vocalverse

This project provides functionalities for Text Translation, Speech Synthesis, and Audio Transcription service.

Features

Version - 1.0.0

• Translate text between different languages.
• Convert text to speech and play it.
• Convert text to speech and export it as an audio file.

Version - 1.1.1

• Transcribes audio file to text.
• Trims audio file efficiently.

Installation

pip install :

pip install vocalverse

if you are getting pip not found error try with pip3 (Latest Python Version 3+)

pip3 install vocalverse

git clone :

1. Clone the repository:

   git clone https://github.com/Vamshi0104/vocalverse.git
   

2. Install the required packages:

   pip install -r requirements.txt
   

Usage

Explore all the vocalverse capabilities :

Example for vocalverse CLI usage:

python3 vocalverse.py --help

python3 vocalverse.py --translate "Hello" "en" "tamil"

python3 vocalverse.py --tts "How are you??" "en"

python3 vocalverse.py --tts-file "How are you??" "en" "my_speech" "mp3"

python3 vocalverse.py --audio-to-text your_file_name.mp3   

python3 vocalverse.py --trim-audio source_file_name.mp3 dest_file_name.mp3 20 30  [trims audio file from 20 to 30 seconds) 

python3 vocalverse.py --trim-audio source_file_name . 20 30  [in this case dest_file_name would be trimmed_source_file_name as output]

python3 vocalverse.py --lang-dict

Note :

>> --translate for translating text to desired destination language from source language specified
>> --tts stands for text to speech
>> --tts-file for text to speech and export to a file
>> --audio-to-text for transcribing audio to text
>> --trim-audio for trimming audio from given start to end time efficiently

These are List of Languages supported for the toolkit :

Example for vocalverse Python function usage:

• Import vocalverse package

import vocalverse

• Calling this function - translates text to desired destination language from source language specified

translate_text(text, src_lang, dest_lang)

• Calling this function - converts text to speech given a destination language specified

text_to_speech(text, lang)

• Calling this function - converts text to speech given a destination language and exports audio to a filename and audio extension specified

text_to_speech_file_export(text, lang, filename, audio_file_extension)

• Calling this function - transcribes audio file to text specified audio_file_name in input

audio_to_text(audio_filename)

• Calling this function - trims audio file from specified start to end time(in seconds) [Note : dest_audio_filename can be '.' - to name it as trimmed_src_audio_filename]

trim_audio(src_audio_filename, dest_audio_filename, start_time, end_time)

>>> Stay tuned for more updates from vocalverse!!!