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

@@ -8,7 +8,37 @@ let package = Package(
   platforms: [
     .macOS("14.2")
   ],
+  products: [
+    // Library that can be imported by other packages
+    .library(
+      name: "AudioTeeCore",
+      targets: ["AudioTeeCore"]
+    ),
+    // CLI executable
+    .executable(
+      name: "audiotee",
+      targets: ["AudioTeeCLI"]
+    )
+  ],
   targets: [
-        .executableTarget(name: "audiotee")
+    // 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

@@ -1,10 +1,22 @@
 # AudioTee
 
-AudioTee captures your Mac's system audio output and writes it in PCM encoded chunks to `stdout` at regular intervals, either in base64-encoded JSON (good for humans, easy on terminals) or binary (good for other programs). It uses 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, visualize it, etc.
+**⚠️ API Instability Warning: The AudioTee API is unstable at present and subject to change without notice.**
 
-By default, it taps the audio output from **all** running process and selects the most appropriate audio chunk output format to use based on the presence of a tty. 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.
+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:
 
-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.
+```bash
+/path/to/audiotee > output.pcm
+```
+
+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.
+
+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.
+
+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.
 
@@ -16,7 +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 base64-encoded chunks of it to your terminal every 200ms:
+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
@@ -24,7 +36,17 @@ cd audiotee
 swift run
 ```
 
-If you're not playing audio when you run it, you'll just see packets full of `AAAAA...` - the base64 version of a bunch of zeroes.
+More usefully, you can redirect `stdout` to a file:
+
+```bash
+swift run audiotee --sample-rate 16000 > output.pcm
+```
+
+Which you can play back using something like `ffplay`:
+
+```bash
+ffplay -f s16le -ar 16000 output.pcm
+```
 
 ## Build
 
@@ -40,23 +62,29 @@ swift build -c release
 Replace the path below with `.build/<arch>/<target>/audiotee`, e.g. `build/arm64-apple-macosx/release/audiotee` for a release build on Apple Silicon.
 
 ```bash
-# Auto-detect output format (JSON in terminal, binary when piped)
+# Write raw PCM audio to stdout (logs go to stderr)
 ./audiotee
 
-# Always use JSON format (terminal-safe)
-./audiotee --format json
+# Redirect audio to a file
+./audiotee > output.pcm
 
-# Always use binary format (pipe-optimised)
-./audiotee --format binary
+# Pipe to another program
+./audiotee | your_audio_processing_tool
+
+# Redirect logs as well
+./audiotee > captured_audio.pcm 2> audiotee.log
 ```
 
 ### Audio conversion
 
-Note that performing 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 in any case it's a behaviour worth being aware of.
+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 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
@@ -94,162 +122,51 @@ Note that trying to include or exclude a PID which isn't currently playing audio
 ./audiotee --chunk-duration 0.1
 ```
 
-## Output formats
+## Output
 
-AudioTee supports two output formats optimised for different use cases:
+AudioTee writes raw PCM audio data directly to `stdout` in chunks. All logging, metadata, and status information is written to `stderr`.
 
-### JSON format (`--format json` or auto in terminal)
+### Audio format
 
-JSON messages to stdout, one per line. Audio data is base64-encoded for terminal safety.
+- **Format**: Raw PCM audio data
+- **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
+- **Chunk duration**: 200ms by default (configurable)
 
-### Binary format (`--format binary` or auto when piped)
+### Logs and monitoring
 
-JSON metadata lines followed by raw binary audio data. More efficient for piping to other processes.
+All program logs are written to `stderr` and can be captured separately:
 
-## Protocol
+```bash
+# Capture audio and logs separately
+./audiotee > audio.pcm 2> audiotee.log
 
