Repository navigation
[FEATURE] Desktop: voice input for prompts (mic → text) and optional voice summary output #41364
Closed as duplicate
Description
Feature request
Desktop app has no way to control OpenCode by voice / from mobile. On Windows desktop, users would like:
- Voice input for the prompt box (Windows Speech Recognition or Whisper-style): press a hotkey, speak, and the prompt is transcribed into the input — far faster for long commands than typing Chinese/English on a keyboard.
- Optionally, when the desktop app is minimized, a quick voice command (e.g. hold hotkey) starts listening and sends the prompt.
Why
- OpenClaw/Hermes support voice notes as first-class input for the agent (via WhatsApp voice).
- For Chinese users typing long prompts is slow; voice-to-text in the desktop input box is a low-effort high-value UX feature.
- The web UI could reuse the same API (MediaRecorder → server-side whisper or browser Web Speech API).
Scope suggestion
- MVP: in Desktop app input box, "🎤" button → Windows native speech recognition (or browser Web Speech API in web UI) → insert text into prompt.
- Later: voice output summary (TTS) after long tasks (like "任务完成,要点:…") — configurable via a plugin hook so no model cost.
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon Aug 9, 2026
This issue might be a duplicate of existing issues. Please check:
There are several open and closed issues requesting voice/speech-to-text input. Please review the above to see if your request is already covered, and consider adding your support or additional context to an existing issue instead.
liudongyan13701205717-source commentedon Aug 9, 2026
This request is fully covered by #33300 ("Voice/Speech Input Support for Desktop App", open, assigned to @Hona) and #35219/#37742/#39688. Closing as duplicate — I've added the TTS-output idea and the Windows user context to #33300 instead.
Keep up the good work! The tying thread is that desktop voice input has multiple open issues — a consolidated spec with a maintainer assignment (#33300) is the right home for the microphones button, push-to-talk, and TTS-voice-summary sub-features.