Hello everyone! I got object recognition working on a Pi4. It works well. I would now like to take the next steps. The goal is that I can write down what is recognized. I would then like to have it as voice output on the Pi. I am now wondering how can I adapt the script detection.py or proceed to get a recognized object as a “Print” command? espeak-ng -v …
1 Like
Hi @Stephan_Skanta, You can use gTTS(google Text-to-Speech) python library. Please refer this document.
Steps: Extract label from a recognized object.
Convert the label to speech using gTTs
Save it in mp3 format and play.
Thank you