implicit system state or hard-coded audio devices.

ScriptsLibrary scripts (meetings/lib/)

Script: meetings/lib/paths.sh

Creates:Responsible
for session creation and path management.

On invocation, it:

• Sessioncreates Directorya new session directory

~/meetings/recordings/<ISO_TIMESTAMP>/

Session Files

defines canonical file locations:

• audio.wav

• transcript.txt

• meta.env

Timestamps (ISO)

provides these paths to all other scripts

andThis script is the only place where session directories are created.

Provides path information for all scripts

Script: meetings/lib/whisper.sh

Contains:Defines the speech recognition backend configuration.

It contains:

• the path to the local whisper.cpp installation

the language model used (currently ggml-base.bin) ASR parameter

model usedselection (language-specific vs. multilingual)

streaming parameters

threading configuration suitable for a Raspberry Pi–class system

The setup is explicitly optimized for Scriptlive transcription: using whisper-stream, not for batch processing.

No audio devices are referenced here.

Executable scripts (meetings/bin/)

meeting-start

Creates

Starts a new directorylive intranscription meetings/recordings/

session.

Responsibilities

1. startsSession
2. ffmpeg (feeds system audio into audio.wav)

whisper.cpp initialization

• creates livea transcriptnew fromsession audio

directory feedsvia transcript into meetings/recordings/$DATE/transcript.txt
paths.sh writes informationthe intoactive session path to ~/meetings/recordings/$DATE/meta.env finetunes whisper.cpp by language switch --de, --en, --auto

Script: meetings/bin/meeting-stop

Stops the recording asks for a meeting name

replaces spaces with hyphens renames the meeting-related files

audio.wav transcript.txt.current according to

Audio graph setup (PipeWire)

ensures a persistent null sink (discord_sink)

routes Discord audio into that sink

exposes the timestampsink containedmonitor inas meta.enva virtual microphone (whisper_mic)

Script: meetings/bin/meeting-follow

 

Shows the transcript while it is written

mainly to monitor the process, but can be used as a live transcript, too. Needs to run in a different terminal from meeting-start

Script: meetings/bin/summarize-meeting

 

Creates a

 summary file based on the meeting transcript.