Merge branch 'main' into lib-split-cli

Add --flush option to reduce stdout buffering latency

.gitignore

@@ -7,3 +7,5 @@ DerivedData/
 .swiftpm/configuration/registries.json
 .swiftpm/xcode/package.xcworkspace/contents.xcworkspacedata
 .netrc
+*.pcm
+*.wav

Package.swift

@@ -4,11 +4,41 @@
 import PackageDescription
 
 let package = Package(
-    name: "audiotee",
+  name: "audiotee",
-    platforms: [
+  platforms: [
-        .macOS("14.2")
+    .macOS("14.2")
-    ],
+  ],
-    targets: [
+  products: [
-        .executableTarget(name: "audiotee")
+    // Library that can be imported by other packages
-    ]
+    .library(
+      name: "AudioTeeCore",
+      targets: ["AudioTeeCore"]
+    ),
+    // CLI executable
+    .executable(
+      name: "audiotee",
+      targets: ["AudioTeeCLI"]
+    )
+  ],
+  targets: [
+    // Core library with all business logic
+    .target(
+      name: "AudioTeeCore",
+      path: "Sources/AudioTeeCore"
+    ),
+    
+    // CLI executable that uses the library
+    .executableTarget(
+      name: "AudioTeeCLI",
+      dependencies: ["AudioTeeCore"],
+      path: "Sources/AudioTeeCLI"
+    ),
+    
+    // Tests for the library
+    .testTarget(
+      name: "AudioTeeCoreTests",
+      dependencies: ["AudioTeeCore"],
+      path: "Tests/AudioTeeCoreTests"
+    )
+  ]
 )

README.md

@@ -2,18 +2,21 @@
 
 **⚠️ API Instability Warning: The AudioTee API is unstable at present and subject to change without notice.**
 
-AudioTee captures your Mac's system audio output and writes it in PCM encoded chunks to `stdout` at regular intervals. All logging and metadata information is written to `stderr`, meaning at its simplest you can
+AudioTee captures your Mac's system audio output and writes it in PCM encoded chunks to `stdout` at regular intervals. All logging and metadata information is written to `stderr`, meaning at its simplest you can capture whatever's playing through your speakers to a file like this:
-capture system audio to a file like this:
 
 ```bash
 /path/to/audiotee > output.pcm
 ```
 
-System audio is captured using the [Core Audio taps](https://developer.apple.com/documentation/coreaudio/capturing-system-audio-with-core-audio-taps) API introduced in macOS 14.2 (released in December 2023). You can do whatever you want with this audio - stream it somewhere else, save it to disk, visualise it, etc.
+It's more likely you want to capture this output programmatically. Check out [AudioTee.js](https://github.com/makeusabrew/audioteejs) for a simple Node.js package which does this.
 
-By default, audiotee captures audio output from **all** running processes. Tap output is forced to `mono` (not yet configurable) and preserves your output device's sample rate (configurable via the `--sample-rate` flag). Only the default output device is currently supported.
+System audio is captured using the [Core Audio taps](https://developer.apple.com/documentation/coreaudio/capturing-system-audio-with-core-audio-taps) API introduced in macOS 14.2 (released in December 2023). You can do whatever you want with this audio - save it to disk, visualise it, transcribe it, etc.
 
-My original (and so far only) use case is streaming audio to a parent process which communicates with a realtime ASR service, so AudioTee makes some design decisions you might not agree with. Open an issue or a PR and we can talk about them. I'm also no Swift developer, so contributions improving codebase idioms and general hygiene are welcome. I have internal variations (and, franky, improvements) of audiotee which allow recording mic input as well as system audio, and I'm open to making that part of the main API.
+By default, AudioTee captures audio output from **all** running processes. Tap output defaults to `mono` (configurable via the `--stereo` flag) and preserves your output device's sample rate (configurable via the `--sample-rate` flag). Only the default output device is currently supported.
+
+My original (and so far only) use case is streaming audio to a parent process which communicates with a realtime ASR service, so AudioTee makes some design decisions you might not agree with. Open an issue or a PR and we can talk about them. I'm also no Swift developer, so contributions improving codebase idioms and general hygiene are welcome. I have internal variations (and, frankly, improvements) of AudioTee which allow recording mic input as well as system audio, and I'm open to making that part of the main API.
+
+## Why?
 
