EdisonJwa
d9c330c23b
User reported persistent crackling/popping from peer audio on Linux even
after fixing the 48k->device-rate resampler boundary discontinuities,
clamping pre-Opus-encode peaks, and pre-allocating the playback scratch
buffer. Logs confirmed cpal opened raw ALSA at 44.1k native, no callback
budget violations, no underrun warnings -- yet the audio was still poor.
Root cause: cpal on Linux opens raw ALSA's 'default' PCM. On modern
PipeWire / pipewire-alsa boxes that virtual device routes through ALSA's
dmix + plug layers, whose default resampler is nearest-neighbour. cpal
also picks a small default period size (~256 frames / 5.8 ms) leaving no
headroom for kernel scheduler jitter. Both effects compound into the
crackling the user heard.
Upstream tsclientlib's own audio example
(tsclientlib/examples/audio_utils/ts_to_audio.rs) and the official Qint
client both use SDL2 with AudioSpecDesired { freq: 48000, channels: 2,
samples: 960 }. SDL2 on the same systems routes through PipeWire's PA
bridge (or PulseAudio directly), both carrying high-quality resamplers.
Fix:
* Add sdl2 = '0.37' as a target_os=linux dependency. Links libSDL2-2.0
.so (Arch sdl2-compat over SDL3, Debian libsdl2-2.0-0, Fedora SDL2).
* New module crates/chanora_audio/src/sdl_output.rs implementing
SdlOutput: opens a 48 kHz stereo 960-frame callback that zeroes the
buffer and calls AudioHandler::fill_buffer directly (no user-side
resampler). Master gain + hard-mute atomics wired in identically to
the cpal callback so set_output_gain / set_output_muted keep working.
* engine.rs cfg-gated: target_os='linux' builds SdlOutput; everywhere
else continues with the cpal output path (including the device-native-
rate negotiation and resampler-continuity fixes shipped earlier --
those remain correct on Windows/macOS where cpal targets WASAPI /
CoreAudio cleanly).
* The cpal output helpers (build_output_stream, PlaybackResampleState,
FromF32) are now cfg(not(target_os='linux'))-gated so the Linux
build doesn't emit dead-code warnings.
Capture path still cpal on every platform -- outbound audio was not
reported as bad. Resampler-continuity fix on the capture side stays:
microphone -> Opus encoder still goes through the linear interpolator
with the last-sample anchor.
Tests: 32 / 0 / 0 (chanora_audio), workspace 78 / 0 / 1 unchanged.
96 lines
4.4 KiB
TOML
96 lines
4.4 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 = ["default-tls", "audio"] }
|
|
|
|
tokio = { version = "1", features = ["sync", "rt", "macros", "time"] }
|
|
|
|
[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 }
|