-
kizuna-voice-designer ★ PINNED
Text prompt-based voice quality designer using FlowMatching + GPT-SoVITS
Python ★ 5 3mo agoExplain → -
kizuna-voice-studio ★ PINNED
Preview-first voice studio for Kizuna Voice Designer, Qwen Voice Designer, MioTTS, Piper, and Style-Bert-VITS2
Python ★ 75 2mo agoExplain → -
Irodori-TTS-Lite
Int4-quantized inference runtime for Faster-Irodori-TTS2 voice-design DiT. ~1GB VRAM end-to-end.
Python ★ 75 26d agoExplain → -
Flux2-klein-Lite
Int4-quantized FLUX.2-klein inference runtime (GemLite / fused Triton / eager backends)
Python ★ 18 26d agoExplain → -
omnivoice-kit
No description.
Python ★ 14 2mo agoExplain → -
piper-plus-swift
Swift package for Piper-based on-device TTS on iOS with swappable model integration and demo app
C++ ★ 2 3mo agoExplain → -
Command-A-Plus-Lite
Run the 218B Command-A-Plus MoE on a single 24GB GPU — int2 CPU-offloaded experts + int4 resident weights.
Python ★ 1 28d agoExplain → -
OneCompression ⑂
Python package for LLM compression
★ 1 26d agoExplain → -
onecompression-runtime
Shared int4 inference runtime extracted from OneCompression per-model runtimes (GPTQ/RTN packed-int4 GEMM kernels + generic diffusion loader).
Python ★ 0 23d agoExplain → -
Irodori-TTS ⑂
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
★ 0 1mo agoExplain → -
OmniVoice ⑂
High-Quality Voice Cloning TTS for 600+ Languages
★ 0 2mo agoExplain → -
.github
GitHub organization profile for Kizuna Intelligence
★ 0 3mo agoExplain →
No repos match these filters.