 Recording system audio is harder than it should be on macOS, and folks often wrestle with outdated advice and poorly documented APIs. It's a boring problem which stands in the way of lots of fun applications. There's more code here than you need to solve this problem yourself: the main classes of interest are probably [`Core/AudioTapManager`](https://github.com/makeusabrew/audiotee/blob/main/Sources/Core/AudioTapManager.swift) and [`Core/AudioRecorder`](https://github.com/makeusabrew/audiotee/blob/main/Sources/Core/AudioRecorder.swift). Everything's wired together in [`CLI/AudioTee`](https://github.com/makeusabrew/audiotee/blob/main/Sources/CLI/AudioTee.swift). The rest is just CLI configuration support, output formatting logic, and some utility functions you could probably live without.
 
@@ -25,7 +28,7 @@ Recording system audio is harder than it should be on macOS, and folks often wre
 
 ## Quick start
 
-The following will start capturing audio output from all running programs and write raw PCM audio data to your terminal:
+The following will start capturing audio output from all running programs and write binary chunks of raw PCM audio data to your terminal:
 
 ```bash
 git clone git@github.com:makeusabrew/audiotee.git
@@ -74,11 +77,14 @@ Replace the path below with `.build/<arch>/<target>/audiotee`, e.g. `build/arm64
 
 ### Audio conversion
 
-Note that performing sample rate conversion will also convert the output bit depth to
+Note that performing _any_ sample rate conversion will also convert the output bit depth to
-16-bit - assuming an original depth of 32-bit this results in a loss of dynamic range in exchange for half the output chunk size. For ASR services, 16-bit is sufficient, but it's a behaviour worth being aware of.
+16-bit - assuming an original depth of 32-bit this results in a loss of dynamic range in exchange for a 50% reduction in output size. For ASR services, 16-bit is sufficient, but it's a non-obvious behaviour worth being aware of.
 
 ```bash
-# Convert to 16kHz mono (useful for ASR services)
+# No sample rate preserves your device's default (probably 44.1 or 48kHz with 32-bit float bit depth)
+./audiotee
+
+# Any sample rate (even one matching your device default) converts to 16-bit signed integers (half the bandwidth)
 ./audiotee --sample-rate 16000
 
 # Other supported sample rates: 22050, 24000, 32000, 44100, 48000
@@ -118,12 +124,12 @@ Note that trying to include or exclude a PID which isn't currently playing audio
 
 ## Output
 
-AudioTee writes raw PCM audio data directly to `stdout` in chunks. All logging, metadata, and status information is written to `stderr`, allowing for clean separation of audio data from program output.
+AudioTee writes raw PCM audio data directly to `stdout` in chunks. All logging, metadata, and status information is written to `stderr`.
 
 ### Audio format
 
 - **Format**: Raw PCM audio data
-- **Channels**: Mono (1 channel)
+- **Channels**: 1 in Mono mode (default), 2 in stereo mode
 - **Sample rate**: Matches your output device's sample rate by default (configurable)
 - **Bit depth**: 32-bit float by default, or 16-bit when sample rate conversion is performed
 - **Endianness**: Little-endian
@@ -146,20 +152,21 @@ All program logs are written to `stderr` and can be captured separately:
 - `--include-processes`: Process IDs to tap (space-separated, empty = all processes)
 - `--exclude-processes`: Process IDs to exclude (space-separated, empty = none)
 - `--mute`: Mute processes being tapped
+- `--stereo`: Record in stereo
 - `--sample-rate`: Target sample rate (8000, 16000, 22050, 24000, 32000, 44100, 48000)
 - `--chunk-duration`: Audio chunk duration in seconds [default: 0.2, max: 5.0]
 
 ## Permissions
 
-There is no provision in the code to pre-emptively check for the required `NSAudioCaptureUsageDescription` permission,
+There is no provision in the code to pre-emptively check for the required `NSAudioCaptureUsageDescription` permission, so you'll be prompted the first time AudioTee tries to record anything. Note that some terminal emulators like iTerm don't always prompt for these permissions (though the macOS builtin terminal definitely does), so you might need to grant them ahead of time if audiotee runs but never records anything.
-so you'll be prompted the first time AudioTee tries to record anything. If you want to check and/or request permissions ahead of time, check out [AudioCap's clever TCC probing approach](https://github.com/insidegui/AudioCap/blob/main/AudioCap/ProcessTap/AudioRecordingPermission.swift). Note that some terminal emulators like
-iTerm don't always prompt for these permissions (the macOS builtin terminal definitely does), so you
-might need to grant them ahead of time if audiotee looks like it's running but never records anything.
 
