Update README.md
Browse files
README.md
CHANGED
|
@@ -1,37 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
title: AI Voiceover
|
| 3 |
emoji: 🧠
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
-
sdk:
|
| 7 |
-
sdk_version: 1.44.1
|
| 8 |
-
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# 🧠 AI Voiceover V2
|
| 13 |
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
---
|
| 17 |
-
|
| 18 |
-
### ✨ Features:
|
| 19 |
-
- Upload a short MP4/AVI/MOV video
|
| 20 |
-
- Transcribe existing voice using Whisper
|
| 21 |
-
- Input your own replacement narration
|
| 22 |
-
- Generate AI voice using Coqui TTS
|
| 23 |
-
- Mix it with original audio (background audio stays!)
|
| 24 |
-
- Download the final enhanced video
|
| 25 |
-
|
| 26 |
-
---
|
| 27 |
-
|
| 28 |
-
### 🛠 Powered by:
|
| 29 |
-
- [OpenAI Whisper](https://github.com/openai/whisper) for speech-to-text
|
| 30 |
-
- [Coqui TTS](https://github.com/coqui-ai/TTS) for AI voice generation
|
| 31 |
-
- [MoviePy](https://zulko.github.io/moviepy/) for video processing
|
| 32 |
-
- [TorchAudio](https://pytorch.org/audio/stable/index.html) for mixing
|
| 33 |
-
|
| 34 |
-
---
|
| 35 |
-
|
| 36 |
-
🚀 Built with Streamlit on Hugging Face Spaces
|
| 37 |
-
👨💻 Perfect for content creators, educators, and developers
|
|
|
|
| 1 |
---
|
| 2 |
+
title: AI Voiceover V2 (Docker)
|
| 3 |
emoji: 🧠
|
| 4 |
+
colorFrom: gray
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: docker
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# 🧠 AI Voiceover V2 — Replace One Speaker Only
|
| 11 |
|
| 12 |
+
Runs Whisper + Coqui TTS + audio mixing inside a Docker container for full compatibility and reliability.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|