Files
punktfunk/clients/apple/Sources/PunktfunkKit/Audio/AudioDevices.swift
T
enricobuehler 42d1c74663
apple / swift (push) Successful in 1m5s
docker / build-push (ci, ci/rust-ci.Dockerfile, punktfunk-rust-ci) (push) Has been cancelled
docker / build-push (docs-site, docs-site/Dockerfile, punktfunk-docs) (push) Has been cancelled
docker / build-push (--build-arg FEDORA_VERSION=44, ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora44-rpm) (push) Has been cancelled
android / android (push) Has been cancelled
apple / screenshots (push) Has been cancelled
ci / web (push) Has been cancelled
ci / docs-site (push) Has been cancelled
ci / bench (push) Has been cancelled
ci / rust (push) Has been cancelled
deb / build-publish (push) Has been cancelled
decky / build-publish (push) Has been cancelled
docker / build-push (., web/Dockerfile, punktfunk-web) (push) Has been cancelled
docker / build-push (ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora-rpm) (push) Has been cancelled
docker / deploy-docs (push) Has been cancelled
rpm / build-publish (fedora-44, punktfunk-fedora44-rpm) (push) Has been cancelled
rpm / build-publish (bazzite, punktfunk-fedora-rpm) (push) Has been cancelled
release / apple (push) Has been cancelled
fix(apple-client/audio): capture the right channel of a multi-channel mic + diagnostics
The mic uplink handed the host pure digital silence on a multi-channel
interface: AVAudioConverter's N→stereo downmix takes channels 0/1, but a
pro interface puts the mic on ONE higher discrete channel. Fold the input
to a mono bus ourselves instead — pick the mic's channel (or sum all) and
resample that to the encoder's 48 kHz stereo, so the silent 0/1 downmix
never happens.

- New "Microphone channel" setting (macOS): Auto (sum every channel — a
  lone hot mic passes at full level) or pin 1-based channel N. Picker
  appears only for multi-channel devices, driven by the device's input
  channel count.
- Diagnostics that make this class of failure self-naming next session:
  log the actual live capture device + format + fold mode, warn on a
  silent UID fallback, and a one-shot silence tripwire on the EXTRACTED
  signal (WARN on 10 s of zeros, else peak dBFS).
- foldToMono extracted as a pure, unit-tested helper (pin / sum-clamp x
  interleaved / deinterleaved / mono / out-of-range).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-04 00:36:35 +02:00

133 lines
5.5 KiB
Swift

// CoreAudio HAL device enumeration for the Settings pickers. Devices are persisted by
// UID (stable across reboots/replugs AudioDeviceIDs are not); the empty UID means
// "system default", which additionally tracks default-device changes because we then
// never pin the engine to a concrete device.
#if os(macOS)
import CoreAudio
import Foundation
public struct AudioDevice: Hashable, Identifiable, Sendable {
public let uid: String
public let name: String
public var id: String { uid }
}
public enum AudioDevices {
/// Output-capable devices (speakers, headphones, multi-output).
public static func outputs() -> [AudioDevice] {
all().filter { hasStreams($0, scope: kAudioObjectPropertyScopeOutput) }
.compactMap(describe)
}
/// Input-capable devices (microphones, interfaces).
public static func inputs() -> [AudioDevice] {
all().filter { hasStreams($0, scope: kAudioObjectPropertyScopeInput) }
.compactMap(describe)
}
/// Resolve a persisted UID to the current AudioDeviceID nil when unplugged.
static func deviceID(forUID uid: String) -> AudioDeviceID? {
all().first { id in
stringProperty(id, kAudioDevicePropertyDeviceUID) == uid
}
}
/// Input channel count of the mic the picker would use the device with this UID, or the
/// system default input when `uid` is empty. 0 when it can't be resolved. Drives the
/// "Microphone channel" picker (only shown for multi-channel interfaces).
public static func inputChannelCount(forUID uid: String) -> Int {
let id = uid.isEmpty ? defaultInputDevice() : deviceID(forUID: uid)
guard let id else { return 0 }
return channelCount(id, scope: kAudioObjectPropertyScopeInput)
}
private static func defaultInputDevice() -> AudioDeviceID? {
var address = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDefaultInputDevice,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var dev = AudioDeviceID(0)
var size = UInt32(MemoryLayout<AudioDeviceID>.size)
guard AudioObjectGetPropertyData(
AudioObjectID(kAudioObjectSystemObject), &address, 0, nil, &size, &dev) == noErr,
dev != 0
else { return nil }
return dev
}
/// Sum of channels across the device's streams in `scope` (its total input/output channels).
private static func channelCount(
_ id: AudioDeviceID, scope: AudioObjectPropertyScope
) -> Int {
var address = AudioObjectPropertyAddress(
mSelector: kAudioDevicePropertyStreamConfiguration,
mScope: scope,
mElement: kAudioObjectPropertyElementMain)
var size: UInt32 = 0
guard AudioObjectGetPropertyDataSize(id, &address, 0, nil, &size) == noErr, size > 0
else { return 0 }
let raw = UnsafeMutableRawPointer.allocate(
byteCount: Int(size), alignment: MemoryLayout<AudioBufferList>.alignment)
defer { raw.deallocate() }
guard AudioObjectGetPropertyData(id, &address, 0, nil, &size, raw) == noErr else { return 0 }
let abl = UnsafeMutableAudioBufferListPointer(
raw.assumingMemoryBound(to: AudioBufferList.self))
return abl.reduce(0) { $0 + Int($1.mNumberChannels) }
}
private static func all() -> [AudioDeviceID] {
var address = AudioObjectPropertyAddress(
mSelector: kAudioHardwarePropertyDevices,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var size: UInt32 = 0
guard AudioObjectGetPropertyDataSize(
AudioObjectID(kAudioObjectSystemObject), &address, 0, nil, &size) == noErr,
size > 0
else { return [] }
var ids = [AudioDeviceID](
repeating: 0, count: Int(size) / MemoryLayout<AudioDeviceID>.size)
guard AudioObjectGetPropertyData(
AudioObjectID(kAudioObjectSystemObject), &address, 0, nil, &size, &ids) == noErr
else { return [] }
return ids
}
private static func hasStreams(
_ id: AudioDeviceID, scope: AudioObjectPropertyScope
) -> Bool {
var address = AudioObjectPropertyAddress(
mSelector: kAudioDevicePropertyStreams,
mScope: scope,
mElement: kAudioObjectPropertyElementMain)
var size: UInt32 = 0
return AudioObjectGetPropertyDataSize(id, &address, 0, nil, &size) == noErr && size > 0
}
/// UID + human name for a live AudioDeviceID (nil if either property is unreadable).
static func describe(_ id: AudioDeviceID) -> AudioDevice? {
guard let uid = stringProperty(id, kAudioDevicePropertyDeviceUID),
let name = stringProperty(id, kAudioObjectPropertyName)
else { return nil }
return AudioDevice(uid: uid, name: name)
}
private static func stringProperty(
_ id: AudioDeviceID, _ selector: AudioObjectPropertySelector
) -> String? {
var address = AudioObjectPropertyAddress(
mSelector: selector,
mScope: kAudioObjectPropertyScopeGlobal,
mElement: kAudioObjectPropertyElementMain)
var ref: CFString?
var size = UInt32(MemoryLayout<CFString?>.size)
let status = withUnsafeMutablePointer(to: &ref) { p in
AudioObjectGetPropertyData(id, &address, 0, nil, &size, p)
}
guard status == noErr, let ref else { return nil }
return ref as String
}
}
#endif