Hugging Face's logo

Spaces:
dooyum
/
AI_Video_Dubber
Runtime error

App Files Community
AI_Video_Dubber / README.md
dooyum's picture
dooyum
Update README.md
9fdd754 verified
preview code
|
Raw
History Blame Contribute Delete
1.18 kB

A newer version of the Gradio SDK is available: 6.27.0

Upgrade
metadata 
title: AI Video Dubber
emoji: 📚
colorFrom: red
colorTo: green
sdk: gradio
sdk_version: 5.42.0
app_file: app.py
pinned: false

🎬 AI Video Dubber

AI-powered app to dub English videos into multiple languages with synchronized speech and subtitles.

✨ Features

  • Upload any English video.
  • Choose a target language and voice gender.
  • Translates speech using OpenAI GPT.
  • Generates natural-sounding speech with Azure Neural TTS.
  • Produces synced subtitles in .srt format.
  • Works with multiple languages:
    • Japanese
    • Italian
    • French
    • German
    • Dutch
    • Swedish
    • Spanish
    • Polish
    • Arabic

🚀 How It Works

  1. Upload video → Extract audio.
  2. Transcribe → Using OpenAI Whisper.
  3. Translate → Using GPT-4o-mini.
  4. Synthesize voice → Using Azure Neural TTS.
  5. Merge audio + video → Output dubbed video.
  6. Generate subtitles → .srt file.

🛠 Requirements

  • Hugging Face Space with Gradio and Python.
  • API Keys:
    • OPENAI_API_KEY
    • AZURE_KEY
    • AZURE_REGION

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