search

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
123 stars 35 forks source link

First Commit - #9

Open 3choff opened 3 weeks ago

3choff commented 3 weeks ago

Add fastxttsapi, Add stream player Change elevenlabs resposes to stream Update README

3choff commented 3 weeks ago

@PromtEngineer Here is the Coqui XTTS implementation. In this PR, I added a streaming player function in the audio.py, changed the ElevenLabs responses to stream for better performance, added a voice example to the repo, and updated the README.