Kekoso

Kekoso is a menu bar app for macOS that turns speech into text without sending audio anywhere. Press a hotkey, talk, release, and the text is pasted into whatever field you were typing in.

Three families of speech models run locally behind one protocol, and you choose which one is active. Parakeet TDT v3 is the fastest and covers 25 European languages, SenseVoice handles Chinese, Cantonese, Japanese and Korean, and Whisper through WhisperKit runs on the Neural Engine and carries the long tail of 99 languages. Models are downloaded once on demand, so you keep only what you use.

Besides dictation it transcribes local audio and video files, YouTube links and recorded calls, exports TXT, SRT and VTT with timecodes, watches folders for new files, and applies a custom dictionary for names and terms.

Because Whisper was trained on subtitled video, it tends to invent sign-off lines on silence. Segments with no audio behind them are dropped before anything reaches your text field.

The app reaches the network in three places only: licence checks, updates, and fetching audio when you paste a YouTube link. Dictation works with Wi-Fi off, and there is no account.

The interface is available in ten languages. Requires macOS 14.4 or later and Apple silicon. One-time purchase for three Macs with a 7-day trial.