Working on 2.7.0 which is on the dev branch right now. It works on my end but I had a few people beta testing with me and they reported various issues across various browsers. It’s the streaming TTS feature that we are testing, enabled in Settings > TTS. It is supposed to start speaking before the LLM finished generating. But on some browser/OS/CPU combination people are hearing it buggy, some overlap audio from multiple chunks, some don’t hear it at all. If you find any issues on your tests, tell me about them, like what browser, OS and hardware you have (if you can share that).
It’s a safe upgrade, easy to turn on and off this streaming feature. I’m always on Discord, but GitHub issues are great and so is email if you find a bug.