-### Message types
-
-All messages (except raw binary audio chunks) follow this envelope structure:
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "...",
-  "data": { ... }
-}
+# View logs in real-time while capturing audio
+./audiotee > audio.pcm 2>&1 | grep "AudioTee"
 ```
 
-#### 1. Metadata
-
-Sent once at startup to describe the audio format:
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "metadata",
-  "data": {
-    "sample_rate": 48000,
-    "channels_per_frame": 1,
-    "bits_per_channel": 32,
-    "is_float": true,
-    "capture_mode": "audio",
-    "device_name": null,
-    "device_uid": null,
-    "encoding": "pcm_f32le"
-  }
-}
-```
-
-#### 2. Stream start
-
-Indicates audio data will follow:
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "stream_start",
-  "data": null
-}
-```
-
-#### 3. Audio data
-
-**JSON format:**
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "audio",
-  "data": {
-    "timestamp": "2024-03-21T15:30:45.123Z",
-    "duration": 0.2,
-    "peak_amplitude": 0.45,
-    "audio_data": "base64_encoded_raw_audio..."
-  }
-}
-```
-
-**Binary format:**
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "audio",
-  "data": {
-    "timestamp": "2024-03-21T15:30:45.123Z",
-    "duration": 0.2,
-    "peak_amplitude": 0.45,
-    "audio_length": 9600
-  }
-}
-```
-
-_Followed immediately by 9600 bytes of raw binary audio data_
-
-#### 4. Stream stop
-
-Sent when recording stops:
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "stream_stop",
-  "data": null
-}
-```
-
-#### 5. Log messages
-
-Info, error, and debug messages (useful for monitoring):
-
-```json
-{
-  "timestamp": "2024-03-21T15:30:45.123Z",
-  "message_type": "info",
-  "data": {
-    "message": "Starting AudioTee...",
-    "context": { "output_format": "auto" }
-  }
-}
-```
-
-### Consuming output
-
-**JSON format:**
-
-1. Parse each line as JSON using the envelope structure
-2. Use `metadata` message to understand the audio format
-3. For `audio` messages, decode `audio_data` from base64 to get raw PCM data
-4. Do something with each chunk of data
-
-**Binary format:**
-
-1. Parse JSON metadata lines using the envelope structure
-2. Use `metadata` message to understand the audio format
-3. For `audio` messages, read `audio_length` bytes of raw binary data after the JSON line
-4. Do something with each chunk of data
-
-**Note**: binary is actually a mixed mode; JSON during boot, JSON packet header information preceding each binary chunk.
-
 ## Command Line options
 
-- `--format, -f`: Output format (`json`, `binary`, `auto`) [default: `auto`]
 - `--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,
-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).
+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.
 
-## 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/ArgumentParser.swift

@@ -189,11 +189,6 @@ class SimpleArgumentParser {
         throw ArgumentParserError.invalidValue(optionName, value)
       }
       return doubleValue as! T
-    } else if type == OutputFormat.self {
-      guard let format = OutputFormat(rawValue: value) else {
-        throw ArgumentParserError.invalidValue(optionName, value)
-      }
-      return format as! T
     }
 
     throw ArgumentParserError.invalidValue(optionName, value)

Sources/AudioTeeCLI/AudioTee.swift

@@ -1,13 +1,15 @@
+import AudioTeeCore
 import CoreAudio
 import Foundation
 
 struct AudioTee {
-  var format: OutputFormat = .auto
   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() {}
 
@@ -18,11 +20,6 @@ struct AudioTee {
       discussion: """
         AudioTee captures system audio using Core Audio taps and streams it as structured output.
 
-        Output formats:
-        • json: Base64-encoded audio in JSON messages (safe for terminals)
