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

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.

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.

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

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

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.

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.

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.

🎙️ 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.

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.

Real-time Urdu-to-English voice interpreter for macOS meetings

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

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

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

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

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

Lipi is a lightweight, local-first desktop speech-to-text and voice note application. Built with Tauri v2, Rust, and React 19, it lets you record audio, transcribe speech with OpenAI Whisper or any OpenAI-compatible local/remote endpoint, and manage your notes seamlessly.

an extremely fast qwen3-asr-0.6B model on CPU for hermes agents and others.

Local-first voice notes for Windows. Press a hotkey, speak, release. Get a transcript — your way.