README.md

metadata

title: FardaVoice
emoji: 🎙️
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false

🎙️ FardaVoice

FardaVoice is an experimental acting-based Text-to-Speech Space.

This project focuses on:

• 🎭 Acting-style prompting (emotion, tone, performance)
• 📝 Long free-form prompts (no censorship)
• 🎬 Voice performance like a dubbing actor, not a robotic TTS
• ⚙️ CPU-friendly architecture (no GPU required at early stages)

---

🧠 How it works (Current Stage)

At this stage, the Space provides:

• One Acting Prompt textbox (emotion + performance)
• One Text textbox (the script to be acted)
• A basic processing skeleton (no TTS engine yet)

This is the foundation for future stages:

• Multi-emotion within a single text
• Scene-based acting
• Voice reference & cloning
• Advanced emotion parsing

---

🚧 Status

This Space is currently in Skeleton / Foundation Stage.
Core UI and architecture are being stabilized before adding TTS engines.

---

👤 Author

Created by FardaTech
Built with ❤️ using Gradio and Hugging Face Spaces