-        • binary: Raw binary audio with JSON metadata headers (efficient for pipes)
-        • auto: Automatically choose based on whether stdout is a terminal (default)
-
         Process filtering:
         • include-processes: Only tap specified process IDs (empty = all processes)
         • exclude-processes: Tap all processes except specified ones
@@ -30,25 +27,25 @@ struct AudioTee {
 
         Examples:
           audiotee                              # Auto format, tap all processes
-          audiotee --format=json                # Always use JSON format
-          audiotee --format=binary              # Always use binary format
-          audiotee --sample-rate=16000          # Convert to 16kHz mono for ASR
-          audiotee --sample-rate=8000           # Convert to 8kHz for telephony
+          audiotee --sample-rate 16000          # Convert to 16kHz mono for ASR
+          audiotee --sample-rate 8000           # Convert to 8kHz for telephony
           audiotee --include-processes 1234     # Only tap process 1234
           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
         """
     )
 
     // Configure arguments
-    parser.addOption(name: "format", shortName: "f", help: "Output format", defaultValue: "auto")
     parser.addArrayOption(
       name: "include-processes",
       help: "Process IDs to include (space-separated, empty = all processes)")
     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)")
@@ -62,10 +59,11 @@ struct AudioTee {
       var audioTee = AudioTee()
 
       // Extract values
-      audioTee.format = try parser.getValue("format", as: OutputFormat.self)
       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)
 
@@ -102,7 +100,6 @@ struct AudioTee {
     setupSignalHandlers()
 
     Logger.info("Starting AudioTee...")
-    Logger.debug("Using output format: \(format)")
 
     // Validate chunk duration
     guard chunkDuration > 0 && chunkDuration <= 5.0 else {
@@ -118,7 +115,8 @@ struct AudioTee {
     let tapConfig = TapConfiguration(
       processes: processes,
       muteBehavior: mute ? .muted : .unmuted,
-      isExclusive: isExclusive
+      isExclusive: isExclusive,
+      isMono: !stereo
     )
 
     let audioTapManager = AudioTapManager()
@@ -143,7 +141,7 @@ struct AudioTee {
       throw ExitCode.failure
     }
 
-    let outputHandler = createOutputHandler(for: format)
+    let outputHandler = BinaryAudioOutputHandler(flushAfterWrite: flush)
     let recorder = AudioRecorder(
       deviceID: deviceID, outputHandler: outputHandler, convertToSampleRate: sampleRate,
       chunkDuration: chunkDuration)
@@ -172,17 +170,6 @@ struct AudioTee {
     }
   }
 
-  private func createOutputHandler(for format: OutputFormat) -> AudioOutputHandler {
-    switch format {
-    case .json:
-      return JSONAudioOutputHandler()
-    case .binary:
-      return BinaryAudioOutputHandler()
-    case .auto:
-      return AutoAudioOutputHandler()
-    }
-  }
-
   private func convertProcessFlags() -> ([Int32], Bool) {
     if !includeProcesses.isEmpty {
       // Include specific processes only
@@ -200,7 +187,7 @@ struct AudioTee {
 // Helper for stderr output
 var standardError = FileHandle.standardError
 
-extension FileHandle: @retroactive TextOutputStream {
+extension FileHandle: TextOutputStream {
   public func write(_ string: String) {
     let data = Data(string.utf8)
     self.write(data)

Sources/AudioTeeCLI/main.swift

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

Sources/AudioTeeCore/Core/AudioBuffer.swift

@@ -0,0 +1,105 @@
+import CoreAudio
+import Foundation
+
+public class AudioBuffer {
+  private var buffer: [UInt8]
+  private var writeIndex: Int = 0
+  private var readIndex: Int = 0
+  private var availableBytes: Int = 0
+  private let maxBufferSize: Int
+
+  private let bytesPerChunk: Int
