I have speech turned on, and accidentally hit the button. Now it’s frozen in a “waiting” state. I can’t type, and it’s not hearing me, although I did allow Mic access in the browser (Chrome/Mac).
Hi @lbdesign ,
Thank you for reaching out!
Are you still encountering this issue? If so, we’d really appreciate it if you could share the steps to reproduce it. We weren’t able to replicate the problem on our end, so it’s possible this was a one-time glitch.
In the meantime, it might help to refresh the page or restart your browser. Please let us know if this happens with a specific Pickaxe or across all Pickaxes that use voice input. Also, if you’ve tried switching browsers or devices, or clearing your cache and cookies, that information would be helpful. Any details you can share will help us investigate further and get things working smoothly again.
Thank you, and it’s still happening on any bot in Chrome. I’m using ChatGPT with my own key. I’ve restarted the entire computer, updated Chrome, etc. Any bot in Chrome just gets stuck “listening” and hitting the Stop button doesn’t work. It gets stuck in “listening” mode. I can’t type, and I can’t stop it.
I tried it in Safari, and it kind of works, but there is no streamed dictation. It acts like nothing is happening or being heard. When I hit the “Stop” button, then the text appears. Is that normal?
Hi @lbdesign ,
Thank you for the update.
Since the issue appears to be specific to your Chrome browser, it may be related to a configuration or setting within Chrome itself. I recommend clearing your cookies and browser cache, which can help resolve potential conflicts. You can also try using an incognito window to rule out interference from extensions or stored data. Additionally, please review your microphone and other permissions in Chrome to ensure the site has full access. Disabling any browser extensions related to privacy, audio, or input control may also help isolate the problem.
Regarding the behavior in Safari, what you described is expected. Streaming dictation is not currently supported. The voice input feature enters a listening state, captures everything you say, and then displays the transcribed text only after you press the Stop button. However, this feature is still relatively new, and we are actively working to improve it. Your feedback is greatly appreciated as it helps us improve the platform.