diff --git a/Sources/AudioTeeCLI/AudioTee.swift b/Sources/AudioTeeCLI/AudioTee.swift
index 4835d5a..e7f8973 100644
--- a/Sources/AudioTeeCLI/AudioTee.swift
+++ b/Sources/AudioTeeCLI/AudioTee.swift
@@ -9,7 +9,6 @@ struct AudioTee {
   var stereo: Bool = false
   var sampleRate: Double?
   var chunkDuration: Double = 0.2
-  var flush: Bool = false
 
   init() {}
 
@@ -33,7 +32,6 @@ 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
         """
     )
 
@@ -45,7 +43,6 @@ struct AudioTee {
       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)")
@@ -63,7 +60,6 @@ struct AudioTee {
       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)
 
@@ -141,7 +137,7 @@ struct AudioTee {
       throw ExitCode.failure
     }
 
-    let outputHandler = BinaryAudioOutputHandler(flushAfterWrite: flush)
+    let outputHandler = BinaryAudioOutputHandler()
     let recorder = try AudioRecorder(
       deviceID: deviceID, outputHandler: outputHandler, convertToSampleRate: sampleRate,
       chunkDuration: chunkDuration)
diff --git a/Sources/AudioTeeCLI/BinaryOutputHandler.swift b/Sources/AudioTeeCLI/BinaryOutputHandler.swift
index 9f8a5b6..732b837 100644
--- a/Sources/AudioTeeCLI/BinaryOutputHandler.swift
+++ b/Sources/AudioTeeCLI/BinaryOutputHandler.swift
@@ -4,17 +4,19 @@ import Foundation
 /// CLI-specific output handler that writes raw PCM audio to stdout
 /// and lifecycle messages to stderr via the logger.
 class BinaryAudioOutputHandler: AudioOutputHandler {
-  private let flushAfterWrite: Bool
+  private let fd = STDOUT_FILENO
 
-  init(flushAfterWrite: Bool = false) {
-    self.flushAfterWrite = flushAfterWrite
-  }
-
-  func handleAudioPacket(_ packet: AudioPacket) {
-    // Write raw binary audio data directly to stdout
-    FileHandle.standardOutput.write(packet.data)
-    if flushAfterWrite {
-      fflush(stdout)
+  func handleAudioData(_ pointer: UnsafeRawPointer, count: Int) {
+    var written = 0
+    while written < count {
+      let result = write(fd, pointer.advanced(by: written), count - written)
+      if result >= 0 {
+        written += result
+      } else if errno == EINTR {
+        continue
+      } else {
+        break  // EPIPE, EIO, etc — consumer gone or real error
+      }
     }
   }
 
diff --git a/Sources/AudioTeeCore/Core/AudioBuffer.swift b/Sources/AudioTeeCore/Core/AudioBuffer.swift
index 10ef775..7b5c781 100644
--- a/Sources/AudioTeeCore/Core/AudioBuffer.swift
+++ b/Sources/AudioTeeCore/Core/AudioBuffer.swift
@@ -1,105 +1,121 @@
 import CoreAudio
 import Foundation
 
+/// Ring buffer for accumulating raw audio data and extracting fixed-size chunks.
+///
+/// Uses a raw heap-allocated pointer rather than Swift Array to avoid
+/// copy-on-write reference-count checks on every mutation. This buffer
+/// lives on the real-time audio IO thread and is never shared, so COW
+/// semantics are pure overhead.
 public class AudioBuffer {
-  private var buffer: [UInt8]
+  /// Raw heap-allocated ring buffer backing store.
+  private let buffer: UnsafeMutableRawPointer
+  /// Pre-allocated buffer for linearizing chunks that straddle the ring
+  /// buffer boundary. Avoids a heap allocation on the wrap-around path.
+  private let linearizationBuffer: UnsafeMutableRawPointer
   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 let bytesPerChunk: Int
 
   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
+    // Calculate max buffer size to hold ~10 seconds of audio (safety limit)
     let bytesPerSecond = Int(format.mSampleRate) * bytesPerFrame
     self.maxBufferSize = bytesPerSecond * 10
 
