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.
Added support for using local models via Ollama.
Now you can set the
RESPONSE_MODEL
toollama
for using local LLMs. Need to make sure theOllama API
is running.config.py
as:LLM Selection
OLLAMA_LLM="llama3:8b" GROQ_LLM="llama3-8b-8192" OPENAI_LLM="gpt-4o"