Open metalshanked opened 3 months ago
Hey @metalshanked, did you figure out how to stop recordings when the user stops speaking? I'm looking for the same information. Essentially trying to build a pipeline that looks like: audio -> speech-to-text -> LLM -> text-to-speech. Appreciate any learnings you may have so far
Thanks for the amazing component! Is there a way to automatically stop recording if there is no longer any sound detected? like how the AI assistants work?
Also, is there a google api quota for Speech to text calls using this component?