-    // Pre-allocated ring buffer
-    self.buffer = Array(repeating: 0, count: maxBufferSize)
+    // Allocate raw memory. We use UnsafeMutableRawPointer instead of [UInt8]
+    // to eliminate Swift Array's COW ref-count check on every write/read.
+    self.buffer = UnsafeMutableRawPointer.allocate(
+      byteCount: maxBufferSize,
+      alignment: MemoryLayout<UInt8>.alignment
+    )
+    buffer.initializeMemory(as: UInt8.self, repeating: 0, count: maxBufferSize)
+
+    self.linearizationBuffer = UnsafeMutableRawPointer.allocate(
+      byteCount: bytesPerChunk,
+      alignment: MemoryLayout<UInt8>.alignment
+    )
   }
 
-  public func append(_ data: Data) {
-    guard availableBytes + data.count <= maxBufferSize else {
+  deinit {
+    buffer.deallocate()
+    linearizationBuffer.deallocate()
+  }
+
+  /// Appends audio data directly from a raw pointer into the ring buffer.
+  /// This is the fast path used by the IO proc callback: one memcpy from
+  /// the Core Audio buffer into our ring buffer, with no intermediate
+  /// Data allocation.
+  public func append(from source: UnsafeRawPointer, count: Int) {
+    guard count >= 0 else {
+      AudioTeeLogging.logger.error(
+        "Audio buffer append called with negative count",
+        context: ["count": String(count)])
+      return
+    }
+
+    guard availableBytes + count <= maxBufferSize else {
       AudioTeeLogging.logger.error(
         "Audio buffer overflow",
         context: [
-          "requested": String(data.count),
+          "requested": String(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
+    if writeIndex + count <= maxBufferSize {
+      // Single contiguous write — no wrap-around needed
+      buffer.advanced(by: writeIndex).copyMemory(from: source, byteCount: count)
+      writeIndex = (writeIndex + count) % maxBufferSize
     } else {
-      // two copies needed due to wrap-around
-      let firstChunkSize = maxBufferSize - readIndex
-      let secondChunkSize = bytesPerChunk - firstChunkSize
+      // Two writes needed due to wrap-around at the end of the ring buffer
+      let firstChunkSize = maxBufferSize - writeIndex
+      let secondChunkSize = count - firstChunkSize
 
-      chunkData.append(contentsOf: buffer[readIndex..<maxBufferSize])
-      chunkData.append(contentsOf: buffer[0..<secondChunkSize])
+      buffer.advanced(by: writeIndex).copyMemory(from: source, byteCount: firstChunkSize)
+      buffer.copyMemory(from: source.advanced(by: firstChunkSize), byteCount: secondChunkSize)
 
-      readIndex = secondChunkSize
+      writeIndex = secondChunkSize
     }
 
-    availableBytes -= bytesPerChunk
+    availableBytes += count
+  }
 
-    return AudioPacket(
-      timestamp: Date(),
-      duration: chunkDuration,
-      data: chunkData
-    )
+  /// Calls `handler` once for each complete chunk available in the buffer.
+  /// The pointer passed to the handler is valid only for the duration of
+  /// that call. In the common (contiguous) case this points directly into
+  /// the ring buffer — zero copies. In the wrap-around case the chunk is
+  /// linearized into a pre-allocated scratch buffer — one memcpy, zero
+  /// heap allocations.
+  public func processChunks(_ handler: (UnsafeRawPointer, Int) -> Void) {
+    while availableBytes >= bytesPerChunk {
+      if readIndex + bytesPerChunk <= maxBufferSize {
+        // Contiguous: point directly into the ring buffer
+        handler(buffer.advanced(by: readIndex), bytesPerChunk)
+        readIndex = (readIndex + bytesPerChunk) % maxBufferSize
+      } else {
+        // Wrap-around: linearize into the pre-allocated scratch buffer
+        let firstChunkSize = maxBufferSize - readIndex
+        let secondChunkSize = bytesPerChunk - firstChunkSize
+
+        linearizationBuffer.copyMemory(
+          from: buffer.advanced(by: readIndex), byteCount: firstChunkSize)
+        linearizationBuffer.advanced(by: firstChunkSize).copyMemory(
+          from: buffer, byteCount: secondChunkSize)
+
+        handler(linearizationBuffer, bytesPerChunk)
+        readIndex = secondChunkSize
+      }
+
+      availableBytes -= bytesPerChunk
+    }
   }
 }
diff --git a/Sources/AudioTeeCore/Core/AudioFormatConverter.swift b/Sources/AudioTeeCore/Core/AudioFormatConverter.swift
index f8f7bae..5a52284 100644
--- a/Sources/AudioTeeCore/Core/AudioFormatConverter.swift
+++ b/Sources/AudioTeeCore/Core/AudioFormatConverter.swift
@@ -2,12 +2,22 @@ import AVFoundation
 import CoreAudio
 import Foundation
 
