gabriele-mastrapasqua / qwen3-tts

What it does

• Pure C, minimal dependencies. Only requires a C compiler and BLAS. No Python runtime needed.
• Runs on macOS, Linux and Windows/WSL2 (ARM/x86). the hot matvec/attention kernels have NEON+SDOT (ARM), AVX2 and AVX-512/VNNI/BF16 (x86) twins with a scalar fallback + runtime ISA guard, and decode threading runs on a cross-OS pool (GCD on
• Optional GPU backends (opt-in). Apple Metal (make metal) and NVIDIA CUDA (make cuda) run the whole fused pipeline resident on the GPU (0.28 RTF for 0.6B on an M4; ~0.44 for 1.7B on a mainstream NVIDIA GPU), plus server request-batching for
• Both model sizes. Automatically detects 0.6B or 1.7B from weight files.
• 9 preset voices. ryan, vivian, serena, aiden, eric, dylan, uncle_fu, ono_anna, sohee.