🗣️ Speech2Text with Whisper-1

A Streamlit web app that transcribes audio and video files using OpenAI's Whisper-1 model.
Simply upload a media file and get accurate, real-time text transcription.

---

🔗 Live App

👉 Try it on Streamlit

---

🎯 Features

• 🎧 Upload audio and video files (MP3, WAV, MP4, MOV, AVI)
• ⚡ Fast and accurate transcription using OpenAI Whisper-1
• 🗃️ Supports long-form content like interviews, podcasts, and lectures
• 🌐 Clean, responsive interface with instant output
• 🧠 Uses OpenAI’s advanced speech recognition model

---

📁 Supported File Formats

• .mp3, .wav (Audio)
• .mp4, .mov, .avi (Video)

---

🚀 Getting Started (Run Locally)

✅ Prerequisites

• Python 3.8+
• OpenAI API key

📦 Installation

pip install -r requirements.txt