+-Discord Shoutbox


Alternatively, join us on Discord directly.
You can help CodeWalrus stay online by donating here.

Text to speech...in my own voice [Python]

Started by JWinslow23, December 07, 2017, 08:33:48 AM

Previous topic - Next topic

0 Members and 1 Guest are viewing this topic.

JWinslow23

After discovering Text to Trump, I thought to myself: how cool would it be to make a text-to-speech voice that resembles my own? And then I thought: how hard would it be?

The answer to both questions is "very". :P

Slightly modified from this Github repository, I created a Python program which would take entries in a modified version of the CMU Pronouncing Dictionary, convert them into individual sounds, and play them back (as well as output them to a .wav file). The results are a bit Stephen-Hawking-ish right now, but I hope to try and improve it soon ;)

Here is an example of "my own voice" reading the CodeWalrus intro: https://clyp.it/02ucuy3z

Requires Python, PyAudio, and PyDub. You do not need FFmpeg, but the program can freak out without it.

Project download here. Try it!

_iPhoenix_

You had a great opportunity to use machine learning, yet you didn't!
  • Calculators owned: Two TI-84+ CE's
Please spam here: https://legend-of-iphoenix.github.io/spam/

"walruses are better than tuxedo chickens, all hail the great :walrii:" ~ me
Evolution of my avatar:

Caleb Hansberry

  • Calculators owned: TI-82, TI-83, TI-83+SE, TI-84+SE, TI-85, TI-89, TI-99/4A
  • Consoles, mobile devices and vintage computers owned: HP Portable Plus 110, Toshiba T3100, Toshiba T5200, GRiD 1660, TI-99/4A, Apple IIgs, and much more than I can list here


Powered by EzPortal