Dictation
Talk into any app
Press the hotkey, say it, and the text appears where your cursor already was — Mail, Slack, Cursor, a browser form. No per-app integration, no window to switch to.
Speech in, text out. Nothing leaves your Mac.
Dictate into any app, drop in a recording or a YouTube link, get notes from your calls, and hand your AI agents a transcription server that runs locally. One purchase — no cloud, no subscription, no account.
macOS 14 or later · Apple silicon · $29 once, not per month · 7-day trial
MailFileEditView
Kekoso100%9:41
New Message
- To:
- counsel@firm.example
- Subject:
- Filing timeline
Quick note before the deposition: the client confirmed the timeline, so we can file on Thursday.
Listening⌥ Space
What it does
Four kinds of speech. One app, one machine.
Most people end up paying three or four services to cover this — one for dictation, one for meetings, one for files, an API key for everything else. All of it runs on hardware you already own.
Files and links
Anything with a voice in it
Drop in an audio or video file, or paste a YouTube link. You get a clean transcript with timestamps, exportable as TXT, SRT or VTT. Hours of recording, processed on your own machine.
Meetings
Calls, without a bot in the room
Record the call and get decisions and action items with timestamps — not a summary nobody reads. Your microphone and the system audio stay on separate tracks, so who said what is not guesswork.
Agents
A transcription server for your tools
Kekoso exposes a local MCP server. Claude Code, and any other MCP client, can transcribe through it — no API key, no per-minute billing, no round trip to anyone else.
The distinction
Bot-free is not the same as local.
Nearly every competitor captures audio on your machine and then sends it somewhere else to be transcribed. That is a different promise than the one it sounds like. Here are the two routes your voice can take.
Most "private" dictation apps
- 1
Your microphone
Audio captured on device
- 2
Their servers
Uploaded for recognition
- 3
Their storage
Transcript retained, sometimes for training
Recording locally is not the same as processing locally.
Kekoso
- 1
Your microphone
Audio captured on device
- 2
Your Neural Engine
Model runs on your Mac
- 3
Your text field
Text inserted, audio discarded
No account, no upload, no server to subpoena.
How it works
Three seconds from thought to text.
- 01
Press the hotkey
Hold to talk, or tap to toggle. Works in every app, including the ones that block other tools. Your cursor stays exactly where it was.
- 02
Say it out loud
The model is already warm in memory, so the first word is never clipped. A small panel shows the level so you know it heard you.
- 03
The text is already there
Punctuated, cleaned up, inserted into the field you were in. Wrong window? One hotkey takes it back.
The rest of it
What else Kekoso does.
Dictation is where most people start. These are the parts that make it worth keeping on the machine.
Files and links
A three-hour recording, transcribed while you make coffee
Drag in an MP3, an MOV, a voice memo, a screen recording. Or paste a YouTube link and let it pull the audio down. Everything after that happens on your Mac — no upload, no queue, no per-minute meter running.
- Audio and video, whatever macOS can already open
- YouTube, podcast and lecture links pasted straight in
- Export as TXT, SRT or VTT with timestamps
Kekoso — Transcribe
Agents
Your coding agent gets ears, for free
Kekoso runs an MCP server on localhost. Point Claude Code, or any MCP client, at it and transcription becomes a tool your agent can call — no API key to leak, no per-minute bill, no audio leaving the machine it runs on.
- One line in your MCP config, no separate daemon to babysit
- Same models as the app, so results match what you see
- Works offline, which matters when an agent runs unattended
Claude Code — MCP servers
Meetings
Decisions and owners, not a wall of summary
Record the call from your side. You get the decisions, the action items and who owns them, each with a timestamp back into the recording. Your microphone and the system audio stay on separate tracks, so attribution is a fact, not a guess.
- No bot joins the call and no one has to approve it
- Separate tracks for you and for everyone else
- Search across every meeting you have ever recorded
Kekoso — Meetings
History
Everything you dictated, still on your Mac
Every transcript is kept locally and searchable, with the app and the moment it came from. Copy it again, edit it, or wipe the whole history in one action — no sync, no backup you did not ask for.
- Full-text search across everything you have ever dictated
- Grouped by day, with the app each snippet went into
- Delete a single entry or everything, permanently
Kekoso — History
Vocabulary
Teach it the words only you use
Client names, drug names, internal acronyms, the library nobody spells right. Add them once and they stop coming out mangled — for any language, not just English.
- Plain list of terms, no training step, effective immediately
- Straight replacements too: say "my email", get the address
- Import a list if you already keep one somewhere
Kekoso — Vocabulary
Details
The small things you notice on day two.
None of these sell an app. All of them decide whether you still have it installed a month later.
Works in every app
Mail, Slack, Notion, Cursor, the browser. Text is delivered through Accessibility, so there is no per-app integration to wait for.
Push-to-talk or toggle
Hold the key for a quick sentence, toggle it for a long one. Both modes, one shortcut, no mode confusion.
Undo the insert
Dictated into the wrong window? One hotkey pulls the text back out. The mistake everyone makes on day one, solved.
Your own vocabulary
Client names, drug names, internal acronyms, that one library nobody spells right. Add them once and they stop coming out wrong.
Searchable history
Every transcript stays on your Mac, searchable, copyable, deletable. Kept in a plain local database you can inspect.
Honest microphone handling
Pick the input you actually want, and get warned when macOS has quietly switched you to the wrong one mid-call.
Warm model, no cold start
The model stays loaded so recognition begins the instant you press the key, not a second and a half later.
A hundred languages
Multilingual out of the box. Auto-detection you can switch off, because on short phrases it guesses wrong.
