As the title suggests, I need to develop a voice chatbot with RASA. I have searched online, but have not found any accurate and up-to-date guides. I would like to use a DeepSpeech for STT and Mozilla TTS as explained in a tutorial on the RASA blog and in the original Medium article, but I am not quite clear on how to integrate the two modules into the project. Could someone provide me with some useful pointers or a link to a detailed tutorial?
Please note: any STT and TSS module is acceptable (not just Mozilla), as long as it is free and implements Italian
@FabioCarosi there is a lot use-case already mentioned on the forum based on your use case, you just need to explore. I have assisted with that in the past but the thread I do not remember and the blog post is quite old so a lot of workaround is already done. Check this conversation and there are others on the forum. Good Luck!
Thank you for your reply, but I had already read the original Medium article linked in the post. I was able to follow the guide laboriously until I tested the STT module, but I am having difficulties with various incompatibilities between versions of python, pip and various packages (Mozilla TTS in particular). I wanted to look for a more up-to-date and definitive guide that uses recent versions of RASA, python, and STT and TTS modules. I also saw some posts recommending using Silero models instead of Mozilla, but for me this is not a viable solution as they do not include Italian.
