Aloud

Turn spoken feedback into tasks your coding agent can run

4.0•1 review•

106 followers

Turn spoken feedback into tasks your coding agent can run

4.0•1 review•

106 followers

Visit website

Screenshots and screen recording apps

Feedback is easier said than written. Aloud records your voice, your screen and a live transcript together while you talk through your app – pointing at things, changing your mind. Then one press: it rewrites the transcript into what you actually meant, asks about anything that could be read two ways, pulls the screenshots you were pointing at, and turns the session into tasks for Claude Code, Cursor or Codex. Whisper runs on-device – your audio and video never leave the Mac.

Free

Launch tags:Mac•Developer Tools•Artificial Intelligence

Launch Team / Built With

LightfieldAI-native CRM that builds itself and does work for you

Promoted

Aloud

Maker

📌

I build with coding agents all day, and the bottleneck stopped being the code a while ago. It's the brief. I'd spot something wrong in the UI, then spend five minutes typing what I could have said in ten seconds – and still leave out the screenshot that would have made it obvious. Aloud is the opposite. Hit record and talk through the build like someone's sitting next to you. Voice, screen and a live transcript, captured together, with the recorder hidden from the video. The part I'm proudest of is what happens after you stop. Real speech is a mess: you say "move this over there", you change your mind mid-sentence, you trail off. Aloud rewrites the transcript into what you actually meant, keeps only the calls you stood by, then asks about anything still ambiguous – one question at a time, over the line it's about, with a recommended answer and one alternative. It pulls the frames you were pointing at, crops and captions them, and turns the whole thing into tasks sized for one agent in one worktree. Copy a task, or export the session as a single self-contained HTML file and drop it into Claude Code, Cursor or Codex. Transcription is on-device Whisper – audio and video never leave your Mac. Only transcript text goes out, and only when you ask for the cleanup. macOS, Apple silicon, free. What does your feedback → agent handoff look like today? I want to know where this breaks for you.

Report

9d ago

@wojciech_dobry Being able to just point and talk feels way more natural than typing it all out.

awesome!

Report

9d ago

Aloud

Maker

@yashekbote exactly that!

Report

9d ago

@wojciech_dobry Any plans to open source this so it can be ported over to intel mac?

Report

8d ago

This is intriguing but I'm confused. I do this process with Whisperflow and tell Claude Code all the things I want to have changed on screens and use Fable to orchestrate Opus agents to make the changes. Since it can see the screen shots on the local dev server for the screen I'm talking about it knows already and I just tell it which button or components to change (not by component library name, just natural language) and it does the updates? Perhaps I'm missing something.

Report

8d ago

Aloud

Maker

@automateiq You're not missing much*. If you're the developer, the app is a local web app, and your agent can drive it – that loop genuinely works. Aloud is for the parts where it doesn't.

Your agent screenshots the dev server, so it sees the screen it can reach. It can't reach the state you were in: a hover, a loading shimmer on the third row, an error that appeared once, step four of a flow behind auth, an animation mid-frame. Aloud records continuously, so the picture attached to a sentence is the frame from the moment you said it. It's also not browser-bound — same thing works on a native app, on Figma, on someone else's product.

The other difference is who resolves "this". In your loop the agent guesses from a screenshot and you find out whether it guessed right after the diff. Aloud asks you first — one question, over the line it's about, with a recommended answer and one alternative, usually a tap — then folds your answer into the transcript, so "move this button" reaches the agent as "Move the Export button to the left of Settings." A wrong guess costs an agent run; a question costs a tap.

What comes out is a plan – tasks sized for one worktree, in waves that run in parallel, each with its own brief and screenshots. You've built that part yourself. Most people talking to an agent haven't.

Aloud takes the commitment out of speaking: with dictation, the moment you stop talking it's already running – here nothing moves until you've read back what you said and changed your mind as many times as you like.

Aloud is designed for long running sessions. You could easily talk to it for an hour.

* – yet, because Aloud in a week will offer MUCH more.

Report

8d ago

Very interesting! Is it limited to Whisper, though? I started using Raycast dictation, and it’s pretty reliable.

Report

8d ago

Aloud

Maker

@tmaleh_ Whisper on-device is what ships today, but it's behind a small adapter, so the engine is swappable — and we're genuinely open to changing it. I'll give Raycast dictation a proper test and see how it compares.

The one hard requirement is timing: every utterance needs a timestamp anchored to the screen recording's clock, because that's how the app pulls a full-res frame from the exact moment you said "this spacing is wrong." If an engine gives me segment timings, it's a real candidate. Thanks for the pointer – I'll report back.

Report

7d ago

@wojciech_dobry I appreciate that!

Report

7d ago

@wojciech_dobry The brief-quality framing rings true, but spoken feedback leans hard on pointing: "move this up", "that button". When the transcript says "this" and the capture shows where my cursor was, does the task your agent receives carry the actual element or file reference, or just the words?

Report

8d ago

Aloud

Maker

@clement_avq Neither – Aloud never touches the DOM, it reads pixels. What it does is refuse to let "this" stay "this": a vision pass reads the frame from the moment you said it and tries to name the thing itself, and only when it can't does Clarify ask you – over the line it's about, with a recommended answer and one alternative.

Report

8d ago

@wojciech_dobry that clears it up, thanks. Naming the thing visually still leaves the agent to locate it in the source though, and a screen can show two instances of the same component where "the one on the right" is unambiguous to me and identical in the code. does the brief carry anything to disambiguate that, or is resolving the name to a file the agent's problem?

Report

8d ago

Aloud

Maker

@clement_avq if screen shows two instances of the same thing it's going to be clarified with the Clarify step. At least it's designed to do so.

Report

8d ago

@wojciech_dobry Makes sense, that's Clarify doing the heavy lifting then. Congrats on the launch.

Report

8d ago

@wojciech_dobry Congrats on the launch. The pointing is the part I'd use. Not having to describe where something is, top left, bottom of this panel, that saves a hell of a lot of time. Definitely worth a try. Thanks for making this.

Report

8d ago

Aloud

Maker

@richardmohammed Thank you for your comment!

Report

8d ago

Refocus

The detail I like most is that it asks you about anything that could be read two ways instead of quietly picking one. I build voice AI that holds daily calls with older adults, and the biggest quality jump we ever got came from the same decision: stop resolving ambiguity silently and ask one short clarifying question. People forgive being asked. They do not forgive a confident wrong interpretation.

How did you tune what counts as ambiguous enough to ask about? Is that a model pass over each segment, or something lighter running across the whole transcript?

Report

5d ago

4.0

Based on 1 review

Review Aloud?

Pros

Cons

Reviews

Most Informative

@automateiq You're not missing much*. If you're the developer, the app is a local web app, and your agent can drive it – that loop genuinely works. Aloud is for the parts where it doesn't.

Aloud

Turn spoken feedback into tasks your coding agent can run

Turn spoken feedback into tasks your coding agent can run

What's great

What needs improvement

vs Alternatives

What's great

What needs improvement

vs Alternatives