Skip to content

Latest commit

 

History

History
118 lines (86 loc) · 2.88 KB

README.md

File metadata and controls

118 lines (86 loc) · 2.88 KB

AudioTextPro logo

Python AudioTextPro

Convert audio to text accurately in real-time using our advanced AI speech recognition technology.

Overview 📖

AudioTextPro is a Python module designed to interact with the AssemblyAI API to transcribe audio files. It provides a simple and efficient way to convert speech into text using AssemblyAI's powerful transcription services.

Features ✨

  • Uploads audio files to AssemblyAI.
  • Requests transcripts of uploaded audio files.
  • Processes and stores the resulting transcripts.
  • Simple API interaction through Python functions.
  • Extensible for future additions, such as more complex processing of transcripts.

Requirements 📋

  • Python 3.9 or higher
  • The requests, and python-dotenv packages
  • An AssemblyAI API key (get one here)

Installation 🛠

  1. Install the required packages:
pip install requests python-dotenv
  1. Clone the audiotextpro repository:
git clone https://github.com/sebastienrousseau/audiotextpro.git
  1. Add your OpenAI API key to a .env file in the project directory:
# API_TOKEN is used to authenticate with the AssemblyAI API.
# Replace with your actual API token from AssemblyAI.
API_TOKEN = ''

# FILENAME should be the path to the audio file you wish to transcribe.
# Replace with the path to your actual file.
FILENAME = ''

# TIMEOUT is the number of seconds to wait for the transcription to complete.
# Replace with the number of seconds you wish to wait.
TIMEOUT=""

Usage 🚀

Command Line Interface

To use AudioTextPro, navigate to the project directory in your terminal and run the following command:

python3 -m audiotextpro

Ensure your audio file is accessible from the project and that the API key is valid to avoid any request issues.

File Structure 📁

.
├── LICENSE-APACHE
├── LICENSE-MIT
├── MANIFEST.in
├── Makefile
├── README.md
├── audiotextpro
│   ├── __init__.py
│   ├── __main__.py
│   ├── api.py
│   ├── file.py
│   ├── transcript.json
│   ├── transcript.txt
│   ├── transcript_processor.py
│   └── utils.py
├── pyproject.toml
├── requirements.txt
├── samples
│   └── call_from_a_customer.mp3
├── setup.cfg
├── setup.py
└── transcript.json

3 directories, 19 files

License 📜

The project is licensed under the terms of both the MIT license and the Apache License (Version 2.0).