Instructions to use Melotts in docker from Verbi

PromtEngineer / Verbi

A modular voice assistant application for experimenting with state-of-the-art transcription, response generation, and text-to-speech models. Supports OpenAI, Groq, Elevanlabs, CartesiaAI, and Deepgram APIs, plus local models via Ollama. Ideal for research and development in voice technology.

MIT License

726 stars 133 forks source link

Instructions to use Melotts in docker from Verbi #18

Open Seneko opened 1 month ago

Seneko commented 1 month ago

I have installed Melotts in docker on win 11 and installed Verbi locally on pc. Melo UI works in Gradio, Verbi works using groq however I cant succeed to use Melo locally, voice assistant api calls endpoint /generate-audio/ , which doesnt exist in container on the docker. Anyone could assist if they assisted to run it in above mentioned way?

austingreisman commented 1 week ago

I'm also having this issue outside of the container. I'm getting a INFO: 127.0.0.1:59933 - "POST /generate-audio/ HTTP/1.1" 500 Internal Server Error when attempting to chat with Verbi from another terminal running python voice_assistant/local_tts_api.py

austingreisman commented 1 week ago

My issue was not having the proper nltk files required by Melotts. I fixed this by running a python instance, then running the following commands

>>> import nltk
>>> nltk.download()