long-audio-whisper

A library to bypass OpenAI Whisper's 25MB limit by chunking long audio files, with LLM-powered text enhancement and precise timestamp reconstruction for SRT/VTT formats.

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install long-audio-whisper

Dependencies

Releases

Version Released Bullseye
Python 3.9
Bookworm
Python 3.11
Trixie
Python 3.13
Files
1.0.0 2025-08-21      

Issues with this package?

Page last updated 2025-11-13 05:06:52 UTC