speech-to-text-transcription

A fully local and private Speech-To-Text app, offering multiple model backends, diarization & calendar mode - Available for Windows, macOS & Linux

Udio Ai Studio

This repository contains a web application for multi-lingual transcription using OpenAI's Whisper Automatic Speech Recognition (ASR) model. Users can upload audio files in WAV, MP3, or M4A formats and get transcriptions in various languages. The application is designed with accessibility and data privacy in mind.

Turn speech into text. Free, open source alternative to Wispr Flow.

Real-time voice to text for Windows. Transcribe microphone input to text in any app. Free offline speech recognition tool for Windows 10/11

This project automates audio processing by removing silence, transcribing speech to text, and storing the output in an SQLite database. It supports multiple audio formats and leverages Google Speech Recognition for high accuracy.

Open-source AI-powered desktop transcription app for macOS. Generate accurate word-level transcripts from audio and video completely offline.

Successfully developed an interview preparation guide using Langchain which can effectively guide users in their interview preparation process and job search journeys by providing valuable insights and feedback regarding their performance. It generates a comprehensive list of questions pertaining to a user query as well.

🎙️ Open-source Speech-to-Text GUI powered by OpenAI Whisper. Convert audio and video files (MP4, MP3, WAV, MOV, AVI, MKV, M4A & FLAC) into text transcripts, SRT/VTT subtitles, JSON & TSV with batch processing, GPU acceleration, and multilingual support.

Herramienta de código abierto que transcribe el audio de videos .mp4 a texto usando ffmpeg y modelos como Whisper, ideal para automatizar la extracción de contenido hablado de forma local y personalizable.

Speech-to-Text dictation for Windows with Hotkey. Whisper.cpp running on your CPU, paste anywhere. Local. Privacy. First. No cloud, no account, no telemetry.

Offline desktop speech-to-text with OpenAI Whisper. Transcribe and translate audio locally. No account, no upload.

Simple local voice-to-text dictation for Windows using OpenAI's Whisper.

Win+H-style offline speech-to-text for Fedora GNOME Wayland using Faster-Whisper.

CLI that turns a YouTube URL into a text transcript: yt-dlp for the audio, Whisper for the transcription, running 100% locally with GPU support.

Backend FastAPI untuk transkripsi rapat real-time, speaker diarization, dan analisis AI

Open Video Transcribe - Open-source video transcription tool that emphasizes the primary use case: transcribing video files to text with support for multiple model types.

AI-powered video analysis assistant for transcription, summarization, semantic search, and conversational Q&A using RAG.

Offline, privacy-first voice dictation for Windows. Global hotkey → on-device Whisper transcription → clipboard, with zero cloud calls. Rust (Tauri) + Python (FastAPI) + React.

Windows meeting recorder with live Whisper transcription, click-to-seek transcripts, AI summaries and chat (bundled Llama 3.2), uploads, and export to 9 formats — all local, all offline.