Juno

Free, local AI powered Voice to Text w/ live transcriptions

Productivity

Open Source

Artificial Intelligence

Visit WebsiteSee on Product HuntGithub ⧉LinkedIn ⧉Twitter ⧉

Congrats on the launch, Jas! I’ve actually been looking for a solid tool to convert audio files and voice notes without uploading sensitive data to a cloud server. The fact that Juno runs completely offline, local, and open-source is a massive win.

I’m almost sad this is currently exclusive to Mac users, because it looks incredible! What’s the main reason behind this choice? Is it due to leveraging Apple's native hardware/CoreML for local AI, or do you have plans to bring Juno to Windows/Linux users in the near future? I'd love to use it across all my setups! 🚀

whisper + live transcription locally is the chunk-size dance — too short and you lose context across the boundary, too long and the perceived latency drags. cold-start hits once, but the per-chunk recompute pattern is the long tail.

how to train this model on my local system? when i make corrections in the transcript does it learn? I have tried similar tools in the past, but I was not successfully able to train them. Like the words that I wanted in its vocabulary, I was just not able to get it to learn them. How does Juno solve this problem?

Local, offline, open source, and free — that's a rare combo. Does Juno work well with longer dictations, like voice memos or drafting emails, or is it more optimized for short bursts of speech?

I always prefer something that's private and works locally. It's works pretty great. Great work @jas_jaski @dudhatparesh

One of the most interesting launches today! The part some people might miss is that live transcription brings its own trust problem like a word commits on screen, then self-correction rewrites it a beat later and now I'm watching my own text flicker. I wonder how long does a token sit provisional before you lock it, and does the local agreement step ever lose a race against me already talking past it?

The fully-local, offline architecture is the part I keep coming back to. I work on voice AI for older adults, and the thing that breaks most transcription is atypical speech: slower pacing, disfluencies, regional accents the generic models were never trained on. Since Juno runs the model on-device, can users add custom vocabulary or adapt it to a specific speaker over time, or is the acoustic model fixed? And with no cloud fallback, what happens to a low-confidence segment, does it surface uncertainty or just commit to a best guess?

Hey congrats on the launch @Juno team and congrats @rohanrecommends for the great hunt!

Wwhy should someone use Juno instead of tools like Wispr Flow or MacWhisper?

Is the main difference that Juno is local-first, offline, open source, and has no subscription? Or are there also specific workflow advantages in how it handles dictation, rewriting, and typing across different Mac apps?

A key discussion for me was: how high can reliability be?

• I give very long blind-prompts (I literally close my eyes because the dancing animation distracts me) - Juno can show me the transcript, which is great

• but what if my prompt is dropped? it happens sometimes in GPT still and I was very keen to understand the speech harness - which will prevent this and other oops moments from happening.

Would love it if @jas_jaski or @dudhatparesh talk a little more about the engineering behind Juno.

The "local" part is what actually matters here, and I'm curious how far it goes. Is the speech-to-text model running fully on-device with no outbound calls at all, or does "local" mean the app itself is local but transcription still hits an external API? That distinction is the whole ballgame for anyone who'd use this with sensitive work. Also wondering how it handles domain-specific vocabulary, medical terms, code identifiers, things that generic transcription models consistently mangle.