Privacy
Take the unplug test.
Don't trust a privacy page — including this one. Turn off Wi-Fi, pull the ethernet cable, and dictate a paragraph. Kekoso keeps working, at full quality, because the model was never anywhere else. Try the same test on anything else you're considering.
- No account. Nothing to sign up for, nothing to log in to.
- No audio or transcript leaves the machine — not for recognition, not for analytics.
- The recognition pipeline makes no network calls at all. Not even optional ones.
- Files, meetings, dictation and the MCP server all use the same local models.
- History lives in a local database you can open, export, or delete yourself.
The one exception, stated plainly
Pasting a YouTube link means fetching that video from YouTube — that request goes to Google, like any other time you open a video. Nothing of yours is sent: no audio of yours, no transcript, no identifier. Once the file is on your Mac, transcription is as local as everything else.
verify.sh
# Every open network connection Kekoso holds
$ lsof -i -a -p $(pgrep -x Kekoso)
(no output)
# Airplane mode on. Dictate anyway.
$ networksetup -setairportpower en0 off
Wi-Fi is off. Recognition still runs on-device.Point Little Snitch or Lulu at it if you prefer a GUI. You will find the same nothing.
Languages
A hundred languages. Including the way you actually talk.
Most people don't speak one language at a time. Technical terms, product names and English verbs get dropped into every other language on earth, and most dictation tools mangle them — transliterating or translating the whole sentence. Kekoso leaves the borrowed words in the alphabet they belong to.
Set a fixed language if you always dictate in one, or let it detect — with detection switched off when you need it, because on short phrases every detector guesses wrong.
What you said
Задеплой ветку на staging и запушь в master.
Russian, with four English technical terms in it.
What other apps write
Задеплой ветку на стейджинг и запуш в мастер.
Every borrowed term transliterated into Cyrillic. Unsearchable, unusable.
What Kekoso writes
Задеплой ветку на staging и запушь в master.
Borrowed words stay in the alphabet they came from.
The maths
What this normally costs, every month, forever.
Speech-to-text got split into four products, each with its own subscription, each uploading your audio to a different company.
The usual stack
- Dictation app
- $8–15/mo
- Meeting notetaker
- $10–30/mo
- Transcription service for files
- $10–25/mo
- Speech-to-text API for your agents
- $0.006/min
$336–840a year, indefinitely
Rough figures from typical plans, not a specific competitor. Add up your own — the point stands either way.
Kekoso
$29once
- All four jobs, one app.
- No per-minute billing, however much you transcribe.
- No bill arrives if you stop using it for three months.
- Nothing to cancel, because there is no account.
Pays for itself somewhere in the first month.
Pricing
Buy it once. It's a tool, not a tenancy.
Four jobs that usually arrive as four subscriptions, running on hardware you already paid for.
$29once
7-day free trial. No card to start.
- Dictation, files and links, meetings and the MCP server — all of it
- No per-minute billing, no monthly cap, no usage dashboard
- Use it on up to 3 of your own Macs
- Free updates through the whole 1.x line
- Works offline indefinitely; no license check to phone home weekly
- 30-day refund, no argument, no questionnaire
macOS 14 or later · Apple silicon · payment handled by Paddle
Questions
The things people ask before buying.
- Does it really work with no internet at all?
- Yes. After the models are downloaded on first launch, you can stay offline permanently — dictation, files, meetings and the MCP server all run locally. The one thing that needs the network is fetching a YouTube link, because the video has to come from YouTube.
- What can it transcribe besides my own voice?
- Any audio or video file macOS can open — MP3, WAV, M4A, MOV, MP4, voice memos, screen recordings — plus YouTube links. Length is limited by your patience and disk space, not by a plan tier, because nothing is metered.
- How does the MCP server work?
- Kekoso runs a local MCP server on your machine. Add it to the config of Claude Code or any other MCP client, and transcription becomes a tool your agent can call. There is no API key, no per-minute billing and no upload — the agent gets the same models the app uses.
- Are my recordings stored anywhere?
- Dictation audio is held in memory while it is recognised and discarded afterwards. Files you transcribe stay wherever you put them; we never copy them anywhere. Transcripts go into a local database you can search, export and delete.
- Is on-device recognition actually as good as the cloud?
- For dictation and clean recordings, yes — modern on-device models are at parity, and Kekoso keeps the model warm so it usually beats a round trip to a server. In genuinely hard audio, a large cloud model can still edge ahead. We would rather tell you that than pretend otherwise.
- Why does it need Accessibility permission?
- That is the macOS API that lets an app place text into the field you are typing in. Without it, Kekoso could recognise your speech but not deliver it anywhere. It is requested only at the point where insertion first matters, not at the start of onboarding.
- What about password fields?
- macOS deliberately blocks all input tools while a secure field is focused, and that is correct behaviour. Kekoso detects secure input and tells you why it is paused instead of silently dropping your words.
- Do I need consent to record a meeting?
- Often yes, and that is on you — the rules differ by country and by state. Kekoso records only from your side, shows a visible indicator while it does, and never joins the call as a participant. What it removes is the bot in the room, not your obligation to say you are recording.
- Which Macs are supported?
- macOS 14 or later · Apple silicon. On-device recognition leans on the Neural Engine, which is why Intel Macs are not supported.
- Is this a subscription?
- No. $29 once, 3 of your own machines, free updates through the 1.x line. Major versions every year or two may be a paid upgrade, at a discount if you already own the previous one.
Try it on your own words.
7 days, every feature unlocked, no card and no account. If it does not earn its place in your week, delete it and nothing follows you.
macOS 14 or later · Apple silicon