Files
voice-cat/clients/apple/Sources/VoiceCatCore/Models.swift
Talon 6c17881cc0 feat(ios): real echo cancellation/NR via native Voice-Processing engine
iOS "voice chat" had echo and no noise suppression: real iOS AEC/NS/AGC
come only from Apple's Voice-Processing I/O unit (VPIO), but the core
plays/captures via miniaudio's plain RemoteIO units, so .voiceChat mode
alone never engaged AEC.

Core (ABI PATCH 1->2):
- vc_set_mixed_output_sink + vc_set_external_playback. In external mode the
  AudioEngine opens no hardware playback device; a mixer-timer thread drives
  on_playback (decode+mix) on a ~20ms cadence and ships the final mix to the
  sink. start() also skips the hardware capture device when the MIC stream is
  external_feed (AudioParams.external_capture).
- New white-box test test_external_playback (drives the timer with no hw).

iOS/Swift:
- StreamDescriptor.externalFeed; VoiceCatClient.setMixedOutputSink /
  setExternalPlayback wrappers.
- IOSVoiceProcessingEngine: AVAudioEngine + setVoiceProcessingEnabled; mic
  tap -> feedPcm, mixed-sink lock-free ring -> AVAudioSourceNode (both share
  the VPIO unit so AEC has its reference signal).
- IOSAudioRouter.currentConfigUsesVoiceProcessing scopes VPIO to the AEC
  presets; SessionState join/leave + reconcileVoicePath() switch paths;
  Voice Chat defaults to speaker; Settings surfaces AEC/NS state.

Known: pending on-device verification; a few bugs to fix afterward.
2026-06-22 02:38:01 +02:00

243 lines
11 KiB
Swift
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// Plain Swift value types what survives past the native struct/free-list lifetime
// (Marshaling.swift converts the C structs into these and immediately frees the native
// list). Nothing here holds a raw pointer. This is the Swift analog of the C# client's
// Models.cs. Field naming follows Swift camelCase (the C structs use snake_case).
import VoiceCatC
/// Channel snapshot mirrors `vc_channel` (the pull-based view; re-call `listChannels()`
/// after `.channelList` / `.userJoined` / `.userLeft` / `.userUpdated` events).
public struct Channel: Sendable, Equatable, Identifiable {
public let id: UInt32
/// 0 = root.
public let parentId: UInt32
public let name: String
public let topic: String
public let passwordProtected: Bool
/// 0 = unlimited.
public let maxUsers: UInt32
public init(id: UInt32, parentId: UInt32, name: String, topic: String,
passwordProtected: Bool, maxUsers: UInt32) {
self.id = id; self.parentId = parentId; self.name = name; self.topic = topic
self.passwordProtected = passwordProtected; self.maxUsers = maxUsers
}
}
/// Channel creation/edition descriptor mirrors `vc_channel_info`. Used by
/// `createChannel(_:)` and `editChannel(_:)`. `id == 0` means new channel (for create).
public struct ChannelEdit: Sendable, Equatable {
public let id: UInt32 // 0 = new channel for create
public let parentId: UInt32 // 0 = root
public let name: String
public let topic: String
public let passwordProtected: Bool
public let password: String? // nil/empty ignored if passwordProtected == false
public let maxUsers: UInt32 // 0 = unlimited
public let sortOrder: UInt32
/// 0/nil fields use server defaults.
public let audio: AudioConfig
public init(id: UInt32, parentId: UInt32, name: String, topic: String,
passwordProtected: Bool, password: String?, maxUsers: UInt32,
sortOrder: UInt32, audio: AudioConfig) {
self.id = id; self.parentId = parentId; self.name = name; self.topic = topic
self.passwordProtected = passwordProtected; self.password = password
self.maxUsers = maxUsers; self.sortOrder = sortOrder; self.audio = audio
}
}
/// User snapshot mirrors `vc_user`.
