Heard
Give Claude Code and Codex a voice
Start new thread

Heard - Give Claude Code and Codex a voice

by•
Heard is a macOS voice layer for your agentic workflows. It connects to Claude Code, Codex, and Cursor and turns their output into intelligent summaries you can hear. Full commentary when your eyes are elsewhere, or silence until something errors or needs a decision. With agents run in parallel, Heard summarizes at the project level, so you hear where the work stands, not five terminals talking over each other. Pair your phone and it comes with you. Open source, free for personal use.

Add a comment

Replies

Best
Maker
📌
Hey PH, Kelly here, maker and founder of Heard. The last two years went into making it easier to talk to agents. Voice input, better prompts, better context. Nobody worked on the other half. Agents still answer in scrolling text you have to sit and watch. Heard is that half. It listens to your Claude Code, Codex, and Cursor sessions, understands what matters in context, and turns the useful parts into concise, natural speech. A useful update, not a transcript. It matters most once you're running more than one agent. Parallelism is free now, attention isn't, and every agent you add makes the terminal a worse instrument for keeping up. So each agent gets its own voice, and a swarm gets summarized at the project level. One clear story instead of five windows you can't watch at once. With Heard Power you can pair your phone and keep the session going from the kitchen, a walk, anywhere you're not at the desk. Hear what's happening, answer by voice, approve the next step in one tap. Open source, free for personal use.

this is a problem I've genuinely felt running a few agents in parallel - the terminal tiling stops scaling around agent 3. curious how Heard decides what's worth saying out loud versus staying silent. is it watching for specific signals like a tool-call failing or a permission prompt, or is there an LLM in the loop summarizing raw output, and if so how do you keep it from either talking over something important that's buried in a wall of routine logs, or going quiet during a long stretch that looks routine but actually needed a decision?

Maker

 yeah agent 3 is the exact wall. tiling breaks down and you end up alt-tabbing to check on things that didn't need you.

it's both of the things you guessed. some events are hard signals - permission prompts, tool-call failures, a run exiting - those get spoken no matter what. everything else goes through a pass that keeps context across the session, so it's not judging each line in isolation. it holds what's happened so far, learns what you actually care about, and decides when there's something worth saying.

the two failure modes you named are the whole problem and most of the tuning went there. talking over something buried in routine logs: the hard-signal list catches that, a permission prompt gets pulled even if it's mid-wall. going quiet during a long routine stretch that actually needed a decision: that's the harder one, and holding context is what makes it possible to catch - it knows a decision point is coming even when the surrounding output looks boring.

curious how many agents are you running, and where does it start breaking for you?

Hunter

Not every product needs to be flashy to stand out.

When you've got Claude Code, Cursor, or Codex all doing their thing, you don't want to babysit five terminals. You just want to know when something important happens.

That's why I was excited to hunt today.

It's simple, useful, open source, and feels like one of those products you'll wonder how you worked without.

Really excited to bring this one to the Product Hunt community. Give it a spin, ask the makers your toughest questions, and let us know what you'd build with it.

Congratulations on the launch!
This solves a problem i run into daily with multiple AI agents.how does Heard decide which updates are important enough to speak instead of reading everything? is the prioritisation customizable for different workflows?


Maker

 thanks!

two layers. hard signals always get through - permission prompts, failed tool calls, a run finishing. the rest goes through a pass that keeps context across the session, so it's weighing what actually matters against what you've already seen, not reading you every line.

and yeah, customizable. there's a verbosity dial from full commentary down to errors-only, so you can run a chatty agent loud and a background one near-silent. different workflows, different settings.

how many terminals do you typically run?

congratulations! love seeing tools that reduce context switching. how does Heard integrate with Claude Code, Cursor and Codex? is setup just a few clicks?


Congratulations! the workflow sounds perfect for developers who multitask. can heard be configured to ignore specific repositories or projects? that would be useful for reducing noise.


i really like the focus on reducing cognitive load. does heard work well with very large codebases? how does it maintain context across long development sessions? curious about the underlying approach.


the open source approach is great to see. are there plans to support additional coding assistants beyond the current integrations? which platforms are highest on your roadmap?


Maker

AI should not be controlling our life, while it should be companion - Heard is the thing you definitely need but might always be ignoring. We give AI and agents a voice, that you hear and you will be heard - that brings to a harmonic vibe for AI and human.

Congratulations! really interesting approach to agent monitoring. can heard read updates in different languages or with different voice options? how customisable is the speech output?


12
Next
Last