Word by word
Word-level timing from Groq Whisper, ElevenLabs Scribe or Google Gemini — on free tiers, with your keys in the macOS Keychain.
Captions for vertical video — automatic and good-looking.
Sukhan is a tiny editor for captions. It transcribes speech with word-level timing (Russian with English terms, English, Kazakh), lets you fix text on the timeline or right in the preview, and the preview matches the export pixel for pixel. In development.
Who it’s forCreators and social media teams making short vertical videos.
Word-level timing from Groq Whisper, ElevenLabs Scribe or Google Gemini — on free tiers, with your keys in the macOS Keychain.
Waveform and zoom, drag phrases and word edges, split and join, nudge the track by 50 ms, ⌘Z.
If the ratio is different — crop by dragging right in the preview, or fit with a blurred background.
One Rust engine for preview and export. On Apple M4, a one-minute 1080×1920 clip with captions exports in 8 seconds.
Drop a video into the window — MP4, MOV, MKV, WEBM, M4V or audio.
Pick a provider and language — Sukhan transcribes word by word.
Fix the text on the timeline and save a .subproj project.
Stages 0–3 are done: renderer, player, frame formats, recognition, editor and projects. Next: styling, presets and export.
No, FFmpeg is bundled with the app.
In the macOS Keychain, not in files.
Radial file converter for macOS
Learn more Morfus ↗Menu bar converter for macOS
Learn more Morfu ↗Image compression and cropping for the web
Learn more Pachaq ↗Local background removal on Mac
Learn more radius ↗Audio & video transcription in the browser
Learn more BLA-БЛА ↗Search photos, icons and video everywhere at once
Learn more Picta ↗A gamepad in any game on Mac
Learn more PadBridge ↗Your Downloads, right next to the Dock
Learn more Moss Pocket ↗Links in a window over the page
Learn more Peecube ↗A video or photo instead of your webcam
Learn more ANY CAMERA ↗Message me on Telegram — I reply fast.