Metadata-Version: 2.4
Name: audiototext-optimizer
Version: 0.1.0
Summary: A lightweight CLI tool to optimize audio and video files for AI Speech-to-Text transcription.
Author-email: FreeAudioToText Developer <support@freeaudiototext.com>
Project-URL: Homepage, https://freeaudiototext.com
Project-URL: Documentation, https://freeaudiototext.com
Project-URL: Repository, https://github.com/double2dev/audiototext
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Multimedia :: Sound/Audio :: Conversion
Requires-Python: >=3.7
Description-Content-Type: text/markdown

# AudioToText Optimizer

A lightweight, local command-line tool designed to prepare and compress audio/video files for fast, highly accurate AI Speech-to-Text transcription. 

This tool is created and maintained by [FreeAudioToText.com](https://freeaudiototext.com).

## Why use this tool?

Most modern AI transcription models (like Whisper) downsample audio to 16kHz mono before processing. Uploading a massive 4K video file or a 320kbps stereo MP3 to a transcription service just wastes bandwidth and upload time.

`audiototext-optimizer` uses `ffmpeg` locally to perfectly format your media for transcription (16kHz, mono, 64k bitrate), reducing file sizes by up to 90% without losing any vocal clarity.

## Installation

```bash
pip install audiototext-optimizer
```

*Note: You must have [ffmpeg](https://ffmpeg.org/) installed on your system.*

## Usage

Simply pass your audio or video file to the CLI:

```bash
audiototext-optimize my_podcast.wav
```

This will automatically create a highly compressed `my_podcast_optimized.mp3` file.

You can then upload this optimized file directly to [FreeAudioToText](https://freeaudiototext.com) for secure, privacy-first transcription.

## Links
- [Official Website](https://freeaudiototext.com)
- [Terms of Service](https://freeaudiototext.com/terms)
- [Privacy Policy](https://freeaudiototext.com/privacy)
- [GitHub Repository](https://github.com/double2dev/audiototext)
