Who said what is the hard part of a meeting transcript, and the usual answer
is to hand one mixed recording to a model and ask it to tell the voices apart.
That guess is wrong often enough to be worse than useless in minutes, where a
decision attributed to the wrong person is a decision nobody made.
So the question never reaches a model. ffmpeg records the microphone and the
default sink's monitor as one stereo stream, you on the left and everyone else
on the right, and one process reading both is what keeps them aligned over an
hour. Each channel is transcribed on its own and the two are interleaved on a
single timeline, so attribution is settled by the wire a voice arrived on.
What a microphone picks up from the speakers lands on both channels; our copy
is dropped when it overlaps theirs in time and says nearly the same thing.
The stream is written to disk as it arrives rather than held in memory, so
length costs nothing and a crash costs the tail instead of the whole meeting.
Every stage the run reaches is recorded in meetings.jsonl, so a failure while
summarising does not throw away the transcription of an hour of audio: the
retry reads the transcript back out of the document and picks up from there.
A run that dies keeps its recording whether or not audio is being kept.
The minutes model is configured on its own, under Settings, with its own
prompt, and it is told who was expected in the room so the names come out
spelled right. It is told outright that the transcript is a record of other
people talking, not instructions addressed to it.
The built-in listener now holds several bindings rather than one, and the KDE
side is parameterised by desktop id, so the meeting toggle gets a shortcut of
its own on the same footing as the dictation one.
The listener reads /dev/input and reacts the instant a key goes down. The
KDE shortcut answers the same press by launching a whole Python process,
which then talks over IPC, so its toggle lands a few hundred milliseconds
later. The 400 ms guard caught that echo only when the machine happened to
be quick, and otherwise the recording was started and stopped by one press:
"No speech detected".
Route the two apart. A toggle arriving from outside the process right
behind a listener trigger is that echo, and its lateness also proves the
KDE shortcut is live, which leaves the listener with nothing to do but
double every press. So retire it, remember that in the config, and say so
in the tray rather than changing behaviour silently.
whisper-1's verbose response carries a start and an end for every segment,
and the file tab was reading only the start, to build the [mm:ss] prefix.
Keeping the end as well is all an SRT needs.
The text stays the authority on wording and the segments on timing; they
meet at that prefix, which the cleanup model is already told to leave alone.
So a transcript that went through cleanup still turns into properly timed
subtitles. A line whose stamp matches no segment runs until the next line
starts, a line with no stamp at all joins the cue above it, and an end that
would run into the next cue is trimmed back.
The button is dead until a timestamped run finishes, because without
timestamps there are no segments to time anything with.
OpenRouter mirrors OpenAI's /audio/transcriptions field for field, so one
multipart request serves both providers and only the key, the base URL and
the model id change. That puts a dozen speech models behind the key that was
already there for the cleanup, and makes a single OpenRouter key enough for
the whole chain.
Its transcription endpoint takes no hint field, so the words from Cleanup
rules are not sent there; they still reach the cleanup model as a glossary.
Timestamps switch to openai/whisper-1, the namespaced id of the only model
that returns segment times.
The API tab is now grouped by role rather than by service, because a key no
longer belongs to a single job: both keys sit at the top, the two jobs below.
Each provider keeps its own model, so switching back and forth does not
overwrite the other one's.
The History tab was read-only, so the only way to get rid of a dictation
was to edit history.jsonl by hand. Entries can now be removed: right-click
or Delete drops the selection, "Clear history" empties the file, and the
Ctrl/Shift selection lets several go at once. Deleting more than one asks
first, since there is no undo.
The cap on the file has existed since the first commit but was never
reachable from the interface. It is now a spinbox in the same tab, applied
the moment you save rather than on the next dictation, and 0 turns it off.
Trimming rewrites the file only when it is actually over the cap, instead
of on every single dictation, and does it through a temporary file so a
crash cannot leave a half-written history behind.
Deletion matches an entry on its whole content, not on its line number: the
worker may well have appended a new dictation while the window sat open.
Save no longer closes the window. It confirms and stays put, so you can
settle several things in one sitting; the cross closes it. Cancel is gone
with it, because it would be a lie next to a Save that already wrote.
The cleanup prompt now asks the model to fix words the transcriber misheard
when the context makes the intended one clear, and to leave them alone when
it does not. Speech models fail phonetically on proper nouns, and that is
exactly what context can recover.
The names you enter for the transcription hint are handed to the cleanup
model as a glossary too. Knowing the spelling is what lets it recognise
"kuber netis" as Kubernetes.
A failed cleanup used to be almost invisible: the raw transcript was pasted
and a progress line flashed by, so a rejected key looked exactly like
working dictation for days. It now leaves the indicator amber with the
reason, sends a notification, and records the error in the history. HTTP
401, 402 and 429 are reported as what they are, naming the service.
Also:
- Settings can test the OpenRouter key, not just the OpenAI one
- Tray menu and CLI gained Restart, which re-execs in place
- Defaults saved into the config by older versions are recognised by their
fingerprint and dropped, so an untouched prompt keeps getting improvements
- The IPC socket is user-only; Qt puts it in /tmp
The screenshots were downscaled to 430 px wide, which made the UI text
blurry. Restore them at native 1292 px as lossless WebP, which is also
half the size of the original PNGs (72 KB against 155 KB for the largest).
Rewrite every em dash in prose, comments, docstrings and interface strings
as ordinary punctuation.
Ctrl+Space starts and stops a recording. The audio goes to OpenAI for
transcription, a model on OpenRouter strips the fillers and restores
punctuation, and the result is copied and pasted into the focused window.
Only the Python standard library and PyQt6 — HTTP, multipart uploads and
WAV writing are all hand-rolled.
- pw-record captures raw 16 kHz mono PCM with a live level meter
- the corner indicator is drawn through XWayland, since a Wayland client
cannot position its own window
- silence is caught before it costs an API call, relative to each
recording's own noise floor, plus a filter for the stock phrases models
invent when handed silence
- audio and video files can be transcribed too, optionally with [mm:ss]
timestamps, chunked through ffmpeg for long inputs
- global shortcut installs as a KDE custom shortcut, with an evdev
listener as a fallback until the session is restarted
- Turkish and English interface, following the system locale by default
yusufipk