+  private let chunkDuration: Double
+
+  public init(format: AudioStreamBasicDescription, chunkDuration: Double = 0.2) {
+
+    // Pre-calculate chunk parameters
+    let bytesPerFrame = Int(format.mBytesPerFrame)
+    let samplesPerChunk = Int(format.mSampleRate * chunkDuration)
+    self.bytesPerChunk = samplesPerChunk * bytesPerFrame
+    self.chunkDuration = Double(samplesPerChunk) / format.mSampleRate
+
+    // Calculate max buffer size to hold ~10 seconds of audio, way more than the maximum we allow
+    let bytesPerSecond = Int(format.mSampleRate) * bytesPerFrame
+    self.maxBufferSize = bytesPerSecond * 10
+
+    // Pre-allocated ring buffer
+    self.buffer = Array(repeating: 0, count: maxBufferSize)
+  }
+
+  public func append(_ data: Data) {
+    guard availableBytes + data.count <= maxBufferSize else {
+      Logger.error(
+        "Audio buffer overflow",
+        context: [
+          "requested": String(data.count),
+          "available": String(maxBufferSize - availableBytes),
+        ])
+      return
+    }
+
+    data.withUnsafeBytes { bytes in
+      let sourceBytes = bytes.bindMemory(to: UInt8.self)
+      let dataSize = sourceBytes.count
+
+      // Check if we can copy in one block (no wrap-around)
+      if writeIndex + dataSize <= maxBufferSize {
+        // only one write needed
+        buffer.replaceSubrange(writeIndex..<writeIndex + dataSize, with: sourceBytes)
+        writeIndex = (writeIndex + dataSize) % maxBufferSize
+      } else {
+        // two writes needed due to wrap-around
+        let firstChunkSize = maxBufferSize - writeIndex
+        let secondChunkSize = dataSize - firstChunkSize
+
+        buffer.replaceSubrange(writeIndex..<maxBufferSize, with: sourceBytes.prefix(firstChunkSize))
+        buffer.replaceSubrange(0..<secondChunkSize, with: sourceBytes.suffix(secondChunkSize))
+
+        writeIndex = secondChunkSize
+      }
+    }
+
+    availableBytes += data.count
+  }
+
+  public func processChunks() -> [AudioPacket] {
+    var packets: [AudioPacket] = []
+
+    while let packet = nextChunk() {
+      packets.append(packet)
+    }
+
+    return packets
+  }
+
+  private func nextChunk() -> AudioPacket? {
+    // Check if we have enough data for a complete chunk
+    guard availableBytes >= bytesPerChunk else { return nil }
+
+    var chunkData = Data(capacity: bytesPerChunk)
+
+    // Check if we can copy in one block (no wrap-around)
+    if readIndex + bytesPerChunk <= maxBufferSize {
+      // one copy needed
+      chunkData.append(contentsOf: buffer[readIndex..<readIndex + bytesPerChunk])
+      readIndex = (readIndex + bytesPerChunk) % maxBufferSize
+    } else {
+      // two copies needed due to wrap-around
+      let firstChunkSize = maxBufferSize - readIndex
+      let secondChunkSize = bytesPerChunk - firstChunkSize
+
+      chunkData.append(contentsOf: buffer[readIndex..<maxBufferSize])
+      chunkData.append(contentsOf: buffer[0..<secondChunkSize])
+
+      readIndex = secondChunkSize
+    }
+
+    availableBytes -= bytesPerChunk
+
+    return AudioPacket(
+      timestamp: Date(),
+      duration: chunkDuration,
+      data: chunkData
+    )
+  }
+}

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 =
@@ -119,17 +119,10 @@ public class AudioFormatConverter {
     return AudioPacket(
       timestamp: packet.timestamp,
       duration: packet.duration,
-      peakAmplitude: packet.peakAmplitude,
-      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 {
@@ -137,26 +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

@@ -3,18 +3,15 @@ import Foundation
 public struct AudioPacket {
   public let timestamp: Date
   public let duration: Double
-  public let peakAmplitude: Float  // useful for level monitoring
-  public let rawAudioData: Data
+  public let data: Data
 
