iohann.s.titov@gmail.com Ivan S. Titov Build the NVIDIA CUDA backend (requires CUDA Toolkit; nvcc is pinned to gcc-15 on this host) Build the example CLI tools that record/play audio (portaudio is vendored + statically linked by upstream cmake) Build and install the Python bindings (pybind11) into site-packages Build text-to-speech support (pulls vendored espeak-ng-for-piper at build time) Build the WebSocket server and client examples sherpa-onnx is a speech-stack toolkit from the k2-fsa project: speech-to-text, text-to-speech, speaker diarization, voice activity detection, source separation, and keyword spotting, all running on ONNX Runtime (no PyTorch dependency). Source build against system sci-libs/onnxruntime. For the prebuilt -bin alternative (faster install, ships upstream's manylinux wheels) see sci-ml/sherpa-onnx-bin. The CMake build vendors a dozen small deps (eigen, asio, cargs, json, kaldi-{decoder,native-fbank,fst}, openfst, kissfft, simple-sentencepiece, hclust-cpp, optionally espeak-ng + piper-phonemize + portaudio + websocketpp + pybind11) via FetchContent. The ebuild pre-fetches them all via SRC_URI and stages into ${S} for the cmake fallback paths; no network access during build. Runtime model files for each task (ASR, diarization, TTS, etc.) live upstream — see https://k2-fsa.github.io/sherpa/onnx/pretrained_models/ k2-fsa/sherpa-onnx libeigen/eigen https://github.com/k2-fsa/sherpa-onnx/issues