A recording is never deleted for being disappointing. A microphone that
handed over nothing still leaves the right channel, which is everyone
else, and an hour of them is worth more than the empty channel costs; the
one thing the user cannot get back is the half that was there. So the
exact-zero check stays and stops throwing the file away: it says what the
microphone did, in a tray warning next to the recording being written up,
and the minutes are produced from what there is.
Reading the two capture pipes in turn from one thread put the failure it
was meant to fix back in a worse place. A microphone that stops delivering
leaves that read waiting forever, and the far side is not read either
until its pipe fills and its ffmpeg stops writing into it: the meeting
freezes, the levels sit still, and nothing is said for as long as nobody
looks. Each stream now has a reader of its own and a queue, so neither can
hold the other up, and a side that has said nothing for STALL_SECONDS ends
the recording the way a dead ffmpeg already did, out loud and keeping what
was captured.
Which system needs how many processes belongs in the table with everything
else that differs, so meeting() returns the list of commands it takes:
one on PulseAudio, one per device on a Mac. meeting_commands() is the
chooser again rather than a function with a Mac inside it, and the empty
entry in COREAUDIO is gone. The two AVFoundation targets are resolved
against a single device listing, which costs one ffmpeg run instead of two
and cannot see the indexes renumber between the microphone and the far
side.
The macOS backends were already here: CoreAudio capture through ffmpeg,
pbcopy and CoreGraphics, Carbon hotkeys, the paths under ~/Library. What
was missing was everything that installs them, so install.sh hands over to
install-mac.sh on Darwin rather than growing a branch per line: the XDG
directories, the .desktop files and the shortcut registry mean nothing
there, and an application is a bundle rather than a path. The bundle
carries a copy of the interpreter, because macOS files the microphone and
Accessibility permissions against the process that asks, and a launcher
running Homebrew's python3 would have asked as python3 and shared the
grant with everything else on that interpreter. It is signed ad-hoc so a
reinstall is the same application rather than two more dialogs, and it
says so plainly when a brew upgrade has moved the tree it needs.
uninstall.sh and update.sh follow it.
The tray icon was invisible: QIcon.fromTheme wants a freedesktop icon
theme and hands back a null icon without one, which in a menu bar is the
whole interface gone. trayicon.py draws the three shapes as template
images, so they follow the menu bar into dark mode, and the bundle's icon
comes off the same glyph rather than a binary in the repository. Linux
keeps its own icons; these are used only where the theme has nothing.
paths.py is the fix that was never about a Mac. config.py imports ggml.py,
so ggml.py could not ask it where the data goes; each worked it out for
itself and only one of them knew about macOS. Settings went to ~/Library
while several gigabytes of models went to ~/.local/share, which is not a
place a Mac user looks and not a place uninstall.sh --purge would have
deleted from.
Ctrl+Space is the input-source switch there and Cmd+Space is Spotlight, so
the default is Ctrl+Option+Space, and hotkey.default_combo is the one
place that difference lives. The first paste asks for Accessibility with
kAXTrustedCheckOptionPrompt, which is what creates the row to switch on;
asking the other way opens a pane Dikte is not listed in. `dikte shortcut
status` asks the running instance, since the combination is held by that
process and by nothing else.
Local speech to text is the one piece a Mac builds by hand. whisper.cpp
publishes no macOS binary and Homebrew's is configured with
WHISPER_BUILD_SERVER=OFF, so it installs whisper-cli and not the server
Dikte talks to; program_path already takes a whisper-server off the PATH
or out of Settings, so the answer is the one a Linux distribution gets,
and the README carries the cmake line. CI grows a macOS job on 3.11 and
3.13, the only place the Carbon and CoreGraphics libraries have to be
there to be opened.
Written and tested on macOS 27.0 arm64. Two things are still unverified on
a Mac: the paste end to end, which waits on the Accessibility toggle, and
a meeting recording, which needs a loopback driver.
Four files disagreed, and all four the same way: master had turned things the
Mac branch wrote out by hand into one list to read from.