public struct User: Sendable, Equatable, Identifiable {
public let id: UInt32
public let nickname: String
public let isGuest: Bool
public let channelId: UInt32
public let selfMicMuted: Bool
public let selfDeafened: Bool
public let serverMuted: Bool
public let serverDeafened: Bool
public init(id: UInt32, nickname: String, isGuest: Bool, channelId: UInt32,
selfMicMuted: Bool, selfDeafened: Bool, serverMuted: Bool,
serverDeafened: Bool) {
self.id = id; self.nickname = nickname; self.isGuest = isGuest; self.channelId = channelId
self.selfMicMuted = selfMicMuted; self.selfDeafened = selfDeafened
self.serverMuted = serverMuted; self.serverDeafened = serverDeafened
}
}
/// Permission bitset mirrors `vc_permissions` (M5).
public struct Permissions: Sendable, Equatable {
public let canCreateTempChannel: Bool
public let canKick: Bool
public let canBan: Bool
public let canMoveUsers: Bool
public let canAdminAccounts: Bool
public let isAdmin: Bool
public init(canCreateTempChannel: Bool, canKick: Bool, canBan: Bool,
canMoveUsers: Bool, canAdminAccounts: Bool, isAdmin: Bool) {
self.canCreateTempChannel = canCreateTempChannel; self.canKick = canKick; self.canBan = canBan
self.canMoveUsers = canMoveUsers; self.canAdminAccounts = canAdminAccounts; self.isAdmin = isAdmin
}
}
/// Account entry mirrors `vc_account` (M5, reply to `listAccounts()`).
public struct Account: Sendable, Equatable {
public let username: String
public let isAdmin: Bool
public let createdAtUnixMs: UInt64
public let lastLoginUnixMs: UInt64
public init(username: String, isAdmin: Bool, createdAtUnixMs: UInt64,
lastLoginUnixMs: UInt64) {
self.username = username; self.isAdmin = isAdmin
self.createdAtUnixMs = createdAtUnixMs; self.lastLoginUnixMs = lastLoginUnixMs
}
}
/// Per-user stream summary mirrors `vc_stream_summary`. For the full effective Opus
/// config of a specific (user_id, stream_id), use `VoiceCatClient.getStreamAudioConfig`.
public struct StreamSummary: Sendable, Equatable, Identifiable {
public let id: UInt32 // stream_id
public let kind: VoiceCatStreamKind
public let label: String
public init(streamId: UInt32, kind: VoiceCatStreamKind, label: String) {
self.id = streamId; self.kind = kind; self.label = label
}
}
/// Receive-side state the local listener chose for a specific remote stream mirrors
/// `vc_remote_stream_state`. All LOCAL (no protocol traffic) docs/voice.md §10.
/// Defaults (if `setRemoteStream` was never called): gain 1.0, unmuted, NR off.
public struct RemoteStreamState: Sendable, Equatable {
public let gain: Float // 0.0 ; default 1.0
public let muted: Bool
public let noiseReduction: Bool
public init(gain: Float, muted: Bool, noiseReduction: Bool) {
self.gain = gain; self.muted = muted; self.noiseReduction = noiseReduction
}
}
/// Audio device mirrors `vc_device`. `id` is an opaque, internally-encoded handle
/// (currently hex-encoded `ma_device_id`) always round-trip an id from `listDevices`;
/// never construct one by hand (docs/architecture.md §4).
public struct Device: Sendable, Equatable, Identifiable {
public let id: String
public let name: String
public let isDefault: Bool
public init(id: String, name: String, isDefault: Bool) {
self.id = id; self.name = name; self.isDefault = isDefault
}
}
/// iOS audio input port derived from `AVAudioSession.availableInputs`. Unlike the
/// miniaudio-based `Device` (which returns ~2 entries on iOS), this exposes the real
/// AVAudioSession input ports (builtInMic, bluetoothHFP, headsetMic, usbAudio, airPlay)
/// with their data sources (orientation: front/back/top/bottom) and polar patterns
/// (omni/cardioid/subcardioid/bidirectional). Used by `IOSAudioRouter` + `SettingsView`.
public struct IOSAudioInputPort: Identifiable, Hashable {
public let id: String // port UID (stable across route changes)
public let name: String // human-readable port name
public let portType: String // AVAudioSession.Port raw value as string
public let dataSources: [IOSAudioDataSource]?
public let isSelected: Bool // true if this is the current preferredInput
public init(id: String, name: String, portType: String,
dataSources: [IOSAudioDataSource]?, isSelected: Bool) {
self.id = id; self.name = name; self.portType = portType
self.dataSources = dataSources; self.isSelected = isSelected
}
}
/// iOS audio data source a sub-selection of an input port (e.g. built-in mic
/// orientation: front/back/top/bottom). May have polar pattern options.