-/// Simple audio format converter using AVFoundation
+/// Audio format converter using AVFoundation's AVAudioConverter.
+///
+/// Pre-allocates input/output buffers on first use and reuses them across
+/// transform() calls. This eliminates two AVAudioPCMBuffer heap allocations
+/// per chunk — significant when chunks are small (50ms = 20 calls/sec).
 public class AudioFormatConverter {
   private let avConverter: AVAudioConverter
   private let sourceFormat: AVAudioFormat
   private let targetFormat: AVAudioFormat
 
+  /// Pre-allocated buffers reused across transform() calls. Lazily created
+  /// on first transform() since we need the actual input frame count to
+  /// size them correctly.
+  private var cachedInputBuffer: AVAudioPCMBuffer?
+  private var cachedOutputBuffer: AVAudioPCMBuffer?
+
   public init(sourceFormat: AudioStreamBasicDescription, targetFormat: AudioStreamBasicDescription)
     throws
   {
@@ -58,51 +68,96 @@ public class AudioFormatConverter {
     return targetFormat.streamDescription.pointee
   }
 
-  public func transform(_ packet: AudioPacket) -> AudioPacket {
-    let inputData = packet.data
+  /// Returns pre-allocated input and output buffers sized for the given
+  /// input frame count. Allocates once on first call; reuses on subsequent
+  /// calls when capacity is sufficient. Re-allocates if a larger frame
+  /// count arrives (shouldn't happen with fixed chunk sizes, but handled
+  /// gracefully).
+  private func getBuffers(inputFrameCount: AVAudioFrameCount)
+    -> (input: AVAudioPCMBuffer, output: AVAudioPCMBuffer)?
+  {
+    // ceil() prevents float-to-int truncation from undersizing the buffer
+    // by one frame (e.g. 3199.9999 → 3199 instead of 3200).
+    let outputFrameCount = AVAudioFrameCount(
+      ceil(Double(inputFrameCount) * (targetFormat.sampleRate / sourceFormat.sampleRate))
+    )
 
-    // Calculate frame counts
-    let inputFrameCount =
-      inputData.count / Int(sourceFormat.streamDescription.pointee.mBytesPerFrame)
-    let outputFrameCount = Int(
-      Double(inputFrameCount) * (targetFormat.sampleRate / sourceFormat.sampleRate))
+    // Reuse cached buffers if they have sufficient capacity
+    if let inputBuf = cachedInputBuffer,
+      let outputBuf = cachedOutputBuffer,
+      inputBuf.frameCapacity >= inputFrameCount,
+      outputBuf.frameCapacity >= outputFrameCount
+    {
+      // Reset frame lengths for reuse — the underlying memory is retained,
+      // we just tell AVAudioPCMBuffer how many frames are valid this time.
+      inputBuf.frameLength = 0
+      outputBuf.frameLength = 0
+      return (inputBuf, outputBuf)
+    }
 
-    // Create input buffer
+    // Allocate new buffers (first call, or unexpected capacity increase)
     guard
-      let inputBuffer = AVAudioPCMBuffer(
-        pcmFormat: sourceFormat, frameCapacity: AVAudioFrameCount(inputFrameCount))
+      let inputBuf = AVAudioPCMBuffer(
+        pcmFormat: sourceFormat, frameCapacity: inputFrameCount)
     else {
       AudioTeeLogging.logger.error("Failed to create input buffer")
-      return packet
+      return nil
     }
 