-## References
+If you want to check and/or request permissions ahead of time, check out [AudioCap's fantastic TCC probing approach](https://github.com/insidegui/AudioCap/blob/main/AudioCap/ProcessTap/AudioRecordingPermission.swift). 
+
+## References / useful links
 
 - [Apple Core Audio Taps Documentation](https://developer.apple.com/documentation/coreaudio/capturing-system-audio-with-core-audio-taps)
 - [AudioCap Implementation](https://github.com/insidegui/AudioCap)
+- [AudioTee.js](https://github.com/makeusabrew/audioteejs)
 
 ## License
 

Sources/AudioTeeCLI/AudioTee.swift

@@ -1,3 +1,4 @@
+import AudioTeeCore
 import CoreAudio
 import Foundation
 
@@ -5,8 +6,10 @@ struct AudioTee {
   var includeProcesses: [Int32] = []
   var excludeProcesses: [Int32] = []
   var mute: Bool = false
+  var stereo: Bool = false
   var sampleRate: Double?
   var chunkDuration: Double = 0.2
+  var flush: Bool = false
 
   init() {}
 
@@ -30,6 +33,7 @@ struct AudioTee {
           audiotee --include-processes 1234 5678 9012  # Tap only these processes
           audiotee --exclude-processes 1234 5678       # Tap everything except these
           audiotee --mute                       # Mute processes being tapped
+          audiotee --flush                      # Flush stdout after each chunk
         """
     )
 
@@ -40,6 +44,8 @@ struct AudioTee {
     parser.addArrayOption(
       name: "exclude-processes", help: "Process IDs to exclude (space-separated)")
     parser.addFlag(name: "mute", help: "Mute processes being tapped")
+    parser.addFlag(name: "stereo", help: "Records in stereo")
+    parser.addFlag(name: "flush", help: "Flush stdout after each audio chunk (reduces latency when piping)")
     parser.addOption(
       name: "sample-rate",
       help: "Target sample rate (8000, 16000, 22050, 24000, 32000, 44100, 48000)")
@@ -56,6 +62,8 @@ struct AudioTee {
       audioTee.includeProcesses = try parser.getArrayValue("include-processes", as: Int32.self)
       audioTee.excludeProcesses = try parser.getArrayValue("exclude-processes", as: Int32.self)
       audioTee.mute = parser.getFlag("mute")
+      audioTee.stereo = parser.getFlag("stereo")
+      audioTee.flush = parser.getFlag("flush")
       audioTee.sampleRate = try parser.getOptionalValue("sample-rate", as: Double.self)
       audioTee.chunkDuration = try parser.getValue("chunk-duration", as: Double.self)
 
@@ -107,7 +115,8 @@ struct AudioTee {
     let tapConfig = TapConfiguration(
       processes: processes,
       muteBehavior: mute ? .muted : .unmuted,
-      isExclusive: isExclusive
+      isExclusive: isExclusive,
+      isMono: !stereo
     )
 
     let audioTapManager = AudioTapManager()
@@ -132,7 +141,7 @@ struct AudioTee {
       throw ExitCode.failure
     }
 
-    let outputHandler = BinaryAudioOutputHandler()
+    let outputHandler = BinaryAudioOutputHandler(flushAfterWrite: flush)
     let recorder = AudioRecorder(
       deviceID: deviceID, outputHandler: outputHandler, convertToSampleRate: sampleRate,
       chunkDuration: chunkDuration)

Sources/AudioTeeCLI/main.swift

@@ -1,3 +1,4 @@
+import AudioTeeCore
 import AudioToolbox
 import Foundation
 

Sources/AudioTeeCore/Core/AudioBuffer.swift

@@ -96,12 +96,10 @@ public class AudioBuffer {
 
     availableBytes -= bytesPerChunk
 
-    let packet = AudioPacket(
+    return AudioPacket(
       timestamp: Date(),
       duration: chunkDuration,
-      rawAudioData: chunkData
+      data: chunkData
     )
-
-    return packet
   }
 }