public struct IOSAudioDataSource: Identifiable, Hashable {
public let id: String // dataSource UID
public let name: String // "Front", "Back", "Top", "Bottom"
public let polarPatterns: [String]? // AVAudioSession.PolarPattern raw values
public let isSelected: Bool // true if this is the current preferredDataSource
public let selectedPolarPattern: String?
public init(id: String, name: String, polarPatterns: [String]?,
isSelected: Bool, selectedPolarPattern: String?) {
self.id = id; self.name = name; self.polarPatterns = polarPatterns
self.isSelected = isSelected; self.selectedPolarPattern = selectedPolarPattern
}
}
/// iOS audio output route read-only display of `AVAudioSession.currentRoute.outputs`.
public struct IOSAudioOutputRoute: Identifiable, Hashable {
public let id: String // port UID
public let name: String // human-readable route name
public let portType: String // AVAudioSession.Port raw value as string
public init(id: String, name: String, portType: String) {
self.id = id; self.name = name; self.portType = portType
}
}
/// Effective Opus configuration mirrors `vc_audio_config`.
public struct AudioConfig: Sendable, Equatable {
public let codec: UInt32 // 0 = OPUS
public let stereo: Bool // mode: 0 = mono, 1 = stereo
public let sampleRate: UInt32
public let bitrateBps: UInt32
public let frameMs: UInt32
public let application: UInt32 // 0 = VOIP, 1 = AUDIO, 2 = LOWDELAY
public let fec: Bool
public let expectedPacketLoss: UInt32 // % 0..100
public let dtx: Bool
public let complexity: UInt32 // 0..10
public let dred: Bool // Deep REDundancy (Opus 1.6), off by default
public init(codec: UInt32 = 0, stereo: Bool = false, sampleRate: UInt32 = 48000,
bitrateBps: UInt32 = 64000, frameMs: UInt32 = 20, application: UInt32 = 0,
fec: Bool = true, expectedPacketLoss: UInt32 = 5, dtx: Bool = false,
complexity: UInt32 = 10, dred: Bool = false) {
self.codec = codec; self.stereo = stereo; self.sampleRate = sampleRate
self.bitrateBps = bitrateBps; self.frameMs = frameMs; self.application = application
self.fec = fec; self.expectedPacketLoss = expectedPacketLoss; self.dtx = dtx
self.complexity = complexity; self.dred = dred
}
}
/// Stream descriptor mirrors `vc_stream_desc`. Used by `startStream(kind:deviceId:label:)`.
public struct StreamDescriptor: Sendable, Equatable {
public let kind: VoiceCatStreamKind
/// nil = default device for this kind.
public let deviceId: String?
public let label: String
/// When true the caller feeds PCM via `feedPcm` (e.g. the iOS VPIO mic path) and the core
/// skips opening a hardware capture device for this stream. Mirrors `vc_stream_desc.external_feed`.
public let externalFeed: Bool
public init(kind: VoiceCatStreamKind, deviceId: String? = nil, label: String,
externalFeed: Bool = false) {
self.kind = kind; self.deviceId = deviceId; self.label = label
self.externalFeed = externalFeed
}
}
/// Server identity info parsed from a `.serverIdentity` event + `getServerIdentityDisplay()`.
/// The `tlsCertFingerprint` (SHA-256 hex of the TLS leaf cert) is the value the TOFU gate
/// actually pins on; `ed25519Fingerprint` is display-only (docs/security.md §1.1).
public struct ServerIdentity: Sendable, Equatable {
public let tofuStatus: VoiceCatTofuStatus
/// SHA-256 hex of the TLS leaf certificate the pinned value. No separators (64 chars).
public let tlsCertFingerprint: String
/// Ed25519 identity fingerprint from ServerHello, hex-formatted display only.
/// Empty if not yet available.
public let ed25519Fingerprint: String
public init(tofuStatus: VoiceCatTofuStatus, tlsCertFingerprint: String,
ed25519Fingerprint: String) {
self.tofuStatus = tofuStatus; self.tlsCertFingerprint = tlsCertFingerprint
self.ed25519Fingerprint = ed25519Fingerprint
}
}