Closes the three items PROGRESS.md's M3 section explicitly carried forward as out of scope: - Device enumeration (vc_list_devices) + input device selection (vc_set_input_device), backed by AudioEngine::enumerate_devices() via miniaudio's ma_context_get_devices. Device ids are opaque hex-encoded ma_device_id strings. - VAD/PTT send-side input gate (vc_set_input_mode, vc_set_push_to_talk). webrtc-audio-processing (the originally-planned APM) has no working Windows/MSVC build upstream (GCC-only Meson, unfinished MinGW support, hard abseil-cpp dependency), so VAD is a new lightweight, dependency-free energy/RMS processor (EnergyVadProcessor) behind the existing ApmProcessor interface. Gating is MIC-only; SCREEN_AUDIO/AUX_DEVICE always bypass it. - True stereo playback: AudioEngine's mixer and output device now carry stereo end-to-end (mono streams upmix L=R) instead of downmixing decoded stereo streams to mono before mixing. - Real WASAPI loopback capture for SCREEN_AUDIO (Windows-only, via miniaudio's loopback device type), replacing test-only injection as the production capture path. Also: vccli gains --list-devices, --input-device, --input-mode, and --share-screen-audio flags, plus a stdin command loop (ptt on/off, mode vad/ptt) for manual verification. New test_vad_ptt_devices.cpp covers all four items (ABI-level + a white-box AudioEngine stereo-mix check). Docs updated to match: voice.md, roadmap.md (decision-log entry superseding the original webrtc-audio-processing choice), tech-stack.md, README.md, architecture.md, CLAUDE.md, PROGRESS.md. Still explicitly out of scope, documented not silently dropped: real webrtc-audio-processing/AEC (no AEC/NS/AGC exists at all yet), macOS/iOS SCREEN_AUDIO capture, process-specific loopback, and a pre-existing RT-thread rule violation in the capture path that predates this work. Verified: ctest 12/12 green across 3 consecutive full-suite runs (both dev and m1-dev presets build clean); test_vad_ptt_devices passed 5 consecutive standalone runs; manually verified live (vccli --list-devices against real hardware, vccli --voice --input-mode vad streaming without incident). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
73 lines
3.1 KiB
CMake
73 lines
3.1 KiB
CMake
# libvoicecat — the shared C++ core (docs/architecture.md).
|
|
# Sources are globbed so adding a stub under src/<subsystem>/ needs no CMake edit.
|
|
file(GLOB_RECURSE VOICECAT_SOURCES CONFIGURE_DEPENDS
|
|
"${CMAKE_CURRENT_SOURCE_DIR}/src/*.cpp")
|
|
|
|
if(VOICECAT_BUILD_SHARED)
|
|
add_library(voicecat SHARED ${VOICECAT_SOURCES})
|
|
else()
|
|
add_library(voicecat STATIC ${VOICECAT_SOURCES})
|
|
# Static consumers must see VC_API as empty (no dllimport).
|
|
target_compile_definitions(voicecat PUBLIC VOICECAT_STATIC)
|
|
endif()
|
|
add_library(voicecat::voicecat ALIAS voicecat)
|
|
|
|
target_include_directories(voicecat
|
|
PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include
|
|
PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src)
|
|
|
|
target_compile_definitions(voicecat PRIVATE VOICECAT_BUILDING)
|
|
target_compile_features(voicecat PUBLIC cxx_std_20)
|
|
|
|
set_target_properties(voicecat PROPERTIES
|
|
C_VISIBILITY_PRESET hidden
|
|
CXX_VISIBILITY_PRESET hidden
|
|
VISIBILITY_INLINES_HIDDEN ON)
|
|
|
|
if(VOICECAT_USE_VCPKG_DEPS)
|
|
find_package(protobuf CONFIG REQUIRED)
|
|
find_package(unofficial-sodium CONFIG REQUIRED)
|
|
find_package(MbedTLS CONFIG REQUIRED)
|
|
find_package(asio CONFIG REQUIRED)
|
|
find_package(unofficial-sqlite3 CONFIG REQUIRED)
|
|
find_package(spdlog CONFIG REQUIRED)
|
|
find_package(Opus CONFIG REQUIRED)
|
|
# miniaudio is header-only; vcpkg does not install a CMake config for it.
|
|
find_path(MINIAUDIO_INCLUDE_DIR "miniaudio.h" REQUIRED)
|
|
|
|
# Generate C++ from voicecat.proto into the build tree.
|
|
protobuf_generate(
|
|
TARGET voicecat
|
|
PROTOS proto/voicecat.proto
|
|
LANGUAGE cpp
|
|
IMPORT_DIRS ${CMAKE_CURRENT_SOURCE_DIR}/proto
|
|
PROTOC_OUT_DIR ${CMAKE_CURRENT_BINARY_DIR}/generated/proto)
|
|
# Generated .pb.h files are included by protocol/envelope.h (consumed by tests and server),
|
|
# so the generated dir and protobuf itself must be PUBLIC.
|
|
target_include_directories(voicecat PUBLIC ${CMAKE_CURRENT_BINARY_DIR}/generated)
|
|
|
|
target_link_libraries(voicecat
|
|
PUBLIC protobuf::libprotobuf
|
|
PRIVATE unofficial-sodium::sodium
|
|
MbedTLS::mbedtls MbedTLS::mbedcrypto MbedTLS::mbedx509
|
|
asio::asio unofficial::sqlite3::sqlite3 spdlog::spdlog
|
|
Opus::opus)
|
|
|
|
target_include_directories(voicecat PRIVATE ${MINIAUDIO_INCLUDE_DIR})
|
|
|
|
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_OPUS VOICECAT_HAS_AUDIO)
|
|
|
|
if(WIN32)
|
|
# AcceptEx / GetAcceptExSockaddrs live in mswsock; ws2_32 covers the base Winsock API.
|
|
target_link_libraries(voicecat PRIVATE ws2_32 mswsock)
|
|
# Real desktop-audio loopback capture for SCREEN_AUDIO (miniaudio's ma_device_type_loopback
|
|
# is WASAPI-only). Other platforms keep vc_test_inject_capture as the only way to feed
|
|
# SCREEN_AUDIO until a per-platform loopback path is built (macOS: ScreenCaptureKit, per
|
|
# docs/voice.md §9 — not in scope yet).
|
|
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_LOOPBACK)
|
|
endif()
|
|
|
|
# Signal to C++ code that the real networking/crypto stack is available.
|
|
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_NET)
|
|
endif()
|