Sources/AudioTeeCore/Core/AudioFormatConverter.swift

@@ -54,7 +54,7 @@ public class AudioFormatConverter {
   }
 
   public func transform(_ packet: AudioPacket) -> AudioPacket {
-    let inputData = packet.rawAudioData
+    let inputData = packet.data
 
     // Calculate frame counts
     let inputFrameCount =
@@ -119,16 +119,10 @@ public class AudioFormatConverter {
     return AudioPacket(
       timestamp: packet.timestamp,
       duration: packet.duration,
-      rawAudioData: outputData
+      data: outputData
     )
   }
-}
 
-// MARK: - Convenience Constructors
-
-extension AudioFormatConverter {
-  /// Create a converter to a specific sample rate with mono PCM 16-bit output
-  /// Since the tap already converts to mono, we hardcode channels to 1
   public static func toSampleRate(
     _ sampleRate: Double, from sourceFormat: AudioStreamBasicDescription
   ) throws -> AudioFormatConverter {
@@ -136,26 +130,17 @@ extension AudioFormatConverter {
     targetFormat.mSampleRate = sampleRate
     targetFormat.mFormatID = kAudioFormatLinearPCM
     targetFormat.mFormatFlags = kAudioFormatFlagIsPacked | kAudioFormatFlagIsSignedInteger
-    targetFormat.mBytesPerPacket = 2
     targetFormat.mFramesPerPacket = 1
-    targetFormat.mBytesPerFrame = 2
-    targetFormat.mChannelsPerFrame = 1  // Always mono since tap handles this
     targetFormat.mBitsPerChannel = 16
+    targetFormat.mChannelsPerFrame = sourceFormat.mChannelsPerFrame
+    targetFormat.mBytesPerFrame =
+      (targetFormat.mBitsPerChannel / 8) * sourceFormat.mChannelsPerFrame
+    targetFormat.mBytesPerPacket = targetFormat.mFramesPerPacket * targetFormat.mBytesPerFrame
 
     return try AudioFormatConverter(sourceFormat: sourceFormat, targetFormat: targetFormat)
   }
 
-  /// Common sample rates for validation
-  public static let supportedSampleRates: [Double] = [
-    8000, 16000, 22050, 24000, 32000, 44100, 48000,
-  ]
-
-  /// Validate if a sample rate is supported
   public static func isValidSampleRate(_ sampleRate: Double) -> Bool {
-    return supportedSampleRates.contains(sampleRate)
+    return [8000, 16000, 22050, 24000, 32000, 44100, 48000].contains(sampleRate)
   }
 }
-
-// MARK: - Error Types
-
-// AudioConverterError moved to Sources/Core/Errors/AudioTeeErrors.swift

Sources/AudioTeeCore/Core/AudioPacket.swift

@@ -3,15 +3,15 @@ import Foundation
 public struct AudioPacket {
   public let timestamp: Date
   public let duration: Double
-  public let rawAudioData: Data
+  public let data: Data
 
   public init(
     timestamp: Date,
     duration: Double,
-    rawAudioData: Data
+    data: Data
   ) {
     self.timestamp = timestamp
     self.duration = duration
-    self.rawAudioData = rawAudioData
+    self.data = data
   }
 }

Sources/AudioTeeCore/Core/AudioRecorder.swift

@@ -5,24 +5,23 @@ import Foundation
 public class AudioRecorder {
   private var deviceID: AudioObjectID
   private var ioProcID: AudioDeviceIOProcID?
-  private var sourceFormat: AudioStreamBasicDescription?
+  private var finalFormat: AudioStreamBasicDescription!
-  private var finalFormat: AudioStreamBasicDescription?
   private var audioBuffer: AudioBuffer?
   private var outputHandler: AudioOutputHandler
   private var converter: AudioFormatConverter?
-  private var chunkDuration: Double
 
-  init(
+  public init(
     deviceID: AudioObjectID, outputHandler: AudioOutputHandler, convertToSampleRate: Double? = nil,
     chunkDuration: Double = 0.2
   ) {
     self.deviceID = deviceID
     self.outputHandler = outputHandler
-    self.chunkDuration = chunkDuration
 
