Switch to Gradio SDK

Replace RVC WebUI with Matcha TTS API - faster TTS solution

Update app.py

Add model verification with torch.load to catch format issues

Add retry logic and verification for model downloads

Add auto-download of OldChineseMan RVC model from model repo

Upload app.py with huggingface_hub

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Upload 4 files

Delete app.py

Use user's OpenVoice V2 elderly voice conversion (Gradio SDK)

Convert Blender Space to Elderly Voice Conversion Space using RVC

Deploy Blender Headless API

Fix: use 'prompt' not 'initial_prompt' for Whisper

Add initial_prompt to Whisper for domain-specific terms

Upgrade ASR to whisper-large-v3-turbo for better accuracy

Fix make_dub filter_complex: don't include silent base as filter, only delay TTS segments

Fix: use soundfile for audio I/O (avoid torchcodec), add attention_mask for TTS, add soundfile dep

Fix Gradio Video type parameter for Gradio 5.x

Replace Comic-Gen with Chinese→Malay Video Dubber (CPU Basic)

Update app.py

Update app.py

Update app.py

Fix: Remove gr.Examples to avoid Gradio 5.0.0 JSON schema bug

Fix: Replace gr.Number with gr.Slider to avoid Gradio 5.0.0 JSON schema bug

Fix: Use correct model ID Laxhar/noobai-XL-1.1

Fix: requirements.txt index-url, Dockerfile single pip install, app.py fp16 for cpu-basic

Upload app.py with huggingface_hub

Delete app.py with huggingface_hub

Upload app.py with huggingface_hub

Delete app.py

Upload 3 files

Delete app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Fix build: upgrade pip toolchain and loosen whisper version

Create app.py