voice-cat/third_party

third_party/ — vendored dependencies

Dependencies that are not consumed through vcpkg live here, copied verbatim into the tree. Everything here is permissively licensed (no GPL/LGPL) per the house rule in docs/tech-stack.md §5.

rnnoise/

Real-time speech noise suppression (the DSP backend behind ApmProcessor — see docs/voice.md §10–11). Used by the receive-side per-stream NR (RemoteStream::recv_ns) and the send-side mic NR (vc_client::mic_ns_).

• Upstream: https://github.com/xiph/rnnoise
• Vendored at commit: 70f1d256acd4b34a572f999a05c87bf00b67730d
• License: BSD-3-Clause (code, see rnnoise/COPYING) + CC0-1.0 (model weights).
• Why vendored, not vcpkg: the vcpkg rnnoise port is marked !windows !arm, i.e. unavailable on our primary targets (Windows MinGW, Apple Silicon, iOS). RNNoise is small, self-contained C99 with no dependencies, so we vendor it directly.

What was copied / changed

• Only the library sources + headers (src/*.c, src/*.h, src/x86/*.h, include/). The training/feature-dump tools (dump_features.c, write_weights.c, the src/x86/*.c RTCD kernels), build scaffolding (autotools, Meson) and torch/ training/ dirs are omitted.
• src/rnnoise_data.c is the shrunk model: upstream's scripts/shrink_model.sh strips the #ifndef DISABLE_DEBUG_FLOAT float-weight duplicates, taking the default model from ~78 MB to ~11.7 MB. We build with -DDISABLE_DEBUG_FLOAT so only the int8-quantized weights are used — this is exactly how upstream's default (non-debug) build behaves. The model is the built-in default loaded by rnnoise_create(NULL); there is no runtime model file.

Build

Built as a standalone static lib rnnoise in core/CMakeLists.txt (no RTCD; portable scalar path on x86, NEON on arm64), and linked into libvoicecat which defines VOICECAT_HAS_NS. To refresh the model, re-run upstream autogen.sh/download_model.sh

• scripts/shrink_model.sh and re-copy src/rnnoise_data.{c,h}.