Releases: 0xShug0/audio.cpp
Release list
audio.cpp Windows prebuilt binaries v0.3.1
These Windows prebuilt packages are for audio.cpp 0.3, built from commit e12fc743ccb294753dcdced0be7778c76a178f95 on main.
What's New
- Adds Windows prebuilt CPU and CUDA packages for audio.cpp 0.3.
- Uses deployment builds, so package specs are compiled into
audiocpp_cli.exeandaudiocpp_server.exefor more portable GGUF and safetensors loading. - Adds new TTS model families from the 0.3 release wave, including IndexTTS2, Irodori-TTS, MOSS-TTS-Nano, MOSS-TTS-Local, and Supertonic 3.
- Adds GGUF support for several refactored model families. Based on the current
docs/gguf.mdmatrix:- 16-bit GGUF path-test coverage passes for
higgs_audio_stt,irodori_tts,moss_tts_local,moss_tts_nano,nemotron_asr,qwen3_asr,qwen3_forced_aligner,qwen3_ttscustom voice,qwen3_ttsvoice design, andvibevoice_asr. - 16-bit GGUF is also runnable with known drift for
index_tts2;supertoniccurrently uses theorigGGUF path instead of the 16-bit column. - Align Qwen3-TTS config with Python.
- 16-bit GGUF path-test coverage passes for
Packages
CPU packages are self-contained:
audiocpp-windows-cpu-fast.zipaudiocpp-windows-cpu-balance.zipaudiocpp-windows-cpu-portable.zip
CUDA packages are split into one shared runtime package plus one profile package:
audiocpp-windows-cuda-runtime.zipaudiocpp-windows-cuda-fast.zipaudiocpp-windows-cuda-balance.zipaudiocpp-windows-cuda-portable.zip
The CUDA runtime package contains the large CUDA DLLs shared by all CUDA profiles. Download it once, then pair it with whichever CUDA profile package you want to use.
Which Package Should I Download?
Use a CUDA package if you have a supported NVIDIA GPU. CUDA profile packages include both CUDA and CPU backend support, so they can run with either --backend cuda or --backend cpu once the CUDA runtime DLLs are available.
Use a CPU package if you do not have a supported NVIDIA GPU or only want CPU inference.
For most users:
- NVIDIA GPU: download
audiocpp-windows-cuda-runtime.zipandaudiocpp-windows-cuda-balance.zip - CPU only: download
audiocpp-windows-cpu-balance.zip
CPU Architecture Profiles
The package names use three CPU compatibility profiles:
| Profile | CPU build setting | Best for | Tradeoff |
|---|---|---|---|
fast |
Native CPU optimization | Newer high-end x86-64 CPUs that support the same instruction families used by the package | Fastest CPU path, but least portable. If your CPU is older or missing newer SIMD instructions, use balance or portable. |
balance |
AVX2 CPU kernels, native CPU optimization off | Most modern x86-64 Windows PCs with AVX2 support | Recommended default. More portable than fast, faster than portable, and avoids AVX512/AVX-VNNI requirements. |
portable |
Baseline CPU kernels, native CPU optimization off, llamafile SGEMM off | Older or unknown x86-64 Windows CPUs | Broadest compatibility, but slowest. Avoids AVX, AVX2, AVX512, AVX-VNNI, and llamafile SGEMM. |
The CUDA packages still include a CPU backend, so the same CPU profile applies when a CUDA package is run with --backend cpu.
CUDA Package Requirements
- 64-bit Windows
- NVIDIA GPU with compute capability 7.5 or newer
- NVIDIA driver 580 or newer
- Model files downloaded separately
The CUDA Toolkit and Visual Studio Build Tools are not required to run the CUDA packages. The required CUDA runtime DLLs are provided in audiocpp-windows-cuda-runtime.zip.
The CUDA packages are intended for RTX 20/30/40/50 series GPUs and similar NVIDIA datacenter GPUs. Older GPUs such as GTX 10-series Pascal cards or V100-class Volta cards are not covered by the CUDA 13 package; use a CPU package or build a separate package with an older CUDA Toolkit if those GPUs must be supported.
Quick Start
CPU users: unzip one CPU package, then run:
.\audiocpp_cli.exe --helpCUDA users: unzip audiocpp-windows-cuda-runtime.zip and one CUDA profile package into the same directory, then run:
.\audiocpp_cli.exe --helpCUDA example:
.\audiocpp_cli.exe --backend cuda --task tts --family <family> --model C:\path\to\model [options]CPU example:
.\audiocpp_cli.exe --backend cpu --task tts --family <family> --model C:\path\to\model [options]Server:
.\audiocpp_server.exe --config C:\path\to\server.jsonNotes
- Models are not bundled.
- For CPU packages, keep the bundled DLL files next to the
.exefiles. - For CUDA packages, keep the CUDA runtime DLLs from
audiocpp-windows-cuda-runtime.zipnext to the.exefiles, or put that runtime directory onPATH. - If CUDA startup fails, update the NVIDIA driver first.
audio.cpp Windows prebuilt binaries v0.2.0
audio.cpp Windows Prebuilt Packages
These Windows prebuilt packages are based on commit cd7e40411adbbbf4cc722981a5cf63f79e3a8ff9.
Packages
audiocpp-windows-cpu-fast.zipaudiocpp-windows-cpu-balance.zipaudiocpp-windows-cpu-portable.zipaudiocpp-windows-cuda-fast.zipaudiocpp-windows-cuda-balance.zipaudiocpp-windows-cuda-portable.zip
Which Package Should I Download?
