Voice to Text for Mac — On-Device Dictation | Kekoso

Speech in, text out. Nothing leaves your Mac.Voice to text on your Mac: dictate into any app, drop in a recording or a YouTube link, record a call and get both sides as text, and hand your AI agents a transcription server that runs locally. One purchase — no cloud, no subscription, no account.macOS 14.4 or later · Apple silicon · $29 once, not per month · 7-day trialWhat it doesFour kinds of speech. One app, one machine.Speech to text on a Mac usually means paying three or four services to cover it — one for dictation, one for calls, one for files, an API key for everything else. All of this runs on hardware you already own.The distinctionBot-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 apps1Your microphoneAudio captured on device2Their serversUploaded for recognition3Their storageTranscript retained, sometimes for trainingRecording locally is not the same as processing locally.Kekoso1Your microphoneAudio captured on device2Your Neural EngineModel runs on your Mac3Your text fieldText inserted, audio discardedNo account, no upload, no server to subpoena.How it worksThree seconds from thought to text.01Press the hotkeyHold to talk, or tap to toggle. Works in every app, including the ones that block other tools. Your cursor stays exactly where it was.02Say it out loudThe 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.03The text is already thereInserted into the field you were in, with your own vocabulary applied, and written to history at the same moment — so nothing is lost if the paste misses.The rest of itWhat else Kekoso does.Dictation is where most people start. These are the parts that make it worth keeping on the machine.Files and linksA three-hour recording, transcribed while you make coffeeDrag in an MP3, an MOV, a voice memo, a screen recording. Or paste a link to a YouTube video you have the rights to. Everything after that happens on your Mac — no upload, no queue, no per-minute meter running.Audio and video: mp3, m4a, wav, aiff, ogg, opus, mp4, mov and the rest macOS already opensA YouTube link for material you own or have permission to use, or a watched folder that queues new files by itselfExport as TXT, SRT or VTT with timestamps — or send a file in from Finder’s “Open With”How to transcribe audio and video on a MacGetting a transcript from a YouTube videoCall recordingWho said what, because it was never one trackTurn recording on before a call and Kekoso captures two streams: your microphone and everything the other side sends to your speakers. Both are transcribed separately and merged back into one timeline, so “You” and “Others” is a fact about the recording, not a guess made afterwards.No bot joins the call, and nobody has to approve oneEcho from your speakers is subtracted, so your side is not doubledThe transcript exports with speaker labels — hand it to your agent for the summaryAgentsGive Claude or Codex a pair of earsKekoso runs an MCP server on a local socket. One click installs it into Claude Code, Claude Desktop or Codex / ChatGPT desktop, and transcription becomes something your agent can just do — no API key to leak, no per-minute bill, no audio leaving the machine.Eight tools: transcribe a file or a YouTube link, read and edit the vocabulary, list, install and remove modelsDeleting anything needs your click in Kekoso — the agent can ask, it cannot removeEvery call is written to a journal you can read, and the whole server has one off switchVocabularyTeach it the words only you useClient names, drug names, internal acronyms, the library nobody spells right. Add a word once and every transcript after that writes it your way — dictation, files, calls and the agent’s calls alike.Two kinds of rule: fix the spelling of a word it already hears, or swap one word for anotherImport a list you already keep — CSV, encoding and separator detected for youApplies to every language, not only EnglishModelsPick the trade-off yourselfFive models from three families, downloaded on demand and kept outside the app bundle. Each card shows measured accuracy and speed on the same benchmark, so “fast” and “accurate” are numbers you compare, not adjectives we chose.Parakeet for speed, Whisper for reach — 99 languages, SenseVoice for CJKWord error rate and real-time factor on every card, with the caveats spelled outSet the recognition language per model, or leave it on AutoVoice to text on a Mac: four ways, comparedBest dictation apps for Mac in 2026Make it yoursSet it up once, the way you work.A dictation tool is on your keyboard all day. Every part of that — the key you press, the microphone it listens to, whether it makes a sound, how long it remembers — is yours to decide.Five assignable shortcuts: start/stop, cancel, push-to-talk, a mouse button, and call recordingPick the microphone yourself, and get told when macOS quietly switches it mid-callRecording panel in full, mini, or hidden entirely — plus light, dark or system themeSound cues you can turn off, launch at login, and a retention limit that clears old transcripts for youYour week, countedHow much you actually talkWords dictated, times you spoke and your speaking rate, for today, this week, this month or all of it — with a bar chart of the days you kept up and the days you did not.Nothing lostEvery transcript, still on your MacEach dictation is saved with the app it went into — including anything that failed to paste, so your words survive a wrong window. Copy an entry again, delete one, or let retention clear them on a schedule.DetailsThe 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.PrivacyTake 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, calls, dictation and the MCP server all use the same local models.History is a plain text file in your Application Support folder. Open it, back it up, delete it.The MCP server listens on a local socket, is off until you turn it on, and never removes anything without your click.The one exception, stated plainlyPasting a YouTube link means Kekoso fetches that video from YouTube, so that one request goes to Google. Nothing of yours is sent: no audio of yours, no transcript, no identifier — and once the file is on your Mac, transcription is as local as everything else. Whether you may take a copy of a particular video is between you and YouTube’s terms; the feature is meant for material you own or have permission to use.LanguagesNinety-nine languages, and the words no model knows.Recognition runs in up to ninety-nine of them, depending on the model you pick. But the words that decide whether a transcript is usable are rarely ordinary ones: they are product names, acronyms and the names of the people you work with — and every model gets those wrong in the same predictable ways.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 saidPush the OAuth fix to GitHub and tell Renée on Slack.Two product names, an acronym and a colleague whose name carries an accent.What you usually getPush the oauth fix to git hub and tell Renee on slack.Lower-cased, split in half, stripped of its accent. Every time, in every transcript.What Kekoso writesPush the OAuth fix to GitHub and tell Renée on Slack.Add each one to your vocabulary once — every transcript after that spells it your way.InterfaceThe app itself speaks ten of them.Kekoso follows macOS by default, or you pick a language in settings and only Kekoso changes. Recognition languages are chosen separately, per model — the two never fight over each other.EnglishDeutschEspañolFrançaisItalianoPortuguêsРусский简体中文日本語한국어The mathsWhat 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 stackDictation app$8–15/moMeeting notetaker$10–30/moTranscription service for files$10–25/moSpeech-to-text API for your agents$0.006/min$336–840a year, indefinitelyRough figures from typical plans, not a specific competitor. Add up your own — the point stands either way.Kekoso$29onceAll 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.PricingBuy it once. It's a tool, not a tenancy.Four jobs that usually arrive as four subscriptions, running on hardware you already paid for.$29once7-day free trial. No card to start.Dictation, files and links, call recording and the MCP server — all of itNo per-minute billing, no monthly cap, no usage dashboardUse it on up to 3 of your own MacsFree updates through the whole 1.x lineWorks offline indefinitely; no license check to phone home weekly30-day refund, no argument, no questionnairemacOS 14.4 or later · Apple silicon · payment handled by Lemon SqueezyQuestionsThe 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, calls and the MCP server all run locally. The one thing that needs the network is fetching a