
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.
Loading comments…
Project Info
Product Keywords
Aloud is a macOS feedback tool that turns rambling, think-out-loud commentary into precise, actionable instructions for coding agents. Instead of writing up detailed bug reports or feature requests, you simply hit record, talk through your app while pointing at things on screen, and let Aloud clean up the mess. It captures your voice, your screen, and a live transcript simultaneously, then rewrites that raw material into a structured, unambiguous prompt your AI coding tools can actually act on.
Aloud records everything in one take: your voice narration, the screen you're pointing at, and a live transcript that scrolls alongside. The recorder stays out of your video, so the playback feels like a clean screen-share session rather than a cluttered recording.
The core magic is in the cleanup. Aloud rewrites your rambling transcript into what you actually meant, removing filler, merging repeated thoughts, and flagging anything that could be read two ways. It asks about ambiguous statements before finalizing, so the output isn't just cleaned up — it's clarified.
When you say "this," "here," or "that button," Aloud knows you're pointing at something. It suggests screenshots from the recording at exactly those moments, letting you drag on the frame to crop. The result is a feedback file with visual context baked in, not just text.
The finished feedback compiles into a single self-contained file you can drop directly into Claude Code, Cursor, or Codex. Your agents receive a precise prompt with pictures included, so there's no back-and-forth guessing about what you meant.
Aloud knows what you mean by "this."
That's the whole pitch in one line. Most feedback tools capture either audio or video or text — Aloud captures all three and then uses the combination to resolve the ambiguity that plagues written feedback. The on-device Whisper transcription means your audio and video never leave your Mac, which is a meaningful privacy win for anyone working on unreleased products. The "wait, no, scrap that" handling is particularly clever: it tracks when you reverse a decision mid-sentence and keeps only the call you stood by.
You're tired of writing detailed feedback for AI coding agents and want to just talk through your screen instead. If you're already working with Claude Code, Cursor, or Codex and find yourself spending more time phrasing prompts than reviewing builds, Aloud removes that friction. And if privacy matters to you, the fully on-device processing makes it a rare option in a space where most tools upload your recordings to the cloud. The first build is coming, so it's worth watching for the Mac download.
Other tools you might consider
The Supercut MCP gives your AI/coding assistants permission-aware access to recordings, including semantic search, transcripts, frames, comments, reactions, and more.
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
AI agents can ship quickly, but without the right product context, they're often flying blind. Brief gives product teams a living source of truth that captures decisions, preserves product intent, and serves relevant context to humans and agents through chat, Slack, CLI, and MCP. It keeps strategy, decisions, and execution connected from vision to impact.
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Maker
modemfox
Loading comments…