Skip to content

A realtime speech to image generator using distil-whisper and stable diffusion SDXL turbo

Notifications You must be signed in to change notification settings

maruel/realtime-speech-to-image

 
 

Repository files navigation

Realtime speech to image with theme selection

Generated lion image

Program flow

Program flow

How to run

./run.sh

Navigate to http://127.0.0.1:7860 to select the theme in realtime.

Start talking into your microphone and images will start appearing in realtime in the .img directory

About

A realtime speech to image generator using distil-whisper and stable diffusion SDXL turbo

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 86.0%
  • Batchfile 8.3%
  • Shell 5.7%