I do not have experience with Twilio, but I can implement any AI and have developed, implemented, deployed AI for VAD, TTS, STT, intent detection, diarization, computer vision, audio synthesis, video synthesis etc. I have experience in implementing, developing and creating API.
For your project, I can implement a VAD AI system and create an API which can be integrated into your existing system.
1. What is the latency are you targeting?
2. What is the quality of the audio (noisy, ambient noise, clean) that will be sent to the VAD AI ?
3. In which format do you want the result to be sent to you ?
Contact me through chat.