Split an audiobook into chapters based on detected chapter heading via `whisper.cpp` AI model.

CLI and UI interface for OpenAI and Openrouter with stored prompts 🔮

gA easy to install/use speach recognition using a webUI with Gradio and faster wisper models (guillaumekln/faster-whisper-large-v2 Is the default)

Web App to automatic creation of a text publication based on a youtube video

A professional RESTful API system that converts audio files to text using OpenAI Whisper.

transcribing english language video files using OpenAI wisper and argos translate offline and adding suntitile to the output .mkv file

Linuxで音声入力するためのスクリプト。

a8项目 开源项目 ai开发中 语音文字工具

A powerful tool for auto-generating multilingual subtitles. Supports Whisper-based transcription and translation. Customizes caption style, layout, and RTL languages. Works with YouTube links or local video files in a full pipeline.

Turn any audio file into a clean, timestamped transcript — fully offline using OpenAI Whisper. No API key required.

This project focuses on enhancing video summarization by integrating both textual and visual information.

This project allows you to transcribe audio files from a given URL, detect the language of the transcription, and save the transcription to a text file.

AI Assistant bot that helps people to do actions with comunications.

Generate accurate, meaningful chapter markers, titles, and descriptions.

Misaki is a lightweight offline desktop voice assistant built in Python that runs smoothly even on low-end laptops.