Shortcuts are the whole of it. master gave every binding a row in
hotkey.SHORTCUTS, so the Mac's DESKTOP_IDS is gone and CarbonHotkey reads the
desktop id off that row, which also gives the new cancel key a status line on a
Mac. Settings builds its four rows through master's _shortcut_row, and that one
now asks _install_buttons for Install and Remove, so macOS gets a combination
box and nothing to press, and everywhere else the button says the desktop's own
name. dikte.py starts the listener from the same table, on macOS whatever the
setting says: there is nothing installed for it to be a fallback to.
The rest is two imports and a paste list that lives in paste.Desktop now.
Cleanup was the one step with only one place to run. Speech to text has three
providers behind a setting and the agent has three behind another, but the
model that drops the "eee"s out of a sentence was always a request to
OpenRouter, which meant a second key on a machine that already pays for a model
and already hands whole dictations to it as commands. Claude Code and Codex can
rewrite a sentence as easily as they can put something in your calendar, and
now they may.
cleanup.py is where that choice lives, so worker, the file transcriber and the
meeting all ask the same question rather than each building the same OpenRouter
request. What comes out of a CLI that failed is a CleanupError, which is an
ApiError, because to the chain a cleanup that failed is a cleanup that failed
however it was run: the raw transcript is still pasted and the reason still
shows in the corner, unchanged.
Neither CLI is given anything it does not need for the job. No tools, no MCP
servers, no session to resume, and the home directory rather than wherever the
agent is pointed, since a project's instructions have opinions about how text
should be written and none of them are about this transcript. The transcript
goes in fenced the same way the OpenRouter call fences it, because it is
material rather than an instruction however much of it reads like one. Claude
takes the cleanup rules as its whole system prompt; Codex has no system prompt
of its own, so they ride in front of the text, and its answer is read from the
file it writes on the way out rather than from a stdout that also carries a
header, its thinking and a token count.
The cost is seconds. OpenRouter answers in about one, a CLI in six or seven,
because each one opens a whole session to do it. That is the trade the box
says out loud, and the default has not moved: OpenRouter cleans up until you
say otherwise.
Codex's two lowest thinking levels now ask for "low". "minimal" was its bottom
rung until the newer models replaced it with "none", and each of them answers
the other's word with a 400, which the agent has been quietly hitting too.
In the settings window the model box belongs to whoever is chosen rather than
meaning three different things in turn, since an OpenRouter id and a Claude
alias do not belong in the same field, and under it is the same "found it or
not" line the agent tab has. dikte doctor asks about the program instead of the
key when a CLI does the cleaning, and the history records which model actually
did it.
Stopping a recording is the step there is no taking back. It is what sends the
audio off, and a moment later the sentence you did not mean to dictate is in
the clipboard and pasted into whatever window you were typing in. The tray menu
was the only way out, and by the time it is open the recording has already
gone. Discarding needed to be as quick as starting, which means a key.
Ctrl+Alt+Space rather than Escape: the combination the recording started with,
one modifier along, so the two are one gesture with a modifier between them.
Escape is the obvious choice and the wrong one, because it belongs to whichever
window has focus, and while you are talking something else usually has it. It
works on a dictation and on a command for the agent alike, since the one you
want to take back is the one that is running.
That made four global shortcuts, and four is the number at which three copies
of the same forty lines stop being a coincidence. The command line already had
a table of them; hotkey.py now holds it, and the settings window reads it too,
so a shortcut is a row rather than a combination box, two buttons, a status
label and three methods written out again. The window no longer takes the
commands to run as arguments either, because ipc.command_for already knows them
from the verb. Adding the fourth key is what this buys: one line in the table
and one call per row.
Both places a key can live are told about it. The listener catching the press
and the KDE shortcut arriving behind it go through the same echo guard the
toggle already had, so the two are one discard rather than two, and the tray
calls the inner method as it already did for the toggle. Ctrl+Space and
Ctrl+Alt+Space land on the same evdev key code, so there is a test for the
modifier matching that keeps them apart.
install.sh takes the second key as a second argument and refuses to register
two of the same. It hands both to `dikte shortcut install` rather than writing
kglobalshortcutsrc itself, which is what makes it work on GNOME, and what
finally puts the chosen key in the settings as well: the built-in listener
reads it from there, so a key written to only one of the two places was a key
that half worked.
Left empty in the settings window the discard key stays empty, unlike the
dictation shortcut which falls back to Ctrl+Space: a recording can always be
thrown away from the tray menu, so there is nothing to guarantee here.
