Launched this week
Heard
Give Claude Code and Codex a voice
582 followers
Give Claude Code and Codex a voice
582 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.
how does Heard avoid interrupting users with unnecessary voice updates? can notification frequency be configured?
Heard
@flora_kendall that's the core of it. hard signals always come through - permission prompts, failures, a run finishing - but everything else gets weighed against what you've already heard this session, so it's not pinging you on every step.
and yeah, configurable. there's a verbosity dial from full commentary down to errors-only, per agent, so a chatty one can run loud and a background one near-silent.
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?
Heard
@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.
Heard
@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?
Heard
@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?
Heard
@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!
This is such a smart approach to staying in the loop without constant notifications.
With multiple agents running in parallel, how does Heard decide which project's update to summarize first if two things happen at the same time?
Also curious if the prioritization logic is customizable.
Heard
@aymi_malik thanks!
when two things land at once, hard signals win - a failed build or a permission prompt jumps the queue over routine progress. everything else gets spoken one at a time, with the voice telling you which agent each came from, so nothing talks over anything.
and yeah, you can tune it - a verbosity dial from full commentary down to errors-only, per agent. run a noisy one loud and a background one near-silent.
what's your parallel setup usually look like?
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?
Heard
@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.