-    // Copy input data to buffer
-    inputData.withUnsafeBytes { bytes in
-      let dest = inputBuffer.audioBufferList.pointee.mBuffers.mData!
-      dest.copyMemory(from: bytes.baseAddress!, byteCount: inputData.count)
-    }
-    inputBuffer.frameLength = AVAudioFrameCount(inputFrameCount)
-
-    // Create output buffer
     guard
-      let outputBuffer = AVAudioPCMBuffer(
-        pcmFormat: targetFormat, frameCapacity: AVAudioFrameCount(outputFrameCount))
+      let outputBuf = AVAudioPCMBuffer(
+        pcmFormat: targetFormat, frameCapacity: outputFrameCount)
     else {
       AudioTeeLogging.logger.error("Failed to create output buffer")
-      return packet
+      return nil
     }
 
-    // Perform conversion - simpler approach
+    // Cache for reuse on subsequent calls
+    cachedInputBuffer = inputBuf
+    cachedOutputBuffer = outputBuf
+
+    AudioTeeLogging.logger.debug(
+      "Allocated converter buffers",
+      context: [
+        "input_frame_capacity": String(inputFrameCount),
+        "output_frame_capacity": String(outputFrameCount),
+      ])
+
+    return (inputBuf, outputBuf)
+  }
+
+  /// Converts audio data in-place through the pre-allocated converter buffers.
+  /// Calls `handler` with a pointer to the converted output, valid only for
+  /// the duration of that call. Returns false on failure (caller should
+  /// pass through the original data or drop it).
+  @discardableResult
+  public func transform(
+    from source: UnsafeRawPointer, count: Int,
+    handler: (UnsafeRawPointer, Int) -> Void
+  ) -> Bool {
+    let bytesPerFrame = Int(sourceFormat.streamDescription.pointee.mBytesPerFrame)
+    let inputFrameCount = AVAudioFrameCount(count / bytesPerFrame)
+
+    guard let (inputBuffer, outputBuffer) = getBuffers(inputFrameCount: inputFrameCount) else {
+      return false
+    }
+
+    // Copy source data into the reusable input buffer
+    let dest = inputBuffer.audioBufferList.pointee.mBuffers.mData!
+    dest.copyMemory(from: source, byteCount: count)
+    inputBuffer.frameLength = inputFrameCount
+
+    // Perform conversion — we do NOT call avConverter.reset() between
+    // calls because the resampler maintains internal state for continuity
+    // across chunks (avoiding discontinuity artifacts).
     var error: NSError?
 
     let status = avConverter.convert(to: outputBuffer, error: &error) {
       requestedPackets, outStatus in
-      // Always provide our input buffer and let converter manage it
       outStatus.pointee = .haveData
       return inputBuffer
     }
 
-    // Check if conversion produced output (regardless of status code)
     guard outputBuffer.frameLength > 0 else {
       AudioTeeLogging.logger.error(
         "Audio conversion produced no output",
@@ -112,20 +167,13 @@ public class AudioFormatConverter {
           "input_frames": String(inputBuffer.frameLength),
           "output_capacity": String(outputBuffer.frameCapacity),
         ])
-      return packet
+      return false
     }
 
-    // Extract converted data
-    let outputData = Data(
-      bytes: outputBuffer.audioBufferList.pointee.mBuffers.mData!,
-      count: Int(outputBuffer.frameLength * targetFormat.streamDescription.pointee.mBytesPerFrame))
-
-    // Return new packet with converted audio (keeping original metadata for simplicity)
-    return AudioPacket(
-      timestamp: packet.timestamp,
-      duration: packet.duration,
-      data: outputData
-    )
+    let outputCount = Int(
+      outputBuffer.frameLength * targetFormat.streamDescription.pointee.mBytesPerFrame)
+    handler(outputBuffer.audioBufferList.pointee.mBuffers.mData!, outputCount)
+    return true
   }
 
   public static func toSampleRate(
diff --git a/Sources/AudioTeeCore/Core/AudioFormatManager.swift b/Sources/AudioTeeCore/Core/AudioFormatManager.swift
index c59a19f..d31a878 100644
--- a/Sources/AudioTeeCore/Core/AudioFormatManager.swift
+++ b/Sources/AudioTeeCore/Core/AudioFormatManager.swift
@@ -3,7 +3,8 @@ import CoreAudio
 import Foundation
 
