search

aj47 / clickolas-cage

a chrome extension that performs web browsing actions autonomously to complete a given goal/task (using LLM as brain).
MIT License
56 stars 11 forks source link

[Feature] Integrate Voice Interaction #7

Open aj47 opened 1 month ago

Shiv282 commented 1 month ago

Hey @aj47, Is this issue still open? We can use webkitSpeechRecognition for the speech to text and I wasn't able to perform the same on the extension level, so scripting this in the active tab and receiving a POST message from there back to extension, have tried this out and works as expected. Do let me know if you find this useful

aj47 commented 1 month ago

Hey @aj47, Is this issue still open? We can use webkitSpeechRecognition for the speech to text and I wasn't able to perform the same on the extension level, so scripting this in the active tab and receiving a POST message from there back to extension, have tried this out and works as expected. Do let me know if you find this useful

Yes @Shiv282 ! That would be great to have the STT done locally with webkit.