we have been building an open source orchestration which enables you to plug in your own TTS/ASR/LLM for end-to-end voice conversations at -> https://github.com/bolna-ai/bolna.
Few days back, was having a discussion here in HN about the possibilities of having a complete open source stack for ASR+LLM+TTS.
Today, we are releasing a complete open sourced Dockerized stack by merging Bolna with Whisper ASR, Llama3 and Melo TTS.