Wrap the command you use.
Start a process with heard run and let Heard follow its output.
OpenClaw and Hermes
Your command line.
Now with a voice.
Use Heard’s open source engine to wrap a compatible command line agent and turn its output into spoken updates.
Apache 2.0 · Build from source
research · terminal
› heard run hermes
Following process output…
Found 12 sources
Kept 5 relevant results
Wrote notes/latency.md
✓ Research complete
Research is done.
Three sources need your review.
Keep your setup.
Build the Apache 2.0 engine from source. Use local Kokoro speech or configure your own provider keys.
Check the behavior.
Wrapper support depends on the agent’s output. Test questions, failures, and completion with your workflow.
- 01
Build the engine.
Follow the open source installation instructions for your Mac.
- 02
Wrap your agent.
Launch it with
heard run <command> [args...]. - 03
Verify the updates.
Compare narration with the terminal on a short task before relying on it for longer work.
A few more details
Questions?
Does Heard have a native OpenClaw or Hermes adapter?
Not a narrating one. The Heard Mac app installs a Hermes plugin that shows Hermes sessions without narrating them. For spoken progress, both tools use the open source engine’s heard run wrapper, so compatibility depends on the output their current versions expose.
Does `heard run` support every command line agent?
No. It can only interpret output that reaches the terminal in a usable form. Interactive and alternate-screen applications may expose less context.
Will I still see the original terminal output?
Yes. The wrapper tees the child process output so the visible terminal remains available for direct inspection.
Keep exploring.
All use casesMake it your own.
Read the code. Choose your providers. Build the engine.
