A lightweight CLI tool to optimize audio and video files for AI Speech-to-Text transcription.
Project description
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.
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
pip install audiototext-optimizer
Note: You must have ffmpeg installed on your system.
Usage
Simply pass your audio or video file to the CLI:
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 for secure, privacy-first transcription.
Links
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file audiototext_optimizer-0.1.0.tar.gz.
File metadata
- Download URL: audiototext_optimizer-0.1.0.tar.gz
- Upload date:
- Size: 2.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2de11b6f14620b60b40e21485dff5f88878e3b0b82ff604740ab275203b80237
|
|
| MD5 |
4180fa2175cc967aa67ea4d24a94612b
|
|
| BLAKE2b-256 |
324659ded3c6b71f6bb267f71a5ad74121f497ad4991ecd5b5d9fb9a5fddec17
|
File details
Details for the file audiototext_optimizer-0.1.0-py3-none-any.whl.
File metadata
- Download URL: audiototext_optimizer-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2424bf3afeb9e3114275c629f40dd9b51cc5d3359d68b59b4874f0885cc20903
|
|
| MD5 |
94b09eda0a454445a77f3477502afa29
|
|
| BLAKE2b-256 |
3995620da35bebbe3f3cbd060c0ad4d96c94c53ce9f0cde527e3f891081bdd43
|