 public class AudioFormatManager {
-  public static func getDeviceFormat(deviceID: AudioObjectID) throws -> AudioStreamBasicDescription {
+  public static func getDeviceFormat(deviceID: AudioObjectID) throws -> AudioStreamBasicDescription
+  {
     // First, wait for the device to become alive/ready
     let deviceReadyTimeout = 2.0  // 2 seconds max wait
     let pollInterval = 0.1  // 100ms poll interval
@@ -49,7 +50,8 @@ public class AudioFormatManager {
         deviceID, &propertyAddress, 0, nil, &propertySize, &streamFormat)
 
       if status == noErr {
-        AudioTeeLogging.logger.debug("Successfully retrieved device format", context: ["attempt": String(attempt)])
+        AudioTeeLogging.logger.debug(
+          "Successfully retrieved device format", context: ["attempt": String(attempt)])
         return streamFormat
       }
 
diff --git a/Sources/AudioTeeCore/Core/AudioPacket.swift b/Sources/AudioTeeCore/Core/AudioPacket.swift
deleted file mode 100644
index 8db7d13..0000000
--- a/Sources/AudioTeeCore/Core/AudioPacket.swift
+++ /dev/null
@@ -1,17 +0,0 @@
-import Foundation
-
-public struct AudioPacket {
-  public let timestamp: Date
-  public let duration: Double
-  public let data: Data
-
-  public init(
-    timestamp: Date,
-    duration: Double,
-    data: Data
-  ) {
-    self.timestamp = timestamp
-    self.duration = duration
-    self.data = data
-  }
-}
diff --git a/Sources/AudioTeeCore/Core/AudioRecorder.swift b/Sources/AudioTeeCore/Core/AudioRecorder.swift
index ade0e6e..6d8dce2 100644
--- a/Sources/AudioTeeCore/Core/AudioRecorder.swift
+++ b/Sources/AudioTeeCore/Core/AudioRecorder.swift
@@ -36,7 +36,8 @@ public class AudioRecorder {
     if let targetSampleRate = convertToSampleRate {
       // Validate sample rate
       guard AudioFormatConverter.isValidSampleRate(targetSampleRate) else {
-        AudioTeeLogging.logger.error("Invalid sample rate", context: ["sample_rate": String(targetSampleRate)])
+        AudioTeeLogging.logger.error(
+          "Invalid sample rate", context: ["sample_rate": String(targetSampleRate)])
         self.converter = nil
         self.finalFormat = sourceFormat
         return
@@ -108,14 +109,16 @@ public class AudioRecorder {
     let bufferList = inputData.pointee
     let firstBuffer = bufferList.mBuffers
 
-    guard firstBuffer.mData != nil && firstBuffer.mDataByteSize > 0 else {
+    guard let sourcePointer = firstBuffer.mData, firstBuffer.mDataByteSize > 0 else {
       AudioTeeLogging.logger.error("Received empty audio buffer")
       return noErr
     }
 
-    // Append raw audio data to buffer
-    let audioData = Data(bytes: firstBuffer.mData!, count: Int(firstBuffer.mDataByteSize))
-    audioBuffer?.append(audioData)
+    // Copy directly from the Core Audio buffer into our ring buffer.
+    // This avoids creating an intermediate Data object (heap alloc + memcpy)
+    // on every IO callback (~10ms). The pointer is valid for the duration
+    // of this callback, so this is safe.
+    audioBuffer?.append(from: sourcePointer, count: Int(firstBuffer.mDataByteSize))
 
     processAudioBuffer()
 
@@ -129,10 +132,17 @@ public class AudioRecorder {
   }
 
   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)
+    audioBuffer?.processChunks { pointer, count in
+      if let converter = self.converter {
+        if !converter.transform(from: pointer, count: count, handler: { outPtr, outCount in
+          self.outputHandler.handleAudioData(outPtr, count: outCount)
+        }) {
+          // Conversion failed — pass through unconverted audio
+          self.outputHandler.handleAudioData(pointer, count: count)
+        }
+      } else {
+        self.outputHandler.handleAudioData(pointer, count: count)
+      }
     }
   }
 
diff --git a/Sources/AudioTeeCore/Core/AudioTapManager.swift b/Sources/AudioTeeCore/Core/AudioTapManager.swift
index ef4c9fc..e8fb079 100644
--- a/Sources/AudioTeeCore/Core/AudioTapManager.swift
+++ b/Sources/AudioTeeCore/Core/AudioTapManager.swift
@@ -8,7 +8,7 @@ public class AudioTapManager {
   private var deviceID: AudioObjectID?
 
