I need some help debugging an issue I'm facing with my agent. I'm streaming audio chunks from a tokenizer to a custom TTS class. The problem is that sometimes, when a new chunk arrives, the previous audio gets replayed briefly at the end—almost like an echo effect. It doesn’t happen consistently, but enough to break the flow. I suspect this might be an issue on the livekit side, possibly related to how I'm handling flushes, synthesized streams, or maybe my no-wait event logic. But I haven't been able to pinpoint it or debug further.

Thanks for reaching out, Ahmad. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

what do you need me to clarify?

Hey there! Thanks for reaching out. I'd love to help you get to the bottom of this. Could you help me understand a bit more about what's going on? I'm curious about a few things that might give us some clues: • Which LiveKit SDK or API are you using for this project? • Can you walk me through how you're handling the audio stream – especially the details about flushing and managing those synthesized streams? • Have you noticed any specific patterns or conditions that seem to trigger the issue? Like certain audio chunk sizes or network situations? • Are there any error messages or logs that might shed some light on what's happening? The more details you can share, the better I'll be able to help you track down the root cause. I'm totally here to help you solve this!