Fix: add phonemizer-fork

Fix: add libgomp1 for onnxruntime

Test: minimal kokoro-onnx install

Revert to working Piper version

Switch to Gradio SDK

Restore Kokoro files

Test minimal build

Use full python image

Simplify Dockerfile

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

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

Switch to Piper TTS - lightweight, fast, multilingual

Replace RVC WebUI with Matcha TTS API - faster TTS solution

Update Dockerfile

Upload Dockerfile with huggingface_hub

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Create Dockerfile

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

Ultra-minimal: pitch+formant shift only (librosa+parselmouth), ~10 deps

Split torch install first to avoid memory peak

Minimal deps + only essential RVC modules

Use pytorch/pytorch:2.4.1-cpu base image to avoid torch install

Split pip install into batches to avoid memory issues

Bundle RVC source code to avoid git clone at build; simplify requirements

Fix Dockerfile: add retry logic for apt-get and pip install

Convert Blender Space to Elderly Voice Conversion Space using RVC

Force rebuild

Dockerfile: python:3.10-slim base

Dockerfile: add set -ex debug output

Dockerfile: python:3.11 base, clean

Dockerfile: add debug output

Dockerfile: use linuxserver/blender:5.2.1 base

Dockerfile: use ghcr.io/blender/blender:4.2 base

Dockerfile: python:3.11 base, cleaned up

Fix Dockerfile: add explicit Debian bookworm sources

Fix Dockerfile: use ubuntu:22.04 base, runtime chown

Fix Dockerfile: move chown to runtime CMD

Deploy Blender Headless API

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

Move gradio pins to requirements.txt, simplify Dockerfile

Docker SDK with pinned Gradio 4.44.1 in Dockerfile

Switch to Gradio SDK (no Dockerfile needed)