   public init() {}
-  
+
   deinit {
     AudioTeeLogging.logger.debug("Cleaning up audio tap manager")
 
@@ -76,7 +76,8 @@ public class AudioTapManager {
     AudioTeeLogging.logger.debug(
       "AudioHardwareCreateProcessTap completed", context: ["status": String(status)])
     guard status == kAudioHardwareNoError else {
-      AudioTeeLogging.logger.error("Failed to create audio tap", context: ["status": String(status)])
+      AudioTeeLogging.logger.error(
+        "Failed to create audio tap", context: ["status": String(status)])
       throw AudioTeeError.tapCreationFailed(status)
     }
 
@@ -115,7 +116,8 @@ public class AudioTapManager {
     let status = AudioHardwareCreateAggregateDevice(description as CFDictionary, &deviceID)
 
     guard status == kAudioHardwareNoError else {
-      AudioTeeLogging.logger.error("Failed to create aggregate device", context: ["status": String(status)])
+      AudioTeeLogging.logger.error(
+        "Failed to create aggregate device", context: ["status": String(status)])
       throw AudioTeeError.aggregateDeviceCreationFailed(status)
     }
 
diff --git a/Sources/AudioTeeCore/Output/AudioOutputProtocol.swift b/Sources/AudioTeeCore/Output/AudioOutputProtocol.swift
index 6175a8b..5a100f5 100644
--- a/Sources/AudioTeeCore/Output/AudioOutputProtocol.swift
+++ b/Sources/AudioTeeCore/Output/AudioOutputProtocol.swift
@@ -2,7 +2,9 @@ import Foundation
 