   public init(
     timestamp: Date,
     duration: Double,
-    peakAmplitude: Float,
-    rawAudioData: Data
+    data: Data
   ) {
     self.timestamp = timestamp
     self.duration = duration
-    self.peakAmplitude = peakAmplitude
-    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
@@ -52,29 +51,22 @@ public class AudioRecorder {
     }
   }
 
-  func startRecording() {
+  public func startRecording() {
     Logger.debug("Starting audio recording")
 
-    guard let sourceFormat = sourceFormat, let finalFormat = finalFormat else {
-      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
+    // 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")
   }
 
-  // FIXME: note to self, what about installTap? Would require audio engine and a node?
+  // Note to self, what about installTap? Would require audio engine and a node?
+  // No; AudioEngine.installTap() can only fire as often as 100ms. too slow for us
   private func setupAndStartIOProc() {
     Logger.debug("Creating IO proc")
     var status = AudioDeviceCreateIOProcID(
@@ -115,24 +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
-    if let finalPacket = audioBuffer?.flushRemaining() {
-      let processedPacket = converter?.transform(finalPacket) ?? finalPacket
-      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() {
-    // Empty init - setup happens in setupAudioTap()
-  }
+  public init() {}
   
   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)
@@ -42,22 +40,20 @@ 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.stream = 0  // first stream of output device
@@ -67,9 +63,7 @@ class AudioTapManager {
       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

@@ -1,18 +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) {
-    // Create metadata without the audio data
-    let metadata = BinaryPacketHeader(from: packet)
-
-    // Write JSON metadata line
-    Logger.writeMessage(.audio, data: metadata)
-
     // 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/Logger.swift

@@ -24,8 +24,8 @@ public class Logger {
     let message = Message(type: type, data: data)
     do {
       let jsonData = try jsonEncoder.encode(message)
-      FileHandle.standardOutput.write(jsonData)
-      FileHandle.standardOutput.write("\n".data(using: .utf8)!)
+      FileHandle.standardError.write(jsonData)
+      FileHandle.standardError.write("\n".data(using: .utf8)!)
     } catch {
       // TODO: handle at some point
     }

Sources/CLI/OutputFormat.swift

@@ -1,16 +0,0 @@
-enum OutputFormat: String, CaseIterable {
-  case json = "json"
-  case binary = "binary"
-  case auto = "auto"
-
-  var description: String {
-    switch self {
-    case .json:
-      return "Base64-encoded JSON (terminal-safe)"
-    case .binary:
-      return "Binary with JSON headers (pipe-optimised)"
-    case .auto:
-      return "Auto-detect based on TTY (default)"
-    }
-  }
-}

Sources/Core/AudioBuffer.swift

@@ -1,61 +0,0 @@
-import CoreAudio
-import Foundation
-
-public class AudioBuffer {
-  private var buffer = Data()
-  private let targetChunkDuration: Double
-  private let streamFormat: AudioStreamBasicDescription
-
-  public init(format: AudioStreamBasicDescription, chunkDuration: Double = 0.2) {
-    self.streamFormat = format
-    self.targetChunkDuration = chunkDuration
-  }
-
-  public func append(_ data: Data) {
-    buffer.append(data)
-  }
-
-  public func processChunks() -> [AudioPacket] {
-    var packets: [AudioPacket] = []
-
-    while let packet = nextChunk() {
-      packets.append(packet)
-    }
-
-    return packets
-  }
-
-  public func flushRemaining() -> AudioPacket? {
-    guard !buffer.isEmpty else { return nil }
-
-    let packet = AudioPacket(
-      timestamp: Date(),
-      duration: 0.0,  // Unknown duration for final chunk
-      peakAmplitude: 0.0,