     // Get source format and set up conversion if requested
     let sourceFormat = AudioFormatManager.getDeviceFormat(deviceID: deviceID)
-    self.sourceFormat = sourceFormat
+
+    // Set up the audio buffer using source format and configurable chunk duration
+    self.audioBuffer = AudioBuffer(format: sourceFormat, chunkDuration: chunkDuration)
 
     if let targetSampleRate = convertToSampleRate {
       // Validate sample rate
@@ -52,23 +51,15 @@ public class AudioRecorder {
     }
   }
 
-  func startRecording() {
+  public func startRecording() {
     Logger.debug("Starting audio recording")
 
-    guard let sourceFormat = sourceFormat, let finalFormat = finalFormat else {
+    // Log format info and send metadata for final format
-      fatalError("Audio formats not initialized")
-    }
-
-    // Set up the audio buffer using source format and configurable chunk duration
-    self.audioBuffer = AudioBuffer(format: sourceFormat, chunkDuration: chunkDuration)
-
-    // Log format info and send metadata for FINAL format
     AudioFormatManager.logFormatInfo(finalFormat)
     let metadata = AudioFormatManager.createMetadata(for: finalFormat)
     outputHandler.handleMetadata(metadata)
     outputHandler.handleStreamStart()
 
-    // Set up and start the IO proc
     setupAndStartIOProc()
 
     Logger.info("Audio device started successfully")
@@ -116,24 +107,23 @@ public class AudioRecorder {
     let audioData = Data(bytes: firstBuffer.mData!, count: Int(firstBuffer.mDataByteSize))
     audioBuffer?.append(audioData)
 
+    processAudioBuffer()
+
+    return noErr
+  }
+
+  public func stopRecording() {
+    processAudioBuffer()
+    outputHandler.handleStreamStop()
+    cleanupIOProc()
+  }
+
+  private func processAudioBuffer() {
     // Process and send complete chunks, applying conversion if needed
     audioBuffer?.processChunks().forEach { packet in
       let processedPacket = converter?.transform(packet) ?? packet
       outputHandler.handleAudioPacket(processedPacket)
     }
-
-    return noErr
-  }
-
-  func stopRecording() {
-    // Send any remaining buffered audio, applying conversion if needed
-    audioBuffer?.processChunks().forEach { packet in
-      let processedPacket = converter?.transform(packet) ?? packet
-      outputHandler.handleAudioPacket(processedPacket)
-    }
-
-    outputHandler.handleStreamStop()
-    cleanupIOProc()
   }
 
   private func cleanupIOProc() {

Sources/AudioTeeCore/Core/AudioTapManager.swift

@@ -3,13 +3,11 @@ import AudioToolbox
 import CoreAudio
 import Foundation
 
-class AudioTapManager {
+public class AudioTapManager {
   private var tapID: AudioObjectID?
   private var deviceID: AudioObjectID?
 
-  init() {
+  public init() {}
-    // Empty init - setup happens in setupAudioTap()
-  }
   
   deinit {
     Logger.debug("Cleaning up audio tap manager")
@@ -26,7 +24,7 @@ class AudioTapManager {
   }
 
   /// Sets up the audio tap and aggregate device
-  func setupAudioTap(with config: TapConfiguration) throws {
+  public func setupAudioTap(with config: TapConfiguration) throws {
     Logger.debug("Setting up audio tap manager")
 
     tapID = try createSystemAudioTap(with: config)
@@ -42,34 +40,30 @@ class AudioTapManager {
   }
 
   /// Returns the aggregate device ID for recording
-  func getDeviceID() -> AudioObjectID? {
+  public func getDeviceID() -> AudioObjectID? {
     return deviceID
   }
 
   private func createSystemAudioTap(with config: TapConfiguration) throws -> AudioObjectID {
     Logger.debug("Creating tap description")
-    // Create a tap description
     let description = CATapDescription()
 