 /// Protocol for handling audio output in different formats
 public protocol AudioOutputHandler {
-  func handleAudioPacket(_ packet: AudioPacket)
+  /// Called with a pointer to raw PCM audio data. The pointer is only
+  /// valid for the duration of this call.
+  func handleAudioData(_ pointer: UnsafeRawPointer, count: Int)
   func handleMetadata(_ metadata: AudioStreamMetadata)
   func handleStreamStart()
   func handleStreamStop()
diff --git a/Tests/AudioTeeCoreTests/AudioBufferTests.swift b/Tests/AudioTeeCoreTests/AudioBufferTests.swift
new file mode 100644
index 0000000..2268e12
--- /dev/null
+++ b/Tests/AudioTeeCoreTests/AudioBufferTests.swift
@@ -0,0 +1,219 @@
+import CoreAudio
+import XCTest
+
+@testable import AudioTeeCore
+
+// CoreAudio defines its own AudioBuffer struct, which collides with ours.
+// Explicit module qualification avoids ambiguity in tests that import both.
+private typealias AudioBuffer = AudioTeeCore.AudioBuffer
+
+final class AudioBufferTests: XCTestCase {
+
+  // MARK: - Helpers
+
+  /// Creates a minimal AudioStreamBasicDescription for testing.
+  /// 16kHz, 16-bit, mono = 2 bytes per frame, 32000 bytes/sec.
+  private func makeFormat(
+    sampleRate: Double = 16000,
+    bytesPerFrame: UInt32 = 2,
+    bitsPerChannel: UInt32 = 16
+  ) -> AudioStreamBasicDescription {
+    return AudioStreamBasicDescription(
+      mSampleRate: sampleRate,
+      mFormatID: kAudioFormatLinearPCM,
+      mFormatFlags: kAudioFormatFlagIsPacked | kAudioFormatFlagIsSignedInteger,
+      mBytesPerPacket: bytesPerFrame,
+      mFramesPerPacket: 1,
+      mBytesPerFrame: bytesPerFrame,
+      mChannelsPerFrame: 1,
+      mBitsPerChannel: bitsPerChannel,
+      mReserved: 0
+    )
+  }
+
+  /// Creates a repeating byte pattern of the given length.
+  private func makeData(byte: UInt8, count: Int) -> Data {
+    return Data(repeating: byte, count: count)
+  }
+
+  /// Appends Data to an AudioBuffer via the raw pointer path,
+  /// matching how processAudio() calls append(from:count:).
+  private func appendData(_ data: Data, to buffer: AudioBuffer) {
+    data.withUnsafeBytes { bytes in
+      buffer.append(from: bytes.baseAddress!, count: bytes.count)
+    }
+  }
+
+  /// Collects chunks from the buffer as Data objects for test verification.
+  private func collectChunks(from buffer: AudioBuffer) -> [Data] {
+    var chunks: [Data] = []
+    buffer.processChunks { pointer, count in
+      chunks.append(Data(bytes: pointer, count: count))
+    }
+    return chunks
+  }
+
+  // MARK: - Basic append + processChunks
+
+  func testSingleChunkExtraction() {
+    // 16kHz, 2 bytes/frame, 0.1s chunk = 3200 bytes per chunk
+    let format = makeFormat()
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+    let chunkSize = 3200  // 16000 * 0.1 * 2
+
+    let data = makeData(byte: 0xAB, count: chunkSize)
+    appendData(data, to: buffer)
+
+    let chunks = collectChunks(from: buffer)
+    XCTAssertEqual(chunks.count, 1)
+    XCTAssertEqual(chunks[0].count, chunkSize)
+    XCTAssertEqual(chunks[0], data)
+  }
+
+  func testMultipleChunksExtracted() {
+    let format = makeFormat()
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+    let chunkSize = 3200
+
+    // Append 2.5 chunks worth
+    appendData(makeData(byte: 0x01, count: chunkSize * 2 + chunkSize / 2), to: buffer)
+
+    let chunks = collectChunks(from: buffer)
+    // Should get 2 complete chunks, remainder stays in buffer
+    XCTAssertEqual(chunks.count, 2)
+    XCTAssertEqual(chunks[0].count, chunkSize)
+    XCTAssertEqual(chunks[1].count, chunkSize)
+  }
+
+  func testInsufficientDataReturnsNoChunks() {
+    let format = makeFormat()
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+    let chunkSize = 3200
+
+    // Append less than one chunk
+    appendData(makeData(byte: 0xFF, count: chunkSize - 1), to: buffer)
+
+    let chunks = collectChunks(from: buffer)
+    XCTAssertEqual(chunks.count, 0)
+  }
+
+  // MARK: - Wrap-around
+
+  func testWrapAroundWrite() {
+    // 8kHz, 2 bytes/frame, 0.3s chunks → chunkSize = 4800, maxBuffer = 160000.
+    // 160000 / 4800 = 33.33 — chunks do NOT divide evenly into the buffer,
+    // so after enough writes the writeIndex will straddle the boundary.
+    let format = makeFormat(sampleRate: 8000)
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.3)
+    let chunkSize = 4800  // 8000 * 0.3 * 2
+
+    // Write 33 chunks (158400 bytes), drain them all.
