Heard
Give Claude Code and Codex a voice
629 followers
Give Claude Code and Codex a voice
629 followers
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.
Free Options
Launch Team
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Congratulations on the launch! 🚀
Really curious about the technical side. how much system overhead does Heard add while monitoring multiple agents? is performance impacted much?
@daris_esteban thanks! it's light. Heard isn't polling or scanning your machine - it reads the output stream the agent already produces, so the monitoring itself is close to free. the only real cost is the summarization pass, and local TTS if you run voices on-device rather than through the cloud.
running several agents at once doesn't multiply that much, since the heavy part is per-event, not per-agent. haven't seen it get in the way of the actual agents doing work.
Congratulations on shipping!
The idea of each agent having its own voice is clever.can users assign custom voices to different agents?seems like that would make them easier to distinguish.
@jazzlyn_amspoker we actually made this happen in a previous version and decided it was too messy. however, might bring that back as a setting that people can try with!
Love the idea of replacing terminal watching with listening. does Heard keep historical voice summaries for later review? or is the experience designed to be entirely live?
@saskia_visser right now it's live, but we're working on a version where you can just put all summaries aside and go through them when you want!
the project-level summarization across parallel agents is the part that stands out to me, most voice/notification tools just narrate everything and become noise. when it decides what counts as "something errors or needs a decision" across say 4 parallel Claude Code sessions, is that heuristic hardcoded or does it learn what you personally care about over time?
@omri_ben_shoham1 that's such a great observation. honest answer: heuristics today, learning loop coming soon.
right now each session gets a quick read - a fresh failure is blocked, an agent mid-decision or dumping a long response needs you, everything else is routine. four sessions, four independent reads, and the blocked/decision ones jump the queue over routine progress. a reasoning pass can override those when context warrants, so it's not a fixed rule table, but it's judging the moment, not your personal taste yet.
that personal-preference layer - it learning what you specifically care about over time - is what's coming next. for now you shape it with the verbosity dial per agent!
Congrats on the launch. The multi agent part caught my eye, giving each agent its own voice identity is a smart way to keep track of parallel sessions without staring at four terminals. How does the filtering decide what counts as a critical event versus routine noise, is that configurable per project?
@adamkamaneh thanks! filtering works in two layers. some events always speak: permission prompts, failures, a run finishing. everything else gets weighed against the session, so routine stuff stays quiet and the important thing cuts through.
and yeah, you can tune it - a verbosity dial from full commentary down to errors-only, per agent.
are your parallel sessions usually separate features, or several agents on one? curious how people want that handled.
Huge congrats on the launch, @itskellysun Solving the outbound half of the agent interface is such an underrated vector. qq can we adjust a 'verbosity slider' to only hear critical errors instead of full updates?
@priya_kushwaha1 hey Priya - yes you can! you can adjust verbosity with 3 different modes in settings :)
really smart approach to the feedback loop problem with agentic coding. half the time I'm running Claude Code I'm doing something else entirely and only check back when it's done — having audio summaries of what happened means you catch errors or odd decisions way earlier instead of reading through the whole diff after the fact. does it differentiate between routine completions vs things that actually need your attention?
@ozandag yes you can switch between modes and have settings to talk with continuous summaries or only when things need your attention!