Dikte already chose its clipboard programs once instead of in every
function; macOS joins that table rather than adding a branch to each one.
A Mac copies through pbcopy and presses Cmd+V straight into CoreGraphics,
records through AVFoundation, and asks Carbon for its global shortcuts.
The three tables are paste.Desktop, audio.Sound, and the pair of
predicates in hotkey.py. Each reads sys.platform inside the chooser, so a
test can stand somewhere else: 697 of the 737 tests now run on any
machine, the Wayland and X11 halves included, and the suite passes whole
whichever system it is run on.
Two things a Mac does not have needed saying rather than pretending:
there is no shortcut registry to install into, so Settings offers no
Install button and the listener is the mechanism instead of a fallback;
and nothing is offered as the sound the speakers are playing, so a
meeting needs BlackHole or Loopback and says so. The KDE-only labels
around them were already wrong on GNOME, and now name whichever desktop
is there.
Co-authored-by: firat <[email protected]>
Which pair of tools a session uses was being asked inside copy(), read(),
copy_bytes() and press(), four times, in a conditional each. A third desktop
means a third branch in each of them, and macOS is already open as a pull
request doing exactly that in a different style.
Wayland and X11 are two entries at the top of the file now, each naming its
programs and how to build a key press from them. The functions below take
whichever entry the session gets. Adding a desktop is an entry and a line in
desktop(), and it touches nothing else.
Two things fall out of it. The key press is checked against the same table on
both: xdotool was being handed the shortcut as typed, so ctrl+f13 was refused
on Wayland and passed through on X11. And a missing tool names the package to
install again, which the shared message had dropped.
The tests say the promises once and run them against both desktops, so a third
one inherits the list rather than needing a copy of it.
A transcript the hallucination filter throws away is named in the message
that says so, and the placeholder it goes into is called {text}. So is the
first parameter of t(), which made the call two values for one argument and
a TypeError: the user was told "Unexpected error" rather than what happened.
Both strings are positional-only now, so no placeholder can ever collide with
them again.
Cleaning up a dictation and cleaning up a file are not the same job, and until
now they shared one prompt. A dictation is read afterwards, so dropping a
filler and tightening a sentence is a favour. A file becomes an SRT, and there
the same favour is damage: the viewer hears the words while the line is on
screen, so a word that was said and is not written is noticed, and a phrase
pulled onto the line above is on screen before it is spoken.
So the file path gets its own system prompt. It says what the text is and what
it is for, and it spends its room on the one repair only context can make: the
word the transcriber misheard. Speech models fail phonetically on names, and
somebody talking about Anthropic said "Claude", not "cloud". The lines stay
where they are, nothing is shortened, nothing is turned into an abbreviation,
and the filler words stay because they were said out loud.
The glossary and the timestamp rule are appended as before, so a name listed
under Cleanup rules still reaches this prompt, and a timestamped run still gets
told to leave the stamps alone. The dictation prompt is untouched, and so are
the meeting and agent paths.
Cleanup rules now has a tab each. An untouched prompt is still stored empty, so
switching the interface language keeps switching the prompt language with it.
Two things a real command turned up.
A job can run for ten minutes. "Report on the front page" is not a question
with an answer a second later, and having the corner narrate every tool it
touches for those ten minutes is worse than saying nothing. So that indicator
can be clicked away. It is the only one that can: a dictation is over in
seconds, and an indicator that swallows a click meant for the window underneath
has to earn it. The work carries on; what is muted is the progress, not the
outcome, which shows up whether or not the box was sent away. A faint cross on
the right says the box can be clicked, because a feature nobody can see is not
one. The next run starts visible again.
Muting leaves the state alone rather than setting it to something hidden, so no
later repaint puts the box back on the screen behind its own back.
Thinking effort is a setting now, offered once rather than three times: how hard
to think is one thing to want, and only the rungs differ. Claude takes it as
--effort, Codex as a model_reasoning_effort override, OpenRouter in the
reasoning field it already understood for cleanup. A level a provider does not
have lands on the nearest one it does, so "maximum" is xhigh on Claude and high
on Codex rather than an error or a silent drop. Left alone, nothing is sent and
each model does what it would have done.
Four things the first use of it turned up.
