Meaning before speech
Progress, blockers, decisions, tests, and results receive different treatment.
The short answer
Short answer: /voice is speech in, a voice layer is speech out
Claude Code's /voice command is dictation: you speak and it types your prompt. A voice layer for Claude Code is the other direction, speech out: it tells you what the agent finished, what failed, which choice it needs, and whether another session became more important.
Heard (heard.dev), the voice layer for coding agents, does this for Claude Code and Codex on macOS 14 or later, with an open source engine.
The useful unit is not every line of terminal text. It is the next piece of information that changes what the developer should know or do.
A place in the room
Distinct session context makes parallel work recognizable without scanning tabs.
A return path
Supported Heard Power sessions can receive a spoken reply when direction is needed.
See it working
The layer in motion
(1)
Narration out, a reply back
Jarvis narrates a Claude Code session. When it needs direction, hold right ⌘ and answer, and the reply lands in that session.
Hands-free coding(2)
Several sessions, one voice
Four agents run at once. Each update carries its session name, and “Hey Parrot” jumps you to the one that needs you.
Multiple coding agentsVoice coding needs both directions
Speech to text helps a developer give an agent a longer instruction. It does not solve the hours that follow, when the agent runs tools, asks questions, discovers a blocker, or finishes while the developer is looking elsewhere.
A complete loop needs selective spoken output and a controlled way to reply. Heard provides that layer while leaving the coding agent in charge of the task.
Silence is part of a good voice interface
Narrating every command replaces visual overload with audio overload. Heard listening modes set a deliberate threshold. Co-pilot speaks short signposts. Companion offers more context. Focus waits for approvals, blockers, failures, and decisions.
The voice should tell you which session matters
When several sessions run at once, a useful voice layer preserves identity and urgency. A blocked authentication migration should interrupt a routine documentation build, while completed low priority work can wait for the next brief.
The integration boundary must stay inspectable
Developers need to know where events come from, what leaves the machine, which provider receives it, and whether the voice path can write back. Heard publishes those boundaries in its compatibility, security, privacy, and open source documentation.
How the layer works
From agent event to spoken update, and back to the session
The voice layer sits between the agents and you. It reads the event stream, decides what deserves speech, and routes your reply to the session that asked.
-
(1)
Agent events
Claude Code
CodexNative hooks, or one MCP connector for cloud agents.
-
(2)
Voice layerJudged by session type, event meaning, listening mode, and recent context.
-
(3)
Narration
“Auth needs one decision before it can continue.”
Jarvis speaks one short update, with the session named.
-
(4)
You
Listen from anywhere in the room, then decide.
Nothing to watch. Low priority work waits for the next brief.
Reply routing Say “Hey Parrot” or hold right ⌘. Heard types your answer into the session that asked.
How it works
From install to the first useful update
Connect the agent Use a native hook for Claude Code or Codex, or the MCP connector for cloud agents.
Filter the event stream Heard identifies progress, questions, blockers, failures, test results, and final responses.
Listen and respond Choose the amount of speech, then answer supported sessions by voice when they need direction.
Questions
Frequently asked questions
What is a voice layer for Claude Code?
A voice layer is the speech-out half of voice coding. Claude Code's /voice command is dictation: you speak and it types your prompt. A voice layer goes the other way: it follows the session, decides what is worth saying, and tells you out loud what finished, what failed and what needs a decision. Heard (heard.dev), the voice layer for coding agents, does this for Claude Code and Codex on macOS, and on Heard Power can route a spoken reply back to a supported session.
How is this different from text to speech?
Raw text to speech reads whatever text it receives. A voice layer uses session type, event meaning, listening mode, and recent context to decide whether to speak, summarize, defer, or stay quiet.
Does Heard replace Claude Code or Codex?
No. Heard is the spoken output and optional talk back layer around the agents you already use. Claude Code and Codex continue doing the coding work.
Why not use a completion sound?
A completion sound tells you that something happened. It does not tell you whether tests passed, what changed, which session is blocked, or what decision is waiting.
Can a voice layer manage several agents?
It can make several sessions easier to follow by keeping session identity separate, prioritizing blockers and questions, and summarizing lower priority work. It should not pretend to replace source control or worktree isolation.
Can it stay local?
The Heard open source engine supports local Kokoro speech and bring your own service keys. Managed plans use hosted services for selected features, with data handling documented on the security and privacy pages.
Ready when your agents are
Hear the work without watching every screen.
Start with the full Heard Power experience for 14 days. No card required. The open source engine remains free.
Download Heard for Mac macOS 14 or later · Claude Code and Codex supported