hi, i added a

say

inside mcp tool call, how ever, the voice didn't come out until the tts begin, is there a way to look into this issue? is it the problem using it inside mcp tool call, i used native tool call a while ago and it's not the problem.

Hi, sorry, I'm a little bit confused by the question. It looks like you are modifying https://github.com/livekit/agents/blob/main/livekit-agents/livekit/agents/llm/mcp.py. For calling

say

in tool calls, we have a number of examples, such as this one: https://github.com/livekit-examples/python-agents-examples/blob/main/docs/examples/say_in_voice/say_in_voice.py which calls

say

from within a function

my question is the say within tool is delayed till the tts node starts to play. i checked using native function, it is delayed as well