-    // Configure the tap to capture all system audio
     description.name = "audiotee-tap"
     description.processes = try translatePIDsToProcessObjects(config.processes)  // Properly translate PIDs
     description.isPrivate = true
     description.muteBehavior = config.muteBehavior.coreAudioValue
     description.isMixdown = true
-    description.isMono = true
+    description.isMono = config.isMono
     description.isExclusive = config.isExclusive
-    description.deviceUID = nil // system default
+    description.deviceUID = nil  // system default
-    description.stream = 0 // first stream of output device
+    description.stream = 0  // first stream of output device
 
     Logger.debug(
       "Tap description configured",
       context: [
         "name": description.name,
         "processes": String(describing: config.processes),
-        "private": String(description.isPrivate),
         "mute": String(describing: description.muteBehavior),
-        "mixdown": String(description.isMixdown),
         "mono": String(description.isMono),
         "exclusive": String(description.isExclusive),
       ])

Sources/AudioTeeCore/Core/TapConfiguration.swift

@@ -2,10 +2,12 @@ public struct TapConfiguration {
   public let processes: [Int32]
   public let muteBehavior: TapMuteBehavior
   public let isExclusive: Bool
+  public let isMono: Bool
 
-  public init(processes: [Int32], muteBehavior: TapMuteBehavior, isExclusive: Bool) {
+  public init(processes: [Int32], muteBehavior: TapMuteBehavior, isExclusive: Bool, isMono: Bool) {
     self.processes = processes
     self.muteBehavior = muteBehavior
     self.isExclusive = isExclusive
+    self.isMono = isMono
   }
 }

Sources/AudioTeeCore/Output/AudioOutputProtocol.swift

@@ -1,4 +1,3 @@
-
 import Foundation
 
 /// Protocol for handling audio output in different formats

Sources/AudioTeeCore/Output/BinaryOutputHandler.swift

@@ -1,12 +1,17 @@
 import Foundation
 
-/// Binary output with JSON headers (pipe-optimised)
 public class BinaryAudioOutputHandler: AudioOutputHandler {
-  public init() {}
+  private let flushAfterWrite: Bool
 
+  public init(flushAfterWrite: Bool = false) {
+    self.flushAfterWrite = flushAfterWrite
+  }
   public func handleAudioPacket(_ packet: AudioPacket) {
     // Write raw binary audio data directly to stdout
-    FileHandle.standardOutput.write(packet.rawAudioData)
+    FileHandle.standardOutput.write(packet.data)
+    if flushAfterWrite {
+      fflush(stdout)
+    }
   }
 
   public func handleMetadata(_ metadata: AudioStreamMetadata) {

Sources/AudioTeeCore/Output/MessageType.swift

@@ -7,9 +7,6 @@ public enum MessageType: String, Codable {
   case streamStart = "stream_start"
   case streamStop = "stream_stop"
 
-  // Audio data
-  case audio
-
   // Logging
   case info
   case error

Sources/AudioTeeCore/Utils/Utils.swift

@@ -89,9 +89,9 @@ func translatePIDsToProcessObjects(_ pids: [Int32]) throws -> [AudioObjectID] {
 }
 
 extension String {
-    func print(to fileHandle: FileHandle) {
+  func print(to fileHandle: FileHandle) {
-        if let data = (self + "\n").data(using: .utf8) {
+    if let data = (self + "\n").data(using: .utf8) {
-            fileHandle.write(data)
+      fileHandle.write(data)
-        }
     }
+  }
 }

Tests/AudioTeeCoreTests/AudioPacketTests.swift

@@ -0,0 +1,30 @@
+import XCTest
+@testable import AudioTeeCore
+
+final class AudioPacketTests: XCTestCase {
+  func testPacketCreation() {
+    let timestamp = Date()
+    let duration = 1.0
+    let data = Data([0x01, 0x02, 0x03, 0x04])
+    
+    let packet = AudioPacket(
+      timestamp: timestamp,
+      duration: duration,
+      data: data
+    )
+    
+    XCTAssertEqual(packet.timestamp, timestamp)
+    XCTAssertEqual(packet.duration, duration)
+    XCTAssertEqual(packet.data, data)
+  }
+  
+  func testPacketDataSize() {
+    let packet = AudioPacket(
+      timestamp: Date(),
+      duration: 0.5,
+      data: Data(repeating: 0xFF, count: 1024)
+    )
+    
+    XCTAssertEqual(packet.data.count, 1024)
+  }
+}