+    // writeIndex = 158400, readIndex = 158400. 1600 bytes remain before boundary.
+    for _ in 0..<33 {
+      appendData(makeData(byte: 0x00, count: chunkSize), to: buffer)
+    }
+    let drained = collectChunks(from: buffer)
+    XCTAssertEqual(drained.count, 33)
+
+    // Next write of 4800 bytes starts at 158400. 158400 + 4800 = 163200 > 160000.
+    // This MUST take the wrap-around else branch in append():
+    //   firstChunkSize = 160000 - 158400 = 1600
+    //   secondChunkSize = 4800 - 1600 = 3200
+    // Verify by using distinct byte patterns for the portion before and after the boundary.
+    var wrappingData = Data()
+    wrappingData.append(makeData(byte: 0xAA, count: 1600))  // fills to boundary
+    wrappingData.append(makeData(byte: 0xBB, count: 3200))  // wraps to start
+    XCTAssertEqual(wrappingData.count, chunkSize)
+    appendData(wrappingData, to: buffer)
+
+    let chunks = collectChunks(from: buffer)
+    XCTAssertEqual(chunks.count, 1)
+    XCTAssertEqual(chunks[0], wrappingData)
+  }
+
+  func testWrapAroundRead() {
+    // Same setup as above: position readIndex so that a chunk extraction
+    // straddles the ring buffer boundary, exercising the else branch in nextChunk().
+    let format = makeFormat(sampleRate: 8000)
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.3)
+    let chunkSize = 4800
+
+    // Write and drain 33 chunks. Both indices land at 158400.
+    for _ in 0..<33 {
+      appendData(makeData(byte: 0x00, count: chunkSize), to: buffer)
+    }
+    _ = collectChunks(from: buffer)
+
+    // Write one chunk starting at 158400. The write itself wraps (tested above),
+    // but crucially the READ will also wrap: readIndex = 158400,
+    // 158400 + 4800 = 163200 > 160000 → else branch in nextChunk():
+    //   firstChunkSize = 160000 - 158400 = 1600 (read from end of buffer)
+    //   secondChunkSize = 4800 - 1600 = 3200 (read from start of buffer)
+    var crossBoundaryData = Data()
+    crossBoundaryData.append(makeData(byte: 0xCC, count: 1600))
+    crossBoundaryData.append(makeData(byte: 0xDD, count: 3200))
+    appendData(crossBoundaryData, to: buffer)
+
+    let chunks = collectChunks(from: buffer)
+    XCTAssertEqual(chunks.count, 1)
+    XCTAssertEqual(chunks[0], crossBoundaryData)
+  }
+
+  // MARK: - Overflow guard
+
+  func testOverflowPreventsWrite() {
+    let format = makeFormat(sampleRate: 8000)
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+    let maxBuffer = 160000
+
+    // Fill the buffer completely
+    appendData(makeData(byte: 0x01, count: maxBuffer), to: buffer)
+
+    // Try to append more — should be silently rejected (overflow guard)
+    appendData(makeData(byte: 0x02, count: 100), to: buffer)
+
+    // Drain and verify we only got the original data
+    let chunks = collectChunks(from: buffer)
+    let totalBytes = chunks.reduce(0) { $0 + $1.count }
+    XCTAssertEqual(totalBytes, maxBuffer)
+
+    // Every byte should be 0x01, not 0x02
+    for chunk in chunks {
+      XCTAssertTrue(chunk.allSatisfy { $0 == 0x01 })
+    }
+  }
+
+  // MARK: - Incremental appends accumulate correctly
+
+  func testIncrementalAppendsThenChunk() {
+    let format = makeFormat()
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+    let chunkSize = 3200
+
+    // Simulate many small IO callbacks building up to one chunk
+    let callbackSize = 320  // 10 callbacks to fill one chunk
+    for i in 0..<10 {
+      appendData(makeData(byte: UInt8(i), count: callbackSize), to: buffer)
+    }
+
+    let chunks = collectChunks(from: buffer)
+    XCTAssertEqual(chunks.count, 1)
+    XCTAssertEqual(chunks[0].count, chunkSize)
+
+    // Verify the data is in the correct order
+    for i in 0..<10 {
+      let slice = chunks[0].subdata(in: (i * callbackSize)..<((i + 1) * callbackSize))
+      XCTAssertTrue(slice.allSatisfy { $0 == UInt8(i) })
+    }
+  }
+
+  // MARK: - Chunk size
+
+  func testBytesPerChunkIsCorrect() {
+    let format = makeFormat()
+    let buffer = AudioBuffer(format: format, chunkDuration: 0.1)
+
+    // 16kHz * 0.1s * 2 bytes/frame = 3200
+    XCTAssertEqual(buffer.bytesPerChunk, 3200)
+  }
+}
diff --git a/Tests/AudioTeeCoreTests/AudioPacketTests.swift b/Tests/AudioTeeCoreTests/AudioPacketTests.swift
deleted file mode 100644
index 35898ac..0000000
--- a/Tests/AudioTeeCoreTests/AudioPacketTests.swift
+++ /dev/null
@@ -1,30 +0,0 @@
-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)
-  }
-}
\ No newline at end of file