vijayengineer / PDFTextSpeechConverter

Converts scanned documents and ordinary documents into speech mp3 using Amazon Polly

Repository from Github https://github.comvijayengineer/PDFTextSpeechConverterRepository from Github https://github.comvijayengineer/PDFTextSpeechConverter

PDFTextSpeechConverter

Converts scanned documents and ordinary documents into text. Synthesizes speech as mp3 using Amazon Polly

Pre-requisites: 1.Setup amazon credentials files and install requirements. 2. Ensure Amazon polly works by checking aws configure

Screenshot

Server.py: Django file which uses Post to render the index.html template regularpdftext.py: Uses pdfminer to scan pdf files to text scannedpdftext.py: Uses tesseract to scan pdf files to text

Polly_synth_speech.py: Converts text file to mp3 using the Polly "Salli" speaker Converted speech files are stored in ConvertedSpeech folder

Test: Run server.py and check with the provided sample pdf Speech sample is provided as a test example

About

Converts scanned documents and ordinary documents into speech mp3 using Amazon Polly


Languages

Language:Python 85.5%Language:HTML 14.5%