-      rawAudioData: buffer
-    )
-
-    buffer.removeAll()
-    return packet
-  }
-
-  private func nextChunk() -> AudioPacket? {
-    let bytesPerFrame = Int(streamFormat.mBytesPerFrame)
-    let samplesPerChunk = Int(streamFormat.mSampleRate * targetChunkDuration)
-    let bytesPerChunk = samplesPerChunk * bytesPerFrame
-
-    guard buffer.count >= bytesPerChunk else { return nil }
-
-    let chunkData = buffer.prefix(bytesPerChunk)
-
-    let packet = AudioPacket(
-      timestamp: Date(),
-      duration: Double(samplesPerChunk) / streamFormat.mSampleRate,
-      peakAmplitude: 0.0,  // No analysis in raw mode
-      rawAudioData: Data(chunkData)
-    )
-
-    buffer.removeFirst(bytesPerChunk)
-    return packet
-  }
-}

Sources/Output/Handlers/AutoOutputHandler.swift

@@ -1,31 +0,0 @@
-import Foundation
-
-/// Auto-detecting output handler based on TTY
-public class AutoAudioOutputHandler: AudioOutputHandler {
-  private let handler: AudioOutputHandler
-
-  public init() {
-    // Auto-detect based on whether stdout is a terminal
-    if isatty(STDOUT_FILENO) != 0 {
-      handler = JSONAudioOutputHandler()
-    } else {
-      handler = BinaryAudioOutputHandler()
-    }
-  }
-
-  public func handleAudioPacket(_ packet: AudioPacket) {
-    handler.handleAudioPacket(packet)
-  }
-
-  public func handleMetadata(_ metadata: AudioStreamMetadata) {
-    handler.handleMetadata(metadata)
-  }
-
-  public func handleStreamStart() {
-    handler.handleStreamStart()
-  }
-
-  public func handleStreamStop() {
-    handler.handleStreamStop()
-  }
-}

Sources/Output/Handlers/JSONOutputHandler.swift

@@ -1,23 +0,0 @@
-import Foundation
-
-/// Base64-encoded JSON output (terminal-safe)
-public class JSONAudioOutputHandler: AudioOutputHandler {
-  public init() {}
-
-  public func handleAudioPacket(_ packet: AudioPacket) {
-    let jsonPacket = JSONAudioPacket(from: packet)
-    Logger.writeMessage(.audio, data: jsonPacket)
-  }
-
-  public func handleMetadata(_ metadata: AudioStreamMetadata) {
-    Logger.writeMessage(.metadata, data: metadata)
-  }
-
-  public func handleStreamStart() {
-    Logger.writeMessage(.streamStart, data: Optional<String>.none)
-  }
-
-  public func handleStreamStop() {
-    Logger.writeMessage(.streamStop, data: Optional<String>.none)
-  }
-}

Sources/Output/OutputPacketTypes.swift

@@ -1,45 +0,0 @@
-import Foundation
-
-/// JSON-serializable version of AudioPacket with base64-encoded audio data
-public struct JSONAudioPacket: Codable {
-  public let timestamp: Date
-  public let duration: Double
-  public let peakAmplitude: Float
-  public let audioData: String  // base64 encoded audio data
-
-  public enum CodingKeys: String, CodingKey {
-    case timestamp
-    case duration
-    case peakAmplitude = "peak_amplitude"
-    case audioData = "audio_data"
-  }
-
-  public init(from packet: AudioPacket) {
-    self.timestamp = packet.timestamp
-    self.duration = packet.duration
-    self.peakAmplitude = packet.peakAmplitude
-    self.audioData = packet.rawAudioData.base64EncodedString()
-  }
-}
-
-/// Metadata-only packet for binary output (without base64 audio data)
-public struct BinaryPacketHeader: Codable {
-  public let timestamp: Date
-  public let duration: Double
-  public let peakAmplitude: Float
-  public let audioLength: Int  // Length of raw audio data in bytes
-
-  public enum CodingKeys: String, CodingKey {
-    case timestamp
-    case duration
-    case peakAmplitude = "peak_amplitude"
-    case audioLength = "audio_length"
-  }
-
-  public init(from packet: AudioPacket) {
-    self.timestamp = packet.timestamp
-    self.duration = packet.duration
-    self.peakAmplitude = packet.peakAmplitude
-    self.audioLength = packet.rawAudioData.count
-  }
-}

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)
+  }
+}