aftaab99/text2speechservice

Text2Speech service with predictive, dynamic load balancing

Shaik Aftaab Zia

Backend developer skilled primarily in NodeJs, Python and Java. Also experienced in Machine learning and NLP.

Connect with me here

Languages and Tools:

text2speechservice's Issues

Add pretrained Text2Speech model

We'll be using a pretrained model called FastText for speech synthesizing.

To be done

1. Activate the worker env, install all dependencies mentioned in the docs and run pip freeze > requirements.txt.
2. For now write a function that takes a string and saves a wav file for the sythesized speech. Instructions to do this are in the docs.
3. Write a flask POST end-point that receives a string, runs the function to generate the audio file(for this instead of storing to disk save to a StringIO buffer) then send it back as response. Check this on how to send a audio file as response.

Once your done send a pull-request.