Create README.md

README.md

@@ -1,13 +1,34 @@
 ---
-title: Testovich
-emoji: ⚡
-colorFrom: green
-colorTo: indigo
+title: Audio-Omni V2A ZeroGPU
+emoji: "🎛️"
+colorFrom: indigo
+colorTo: blue
 sdk: gradio
-sdk_version: 6.12.0
-python_version: '3.12'
+sdk_version: 5.50.0
 app_file: app.py
+python_version: "3.11"
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Audio-Omni V2A on ZeroGPU
+
+This Space runs **Video-to-Audio (V2A)** only, based on
+[`ZeyueT/Audio-Omni`](https://github.com/ZeyueT/Audio-Omni).
+
+## What it does
+
+- Input: video file + optional text prompt
+- Output: generated audio (`.wav`)
+- Task used internally: `model.generate("V2A", prompt=..., video_path=...)`
+
+## Environment variables (optional)
+
+- `AUDIO_OMNI_REPO_ID` (default: `HKUSTAudio/Audio-Omni`)
+- `AUDIO_OMNI_CACHE_DIR` (default: `./model`)
+- `GPU_DURATION_SECONDS` (default: `240`)
+
+## Notes
+
+- First run can be slow due to model download and initialization.
+- This demo focuses only on V2A.
+- Model weights license: CC BY-NC 4.0 (research use).