Voice-Cloning 0.0.4

Introducing Voice_Cloning: A Python Package for Speech Synthesis and Voice Cloning!

Introducing Voice_Cloning: A Python Package for Speech Synthesis and Voice Cloning!

Feature	Output
Real-time voice cloning	The package can clone a user's voice in real-time by analyzing a reference voice clip and a user's speech input
Speech synthesis	Allow users to generate synthetic speech using a text input with pre-loaded speakers, similar to a text-to-speech (TTS) system
Multi-Accent support	Supports Indian and Western-style accents for voice cloning and speech synthesis
Noise reduction	The package includes functionality to reduce noise in the recorded audio, improving the quality of the cloned or synthesized voice

Installation

Use the package manager pip to install Voice-Cloning

pip install voice-cloning

Usage

Clone using an external reference voice

# load all the functions
from voice_cloning.generation import *

# provide a reference sound file and a speech text
sound_path = r"xx/xxx/xxx.wav"
speech_text = "This is an awesome package!"

voice_generator(sound_path, speech_text)

# if you want to select the voice type, currently supports "indian" & "western", by default its "western"
voice_generator(sound_path, speech_text, voice_type = "western")

Play and save the sound with noise reduction capabilities

# play the generated sound
play_sound(generated_wav)

# save the file
save_sound(generated_wav, filename="sample output", noise_reduction=True) # enable noise reduction

About

This Package is part of the Research topic "xxxxxxxx" conducted by xxxxx, xxxxxxxx. If you use this work (code, model or dataset),

Please cite us and star at: xxxxxxxxxxxxxxxxxxxxxx

License

MIT License