Agent Speak for Codex and Claude Code
Connect Codex or Claude Code, read or hear short summaries, and reply through the HUD.
Connect Agent Speak
Agent Speak shows Codex and Claude Code replies in Whisperstream's HUD. You can read a short written summary, hear it through local speech, and dictate a reply after an agent finishes.
Agent Speak connects to coding agents on your PC. A connected agent can still send messages to its configured model service, and Lockdown Mode does not disable Agent Speak.
Install Codex or Claude Code and open it at least once. Then:
- Open Experimental in Whisperstream and turn on Agent Speak.
- Under Connect your coding agents, select Connect for Codex, Claude Code, or both.
- For Codex, open Codex and run
/hooks, then review and trust Whisperstream. For Claude Code, run/reload-pluginsif Whisperstream says its plugin was installed or updated. - Choose Show summaries, Read replies aloud, or both. Setup starts with both selected and requires at least one. If you choose speech, select a local voice model and voice, adjust Speed, and use Play to test it.
- Set the shortcut that opens the full response, then follow the final on-screen test with your connected agent.
The test checks your selected response mode and voice replies. Claude Code also presents a practice structured question. Codex does not provide structured questions to Agent Speak.
After setup, select Configure beside Agent Speak to change its settings. Each agent has separate Check for updates and Disconnect actions. Follow any status instruction shown below it.
View responses and dictate replies
Turn on Show summaries to display the agent's short written summary when it finishes. This is independent of Voice, so you can read summaries without hearing them. New installations start with both settings off; completing setup saves your selections.
Use View full response to expand the complete reply, even with automatic summaries off. The default shortcut is Ctrl+Alt+backtick, and you can replace or clear it in Agent Speak settings. Existing saved shortcuts are not changed automatically.
Reply window controls how long your normal dictation shortcut answers the response that just finished. Choose 1 to 30 seconds, or Off to disable temporary replies. Setup selects 20 seconds with written summaries or 6 seconds with speech alone. In Configure, enabling summaries changes a 6-second window to 20 seconds; disabling them changes 20 back to 6. Other values stay unchanged.
During that window, start dictation with your usual Push to Talk or Toggle shortcut. Your draft appears in the HUD:
- With Send replies automatically off, review the draft and press Enter to send it. This is the default.
- With Send replies automatically on, Whisperstream sends it when dictation finishes.
Claude Code can also send structured questions to the HUD. Expand the question, then press the displayed number for your answer. Codex structured questions remain in Codex. Press Escape to close the response or defer a Claude Code question without answering it.
For replies after this temporary window closes, see Coding agent sessions.
Configure local speech
In Agent Speak > Configure, turn on Voice to hear short summaries. Speech is generated locally and does not read the complete response aloud.
Whisperstream recommends a voice model from your computer's available memory. Higher quality sounds more natural; Lower memory starts faster and uses less memory. Change Voice model, Voice, Speed, and Volume here. Voice previews are available in the picker. For the playback destination, see Audio.
Use Speak in to choose when speech is requested:
| Choice | Behavior |
|---|---|
| Every session | The default once Voice is enabled. Requests speech from every connected session. |
| When I ask | Use /whisperstream:speak in a Claude Code session or $speak in a Codex session. |
In Claude Code, /whisperstream:speak Project name also names the session. Use /whisperstream:name Project name to name or rename it, or /whisperstream:name to clear that name. Named sessions show their names in the HUD, and their spoken summaries begin with the name.