Solo transcribes your speech and rewrites it with AI — entirely on your device. No cloud. No latency. No compromise. Built for Apple Silicon.

Framer — Launch websites with enterprise needs at startup speeds.

Launch websites with enterprise needs at startup speeds.

Hey Product Hunt! 👋 I built Solo because I got tired of every voice dictation tool sending my audio to someone's server. Whisper is incredible, but running it yourself felt too technical for most people. I wanted something that just works — press a hotkey, speak, get polished text — with zero cloud involved. Under the hood, Solo runs two on-device models back to back: - WhisperKit (Apple Neural Engine) transcribes your speech - Apple Foundation Models rewrites the raw transcript into clean, polished text Both run entirely on your Mac or iPhone. Your audio and text never leave your device. A few things I'm proud of: - Option+Space → speak → ⌘V to paste. That's the whole macOS workflow. - The iOS keyboard extension lets you dictate into any app without switching away - Lifetime purchase option I'd love to hear what you think, and happy to answer any questions about how it works under the hood.

What strikes me the most is that all voice recognition runs locally, without uploading to the cloud. Don't have to worry about the recording being uploaded to any server. It's easy to use. I wonder if there are plans for an Android version.

@dingdingdingyinyinyin

Thank you so much 🙏

Yes, definitely. I have plans for that. As Solo is built completely native for Mac and iOS devices, I also want to have a native experience for Android as well. So it will take some time, but I will build a native application for Android soon 💪