Voice mode feedback

The new voice mode is good but is far away from the ChatGPT voice mode, which feels like you’re actually having a conversation with someone. The Venice voice mode by contrast is just reading the text response, which is similar but feels totally different. I think this is to do mainly with the time delay in getting the voice response because the full text response is delivered first. Would be better if voice mode was the same as ChatGpT and the immediate response is voice and then after the conversation is finished a transcript is provided in the chat.

Also the app should allow the response from the user to be automatically entered via the users voice, rather than either typed or just spoken with pressing the microphone key on the device. Again like ChatGPT’s voice mode.