Use a CUDA package if you have a supported NVIDIA GPU. The CUDA packages include both CUDA and CPU backend support, so they can run with either --backend cuda or --backend cpu.
Use a CPU package if you do not have a supported NVIDIA GPU or only want CPU inference.
For most users:
- NVIDIA GPU: download
audiocpp-windows-cuda-balance.zip - CPU only: download
audiocpp-windows-cpu-balance.zip
CPU Architecture Profiles
The package names use three CPU compatibility profiles:
| Profile | CPU build setting | Best for | Tradeoff |
|---|---|---|---|
fast |
Native CPU optimization | Newer high-end x86-64 CPUs that support the same instruction families used by the package | Fastest CPU path, but least portable. If your CPU is older or missing newer SIMD instructions, use balance or portable. |
balance |
AVX2 CPU kernels, native CPU optimization off | Most modern x86-64 Windows PCs with AVX2 support | Recommended default. More portable than fast, faster than portable, and avoids AVX512/AVX-VNNI requirements. |
portable |
Baseline CPU kernels, native CPU optimization off, llamafile SGEMM off | Older or unknown x86-64 Windows CPUs | Broadest compatibility, but slowest. Avoids AVX, AVX2, AVX512, AVX-VNNI, and llamafile SGEMM. |
The CUDA packages still include a CPU backend, so the same CPU profile applies when a CUDA package is run with --backend cpu.
CUDA Package Requirements
- 64-bit Windows
- NVIDIA GPU with compute capability 7.5 or newer
- NVIDIA driver 580 or newer
- Model files downloaded separately
The CUDA Toolkit and Visual Studio Build Tools are not required to run the CUDA packages. The required CUDA runtime DLLs are bundled next to the executables.
The CUDA packages are intended for RTX 20/30/40/50 series GPUs and similar NVIDIA datacenter GPUs. Older GPUs such as GTX 10-series Pascal cards or V100-class Volta cards are not covered by the CUDA 13 package; use a CPU package or build a separate package with an older CUDA Toolkit if those GPUs must be supported.
Quick Start
Unzip one package, then run:
.\audiocpp_cli.exe --helpCUDA example:
.\audiocpp_cli.exe --backend cuda --task tts --family <family> --model C:\path\to\model [options]CPU example:
.\audiocpp_cli.exe --backend cpu --task tts --family <family> --model C:\path\to\model [options]Server:
.\audiocpp_server.exe --config C:\path\to\server.jsonNotes
- Models are not bundled.
- Keep the DLL files next to the
.exefiles. - If CUDA startup fails, update the NVIDIA driver first.
audio.cpp Windows prebuilt binaries
audio.cpp Windows Prebuilt Packages
These Windows prebuilt packages are based on commit 11d5057ca35709e36643125066259ba73d0ed42f.
Packages
audiocpp-windows-cpu-fast.zipaudiocpp-windows-cpu-balance.zipaudiocpp-windows-cpu-portable.zipaudiocpp-windows-cuda-fast.zipaudiocpp-windows-cuda-balance.zipaudiocpp-windows-cuda-portable.zip
Which Package Should I Download?
Use a CUDA package if you have a supported NVIDIA GPU. The CUDA packages include both CUDA and CPU backend support, so they can run with either --backend cuda or --backend cpu.
Use a CPU package if you do not have a supported NVIDIA GPU or only want CPU inference.
For most users:
- NVIDIA GPU: download
audiocpp-windows-cuda-balance.zip - CPU only: download
audiocpp-windows-cpu-balance.zip
CPU Architecture Profiles
The package names use three CPU compatibility profiles:
| Profile | CPU build setting | Best for | Tradeoff |
|---|---|---|---|
fast |
Native CPU optimization | Newer high-end x86-64 CPUs that support the same instruction families used by the package | Fastest CPU path, but least portable. If your CPU is older or missing newer SIMD instructions, use balance or portable. |
balance |
AVX2 CPU kernels, native CPU optimization off | Most modern x86-64 Windows PCs with AVX2 support | Recommended default. More portable than fast, faster than portable, and avoids AVX512/AVX-VNNI requirements. |
portable |
Baseline CPU kernels, native CPU optimization off, llamafile SGEMM off | Older or unknown x86-64 Windows CPUs | Broadest compatibility, but slowest. Avoids AVX, AVX2, AVX512, AVX-VNNI, and llamafile SGEMM. |
The CUDA packages still include a CPU backend, so the same CPU profile applies when a CUDA package is run with --backend cpu.
CUDA Package Requirements
- 64-bit Windows
- NVIDIA GPU with compute capability 7.5 or newer
- NVIDIA driver 580 or newer
- Model files downloaded separately
The CUDA Toolkit and Visual Studio Build Tools are not required to run the CUDA packages. The required CUDA runtime DLLs are bundled next to the executables.
The CUDA packages are intended for RTX 20/30/40/50 series GPUs and similar NVIDIA datacenter GPUs. Older GPUs such as GTX 10-series Pascal cards or V100-class Volta cards are not covered by the CUDA 13 package; use a CPU package or build a separate package with an older CUDA Toolkit if those GPUs must be supported.
Quick Start
Unzip one package, then run:
.\audiocpp_cli.exe --helpCUDA example:
.\audiocpp_cli.exe --backend cuda --task tts --family <family> --model C:\path\to\model [options]CPU example:
.\audiocpp_cli.exe --backend cpu --task tts --family <family> --model C:\path\to\model [options]Server:
.\audiocpp_server.exe --config C:\path\to\server.jsonNotes
- Models are not bundled.
- Keep the DLL files next to the
.exefiles. - If CUDA startup fails, update the NVIDIA driver first.