---
title: Whisper Gradio Template
emoji: 🎙️
colorFrom: indigo
colorTo: green
sdk: gradio
sdk_version: 5.10.0
app_file: app.py
pinned: false
short_description: hf space gradio app to transcribe audio using whisper ai
---

# Whisper Gradio App

This Gradio app uses OpenAI's Whisper model to transcribe audio files into multiple formats:
- Plain text transcription
- SRT subtitle format
- Detailed JSON output with timestamps and metadata

## Usage
1. Upload an audio file (supports various formats)
2. Wait for the model to process the audio
3. Get the transcription in three different formats


Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference