EdisonJwa
af686ca7a6
Skeleton scaffolding for the iOS VoiceProcessingIO backend that
will replace cpal on iOS. This commit lands the dependency + the
module + a constructable AudioUnit that emits silence and drops
input; nothing in engine.rs is wired up yet (that is commit 2).
Compilation contract for this commit:
* Linux / Windows / macOS / Android builds unaffected (the new
module is target_os='ios' gated, the new dep is in
'[target."cfg(target_os = \"ios\")"]').
* iOS build pulls in coreaudio-rs 0.14, constructs a VPIO unit,
pins stream format to 48 kHz Int16 mono on both buses, installs
no-op input + silence-emitting render callbacks, initializes,
and starts. No audio is actually moved until commits 3/4.
Why VPIO and not RemoteIO via cpal: cpal's iOS backend opens
RemoteIO with no control over stream format / buffer size /
channels and produces a mono-only output element that stays bound
to the route present at construction time. End-user symptom on
iPhone 16 Pro iOS 18.7.8: tapping Speaker in the picker flips
AVAudioSession.currentRoute.outputs to Speaker (confirmed in our
diagnostic logs from commit da631a2) but audio keeps coming out
the receiver because the AudioUnit's output binding is stale.
Every production iOS VoIP client (Mumble iOS, Linphone /
mediastreamer2, Signal-iOS, Jitsi Meet iOS, the WebRTC reference
impl) avoids RemoteIO and uses VoiceProcessingIO instead. VPIO is
Apple's recommended voice unit; it ships hardware AEC + AGC + NS
and re-binds the physical transducer correctly on route changes
because it IS the canonical voice unit on iOS — FaceTime's audio
path runs through it.
coreaudio-rs 0.14 (RustAudio org, 8.6M downloads, same maintainers
as cpal) gives us a safe wrapper around the AudioUnit C API on
iOS. Uses objc2-* crates underneath so links cleanly into iOS
builds. ios_voice_unit.rs sits next to sdl_output.rs as the iOS
sibling of the Linux SDL2 output path.
Build verify (Linux host): `cargo check -p chanora_audio`
finished clean in 16.09s. iOS build verification happens in
commit 2 when the module is exercised; for this commit the module
compiles in isolation but is dead code on iOS too (no caller).
127 lines
6.1 KiB
TOML
127 lines
6.1 KiB
TOML
[package]
|
|
name = "chanora_audio"
|
|
description = "Chanora audio subsystem — cpal-based capture/playback, audiopus encode, tsclientlib AudioHandler for decode + jitter buffer + mix. DEC-011, DEC-011.1."
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
authors.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
publish.workspace = true
|
|
|
|
[dependencies]
|
|
chanora_protocol = { path = "../chanora_protocol" }
|
|
thiserror.workspace = true
|
|
tracing.workspace = true
|
|
|
|
# Cross-platform audio I/O (DEC-011.1).
|
|
cpal = "0.16"
|
|
# Opus encoder. tsclientlib already pulls this; we depend explicitly so
|
|
# this crate can compile against it without going through tsclientlib.
|
|
audiopus = "0.3.0-rc.0"
|
|
|
|
# AudioHandler lives in the tsclientlib crate behind the `audio`
|
|
# feature. We import the crate just for the AudioHandler type; the
|
|
# Connection type stays inside chanora_protocol.
|
|
tsclientlib = { git = "https://github.com/ReSpeak/tsclientlib.git", rev = "04aa2491", default-features = false, features = ["audio"] }
|
|
# Force the reqwest TLS backend to native-tls (Security.framework on
|
|
# Apple, SChannel on Windows, system OpenSSL on Linux/BSD) instead of
|
|
# the rustls + aws-lc-rs combination tsclientlib's `default-tls`
|
|
# feature would otherwise pick. aws-lc-sys does not cross-compile
|
|
# cleanly to aarch64-apple-ios, and native-tls is the standard
|
|
# answer for "TLS that just works on every desktop+mobile platform
|
|
# without a vendored C dependency". Cargo's feature unification means
|
|
# this single direct dep applies to the transitive
|
|
# tsclientlib -> reqwest chain too.
|
|
reqwest = { version = "0.13", default-features = false, features = ["charset", "http2", "native-tls"] }
|
|
|
|
tokio = { version = "1", features = ["sync", "rt", "macros", "time"] }
|
|
|
|
[target.'cfg(target_os = "ios")'.dependencies]
|
|
# Direct CoreAudio AudioUnit access on iOS (DEC-011.x follow-up).
|
|
# cpal's iOS backend is unsuitable for VoIP: it opens
|
|
# kAudioUnitSubType_RemoteIO with a mono-only output element and no
|
|
# control over buffer size / sample rate, AND its AudioUnit stays
|
|
# bound to the route present at construction time so user-driven
|
|
# `overrideOutputAudioPort` flips do not actually move audio to the
|
|
# new transducer. Every production iOS VoIP client (Linphone, Mumble
|
|
# iOS, Signal, Jitsi, WebRTC reference) instead drives
|
|
# `kAudioUnitSubType_VoiceProcessingIO` (a.k.a. VPIO) directly. VPIO
|
|
# is Apple's recommended voice unit; it ships hardware AEC + AGC + NS
|
|
# and honours route changes natively because it IS the canonical
|
|
# voice unit on iOS. `coreaudio-rs` (RustAudio org, same maintainers
|
|
# as `cpal`, 8.6M downloads) gives us a safe wrapper around the
|
|
# AudioUnit C API. We use it on iOS only; cpal stays on macOS where
|
|
# its CoreAudio backend works well against HAL units.
|
|
#
|
|
# Default features keep `audio_toolbox` + `core_audio`, both required
|
|
# for AudioUnit construction + property access.
|
|
coreaudio-rs = "0.14"
|
|
|
|
[target.'cfg(target_os = "android")'.dependencies]
|
|
# JNI bindings to flip Android's AudioManager into MODE_IN_COMMUNICATION
|
|
# when the voice-comm preset is requested. ndk_context is initialised
|
|
# by the bridge crate's android_init shim.
|
|
jni = { version = "0.21", default-features = false }
|
|
ndk-context = "0.1"
|
|
|
|
[target.'cfg(target_os = "windows")'.dependencies]
|
|
# Real Windows global PTT (SDD-083 / SDD-084): RegisterRawInputDevices
|
|
# + WM_INPUT translation backed by a hidden message-only window, and
|
|
# SetWindowsHookExW(WH_KEYBOARD_LL / WH_MOUSE_LL) fallback. Both
|
|
# require a per-backend OS thread that owns a message pump.
|
|
windows = { version = "0.54", features = [
|
|
"Win32_Foundation",
|
|
"Win32_Graphics_Gdi",
|
|
"Win32_System_LibraryLoader",
|
|
"Win32_System_Threading",
|
|
"Win32_UI_Input",
|
|
"Win32_UI_Input_KeyboardAndMouse",
|
|
"Win32_UI_WindowsAndMessaging",
|
|
] }
|
|
|
|
[dev-dependencies]
|
|
# `test-util` enables `start_paused` / virtual-clock tests used by
|
|
# the missed-key-up watchdog unit tests.
|
|
tokio = { version = "1", features = ["sync", "rt", "macros", "time", "test-util"] }
|
|
# Cross-platform recording Layer for the SDD-090 / DEC-027 privacy
|
|
# invariant integration test (`tests/ptt_privacy.rs`).
|
|
tracing-subscriber = { version = "0.3", features = ["registry"] }
|
|
|
|
[target.'cfg(target_os = "linux")'.dependencies]
|
|
# GNOME-on-Wayland Global Push-to-Talk uses the freedesktop
|
|
# `org.freedesktop.portal.GlobalShortcuts` interface over D-Bus.
|
|
# `zbus` is the standard async D-Bus crate; the `tokio` runtime
|
|
# selector is mandatory in zbus 5; we share the tokio runtime
|
|
# the rest of the audio + core crates already depend on. The
|
|
# `blocking-api` feature is retained so the audio-engine
|
|
# probe path can do a synchronous portal-version read without
|
|
# starting an async runtime; the live session flow uses the
|
|
# async surface.
|
|
zbus = { version = "5", default-features = false, features = ["tokio", "blocking-api"] }
|
|
# Stream / sink utilities for consuming portal signals on the
|
|
# async path.
|
|
futures-util = { version = "0.3", default-features = false, features = ["std"] }
|
|
# Random token bytes for the portal handle_token / session_handle_token
|
|
# options. The portal recommends fresh tokens to scope its own
|
|
# object paths per call.
|
|
rand = "0.8"
|
|
# SDL2 audio for Linux. Replaces the cpal capture / playback paths
|
|
# on Linux only; cpal stays in use on Windows/macOS. Rationale: the
|
|
# cpal Linux backend opens raw ALSA `default`, which on most Arch
|
|
# / Fedora / Debian installs routes through `dmix` + `plug` with
|
|
# nearest-neighbour resampling and very small period sizes — the
|
|
# combination produces audible crackling/popping. SDL2 on the same
|
|
# systems routes through PipeWire's PulseAudio compat bridge (or
|
|
# real PulseAudio), both of which carry a high-quality resampler
|
|
# and a sensible default period. The upstream tsclientlib audio
|
|
# example (`tsclientlib/examples/audio_utils/ts_to_audio.rs`) and
|
|
# the official Qint client both use SDL2 in exactly this shape;
|
|
# this dep brings Chanora in line with that pattern.
|
|
#
|
|
# `bundled` is OFF deliberately — we link against the system
|
|
# libSDL2.so. Arch ships `sdl2-compat`; Debian/Ubuntu ship
|
|
# `libsdl2-2.0-0`; Fedora ships `SDL2`. The chanora-flutter Linux
|
|
# build documentation lists this as a runtime dependency.
|
|
sdl2 = { version = "0.37", default-features = false }
|