The tab was called Claude while the setting inside it chooses between three
providers, two of which are not Claude. It is Agent now, and the messages that
pointed at it by name point at the new one.
The three global shortcuts were the only fields in the window you had to know
the syntax of to fill in, next to a paste key that has been a dropdown all
along. They are editable combo boxes now, sharing one shortlist of combinations
that are usually free. Typing your own still works; it is just no longer the
only way.
The instruction was read as discouraging the tools, which is the opposite of the
point. "Keep it short" is about the answer, and a model that reads it as "answer
off the top of your head" hands back a caveat about its training data instead of
the thing it was asked. Asked who won the 2026 World Cup it answered, twice, that
the tournament had not been played, on the 28th of July. So shortness is now
stated as being about the answer rather than the work, and writing a caveat is
named as the moment to go and look instead. Same question, same model, only the
prompt changed: no tool calls and a wrong answer before, a web search and the
right one after. It also appended its sources, which a reply being pasted into
someone's text field has no use for, so that is ruled out alongside the headings
and the bullet lists.
Clicking the tray icon during a Claude recording did nothing, because the icon
was wired to the dictation toggle and that one leaves the other mode's recording
alone on purpose. The shortcuts should stay tied to their own mode; the icon is
one button and now ends whichever recording is running.
Everything the last commit built assumed one agent was installed, which is a
poor assumption to bake into a dictation tool. So the provider is a setting, and
what it selects is one of three quite different things.
Claude Code and Codex are the same shape: a CLI, streaming JSONL, a session id
to resume, tools that reach the machine and whatever is connected to it. They
share the runner. What differs is spelled out where it differs, which is more
than the flag names: Codex has no system prompt to append, so the instruction
rides in front of the command with a rule between them; it confines its commands
in a sandbox rather than asking about them, so the permission setting is a
sandbox mode; and `-s` is not accepted by `exec resume`, so both settings go
through `-c` overrides, which are.
OpenRouter is the odd one and is meant to be. No tools, no files, no calendar:
it can say what the capital of Peru is and not what is in your diary, and the
settings box says so rather than letting it be discovered. It also has no
session to resume, so the conversation is kept here and resent, capped at 24
messages.
A stored conversation names the provider that made it, and is ignored by any
other: none of them can pick up another's thread, and a stale id would otherwise
fail every command until the timeout cleared it.
The interface calls the thing by its name, which in Turkish means the suffix has
to agree with it: Claude'a but Codex'e, Claude'u but Codex'i. A name dropped
into a sentence through t() cannot be inflected by that sentence, so it arrives
inflected, from a small table in i18n. English takes the name as it is and keeps
the preposition in the sentence.
Dictation ends the same way every time: the words you said land in the window
you were in. But half of what you say to a machine is not text to place, it is
something to do, and the answer to "what is on my calendar today" is not that
sentence written out.
`claude -p` is that session run without a window: the same skills, the same
connected services, the same account. So a second shortcut records exactly as
the first one does and sends the transcript there instead, and what comes back
is pasted where the transcript would have been. Which is what puts "save that
to my calendar on Thursday at three" inside a text field that has nothing to do
with Claude.
Permissions are the part worth being deliberate about, because nothing here can
answer a prompt: a mode that would have asked denies instead. It runs in `auto`,
which decides for itself with the prompt-injection checks left on, and the other
two modes are one setting away. What Claude was not allowed to touch is reported
rather than swallowed, since a reply that reads perfectly normal is otherwise
the only sign that the job did not happen.
Commands close together stay in one conversation, so "and move that to Thursday"
knows what "that" is; half an hour of silence ends it, as does the tray. The
answer is written to be read where it lands: no headings, no lists, and a
sentence naming what was done when something was done.
Its output is read as it streams rather than waited out, so the corner names the
tool it is on. A calendar lookup took 29 s in testing, which a still indicator
would have made indistinguishable from a hang. The clock and the stop button are
watched from a thread of their own, because the stream blocks between lines and
a model that thinks for a minute sends none: they end the run by killing the
process, which closes the stream and unwinds everything else on its own.
Transcript cleanup is off on this path. Claude reads through "erm" and "hani"
without help, and skipping it saves an API call and a second or two in front of
a screen you are standing at.
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
Yusuf İpek
yusufipek