Dictate into any app on Mac, Windows or Linux with free on-device speech recognition
Sayso is an open-source dictation app: press a key, speak and the text lands in whatever app you are using. Recognition runs on your own computer (WhisperKit on Mac, whisper.cpp on Windows) unless you choose a cloud model.
Source
watzon on Hacker News · 2026-10-13 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-16.
What they did
Sayso is an open-source dictation app: press a key, speak and the text lands in whatever app you are using. Recognition runs on your own computer (WhisperKit on Mac, whisper.cpp on Windows) unless you choose a cloud model.
Result (as claimed)
Free and open source (GPL-3.0); 25 points on Show HN.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Define the job
Say exactly what you want done and what the agent may and may not do on your behalf.
Share only what is needed
Give Whisper the minimum files or access required. Avoid sharing passwords in chat when a safer login flow exists.
Review the plan
Ask the agent to show its plan or draft before it acts, and approve each step that has real consequences.
Check the result
Confirm the outcome yourself (order placed, request sent, document understood) and keep a record.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Dictate into any app on Mac, Windows or Linux with free on-device speech recognition What the original author did: Sayso is an open-source dictation app: press a key, speak and the text lands in whatever app you are using. Recognition runs on your own computer (WhisperKit on Mac, whisper.cpp on Windows) unless you choose a cloud model. Reported result (as claimed by the author): Free and open source (GPL-3.0); 25 points on Show HN. Source: https://news.ycombinator.com/item?id=50073755 Tools they used: Whisper Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Dictate into any app on Mac, Windows or Linux with free on-device speech recognition What the original author did: Sayso is an open-source dictation app: press a key, speak and the text lands in whatever app you are using. Recognition runs on your own computer (WhisperKit on Mac, whisper.cpp on Windows) unless you choose a cloud model. Reported result (as claimed by the author): Free and open source (GPL-3.0); 25 points on Show HN. Source: https://news.ycombinator.com/item?id=50073755 Tools they used: Whisper Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Dictate into any app on Mac, Windows or Linux with free on-device speech recognition What the original author did: Sayso is an open-source dictation app: press a key, speak and the text lands in whatever app you are using. Recognition runs on your own computer (WhisperKit on Mac, whisper.cpp on Windows) unless you choose a cloud model. Reported result (as claimed by the author): Free and open source (GPL-3.0); 25 points on Show HN. Source: https://news.ycombinator.com/item?id=50073755 Tools they used: Whisper Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Related use cases
Flag moments in offline Mac meeting transcripts mid-call
Built Trace, an offline Mac app for meeting transcripts you can flag while the call is still going.
Dictate on Mac with on-device voice and no model download
Built Yap, open-source on-device voice dictation for macOS that needs no model download.
Vibe-code a Mac voice app that types or runs agent actions
Vibe-coded a Mac dictation app with Claude Code: one mode types what you say, another runs agent actions across files, shell, AppleScript and any MCP server.
Send ideas to your Grok Bots from a Mac hotkey
Tired of opening Grok Bot for every idea, the author built a Mac shortcut: Option+Cmd, type or talk, pick a bot, send.