Hi everyone,
I'm working on an idea and would love to hear from anyone who has explored or implemented something similar. I'm currently using Google Cast devices (like Nest Mini or Chromecast Audio) integrated with Home Assistant to send text-to-speech messages using the cast integration.
Now, I'm trying to go a step further and enable interactive voice conversations powered by Home Assistant Voice and a large language model (LLM) like GPT, Claude, etc. Ideally, I'd like to:
Use a Google Cast device as both input and output for voice.
Capture the user's voice, transcribe it, and send it to an LLM.
Receive the LLM's response and play it back as audio on the same Cast device.
Here’s my main question:
🔸 Is it technically possible to use a Google Cast device as a full voice interface (bidirectional) for Home Assistant Voice or any setup involving LLMs?
🔸 Has anyone implemented something like this or knows of any major limitations?
I know that Cast works great for TTS, but I'm not sure if it can serve as a fully interactive conversational device. Any tips, ideas, or experience you can share would be greatly appreciated 🙏
Thanks in advance!