Fix: add phonemizer-fork

Fix: add libgomp1 for onnxruntime

Update main.py for Kokoro

Test: minimal kokoro-onnx install

Test: add kokoro-onnx back

Test: onnxruntime only

Test: older onnxruntime

Test: kokoro-onnx deps only

Revert to working Piper version

Switch to Gradio SDK

Restore Kokoro files

Test minimal build

Use full python image

Simplify Dockerfile

Force rebuild

Replace Piper with Kokoro 82M TTS - higher quality CPU TTS

Fix Piper 1.2+ synthesize API: handle single-speaker models (no sid input)

Fix Piper 1.2+ synthesize API: use wave.open with BytesIO buffer

Fix Piper 1.2+ synthesize API: pass wav_file BytesIO buffer

Piper TTS: runtime model download, no build-time network

Switch to Piper TTS - lightweight, fast, multilingual

Fix matcha-tts version to 0.0.7.2 (0.1.0 doesn't exist)

Replace RVC WebUI with Matcha TTS API - faster TTS solution

Update app.py

Update Dockerfile

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 Dockerfile with huggingface_hub

Upload requirements.txt with huggingface_hub

Upload app.py with huggingface_hub

Update app.py

Update README.md

Update app.py

Update Dockerfile

Update Dockerfile

Update app.py

Update .gitignore

Update app.py

Update Dockerfile

Update app.py

Update app.py

Update Dockerfile

Update app.py

Update app.py

Update Dockerfile

Update requirements.txt

Update Dockerfile

Update requirements.txt

Update Dockerfile