An OpenAI compatible transcriber using transformers and whisperx.

🎙️ Powerful GUI tool to transcribe and translate audio/video files using Whisper — fast, simple, and GPU-optimized.

A handy app that transcribes your voice into text amongst other useful utilities.

Youtube video subtitle generator from audio

🚀 Ferramenta CLI Open-Source em Python para transcrever vídeos locais e do YouTube usando Inteligência Artificial. Utiliza o motor faster-whisper para extrair a minutagem exata das falas de forma ultra rápida.

Extract vtt and srt subtitle using fast whisper

CLI to transcribe YouTube audio to clean JSON + SRT using local Whisper/whisper.cpp or cloud engines (Gemini/OpenAI/ Deepgram). Supports chapters, summaries, caching, and resilient retries.

A web API for speech-to-text (STT) and text-to-speech (TTS) that integrates with existing engines, supporting real-time audio streaming and modular engine selection.

AI Vtuber/Assistant for chatting and performing various commands

Extract text and transcribe audio from PowerPoint presentations, MP3, MP4 using OpenAI Whisper.

Amadeus AI: A modular, voice-enabled AI assistant featuring a hybrid architecture that combines local ML classifiers for rapid intent routing with Google Gemini for complex reasoning. Built with Python, FastAPI, and Docker.

AURALEX- FIR Generator and Legal Section Analyzer- AI-powered legal assistant that leverages Retrieval-Augmented Generation (RAG) to analyze user inputs and generate structured FIR reports. Integrated vector databases for efficient retrieval of relevant IPC/CrPC sections, combined with NLP techniques like named entity recognition and voice-to-text

Multilingual RAG Pipeline for Speech/Voice/Audio and Video Transcription

Dictation that works offline because your words are yours

Local CLI for benchmarking STT → TTS pipelines using Fast-Whisper and Piper

"Base de conhecimento para suporte técnico construída com Python, Flet e SQLite. Conta com armazenamento de imagens, busca instantânea, transcrição de voz e mensagens automáticas via atalhos de teclado."

🚄 This repository contains an NLP-powered system designed to process natural language travel requests (in French), extract departure/destination points and times, then generate optimal train itineraries via the Navitia API.

Audio-to-Lyrics & SRT Generator using FastWhisper and NLP models with Streamlit UI for easy transcription and subtitle creation.

macOS Voice Input Tool - One-Key Recording & One-Key Sending for Seamless Voice Input Experience

Offline subtitle generator for audio/video using faster-whisper and ffmpeg, with smart chunking, presets, and multi-format output (SRT/VTT/ASS/TXT/JSON).