optimise hot-path audio pipeline: zero-copy ring buffer, pre-allocated converter buffers

- Replace Swift Array<UInt8> ring buffer with UnsafeMutableRawPointer to
  eliminate COW ref-count checks on every write/read
- Add append(from:count:) to copy directly from Core Audio buffer pointer
  into the ring buffer, removing the per-callback Data heap allocation
- Pre-allocate AVAudioPCMBuffer pair in AudioFormatConverter and reuse
  across transform() calls (lazy init, capacity-checked)
- Fix float-to-int truncation in output frame count calculation (ceil)
- Add comprehensive AudioBuffer test suite (12 tests) including proper
  wrap-around coverage for both append and read paths

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Sources/AudioTeeCore/Core/AudioBuffer.swift

@@ -1,8 +1,15 @@
 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
   private var writeIndex: Int = 0
   private var readIndex: Int = 0
   private var availableBytes: Int = 0
@@ -12,56 +19,80 @@ public class AudioBuffer {
   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
+    // 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)
   }
 
-  public func append(_ data: Data) {
-    guard availableBytes + data.count <= maxBufferSize else {
+  deinit {
+    buffer.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
+    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 writes needed due to wrap-around at the end of the ring buffer
+      let firstChunkSize = maxBufferSize - writeIndex
+      let secondChunkSize = count - firstChunkSize
 
-      // 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.advanced(by: writeIndex).copyMemory(from: source, byteCount: firstChunkSize)
+      buffer.copyMemory(from: source.advanced(by: firstChunkSize), byteCount: secondChunkSize)
 
-        buffer.replaceSubrange(writeIndex..<maxBufferSize, with: sourceBytes.prefix(firstChunkSize))
-        buffer.replaceSubrange(0..<secondChunkSize, with: sourceBytes.suffix(secondChunkSize))
-
-        writeIndex = secondChunkSize
-      }
+      writeIndex = secondChunkSize
     }
 
-    availableBytes += data.count
+    availableBytes += count
   }
 
+  /// Appends audio data from a Data value. Delegates to the raw pointer
+  /// path; prefer append(from:count:) when you already have a pointer to
+  /// avoid creating a Data object.
+  public func append(_ data: Data) {
+    data.withUnsafeBytes { bytes in
+      guard let baseAddress = bytes.baseAddress else { return }
+      append(from: baseAddress, count: bytes.count)
+    }
+  }
+
+  /// Extracts all complete chunks currently available in the buffer.
   public func processChunks() -> [AudioPacket] {
     var packets: [AudioPacket] = []
 
@@ -76,20 +107,26 @@ public class AudioBuffer {
     // Check if we have enough data for a complete chunk
     guard availableBytes >= bytesPerChunk else { return nil }
 
-    var chunkData = Data(capacity: bytesPerChunk)
+    let chunkData: Data
 
     // 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])
+      chunkData = Data(bytes: buffer.advanced(by: readIndex), count: 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])
+      var assembled = Data(capacity: bytesPerChunk)
+      assembled.append(
+        buffer.advanced(by: readIndex).assumingMemoryBound(to: UInt8.self),
+        count: firstChunkSize)
+      assembled.append(
+        buffer.assumingMemoryBound(to: UInt8.self),
+        count: secondChunkSize)
+      chunkData = assembled
 
       readIndex = secondChunkSize
     }

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
   {
@@ -58,46 +68,91 @@ public class AudioFormatConverter {
     return targetFormat.streamDescription.pointee
   }
 
+  /// 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))
+    )
+
+    // 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)
+    }
+
+    // Allocate new buffers (first call, or unexpected capacity increase)
+    guard
+      let inputBuf = AVAudioPCMBuffer(
+        pcmFormat: sourceFormat, frameCapacity: inputFrameCount)
+    else {
+      AudioTeeLogging.logger.error("Failed to create input buffer")
+      return nil
+    }
+
+    guard
+      let outputBuf = AVAudioPCMBuffer(
+        pcmFormat: targetFormat, frameCapacity: outputFrameCount)
+    else {
+      AudioTeeLogging.logger.error("Failed to create output buffer")
+      return nil
+    }
+
+    // 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)
+  }
+
   public func transform(_ packet: AudioPacket) -> AudioPacket {
     let inputData = packet.data
 
-    // Calculate frame counts
-    let inputFrameCount =
-      inputData.count / Int(sourceFormat.streamDescription.pointee.mBytesPerFrame)
-    let outputFrameCount = Int(
-      Double(inputFrameCount) * (targetFormat.sampleRate / sourceFormat.sampleRate))
+    // Calculate frame count from the input data size
+    let bytesPerFrame = Int(sourceFormat.streamDescription.pointee.mBytesPerFrame)
+    let inputFrameCount = AVAudioFrameCount(inputData.count / bytesPerFrame)
 
-    // Create input buffer
-    guard
-      let inputBuffer = AVAudioPCMBuffer(
-        pcmFormat: sourceFormat, frameCapacity: AVAudioFrameCount(inputFrameCount))
-    else {
-      AudioTeeLogging.logger.error("Failed to create input buffer")
+    // Get or create pre-allocated buffers
+    guard let (inputBuffer, outputBuffer) = getBuffers(inputFrameCount: inputFrameCount) else {
       return packet
     }
 
-    // Copy input data to buffer
+    // Copy input data into the reusable input buffer
     inputData.withUnsafeBytes { bytes in
       let dest = inputBuffer.audioBufferList.pointee.mBuffers.mData!
       dest.copyMemory(from: bytes.baseAddress!, byteCount: inputData.count)
     }
-    inputBuffer.frameLength = AVAudioFrameCount(inputFrameCount)
+    inputBuffer.frameLength = inputFrameCount
 
-    // Create output buffer
-    guard
-      let outputBuffer = AVAudioPCMBuffer(
-        pcmFormat: targetFormat, frameCapacity: AVAudioFrameCount(outputFrameCount))
-    else {
-      AudioTeeLogging.logger.error("Failed to create output buffer")
-      return packet
-    }
-
-    // Perform conversion - simpler approach
+    // Perform conversion — the block-based API lets AVAudioConverter pull
+    // input data as needed. 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
     }
@@ -115,12 +170,11 @@ public class AudioFormatConverter {
       return packet
     }
 
-    // Extract converted data
+    // Extract converted data from the reusable output buffer
     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,

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
       }
 

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()
 

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)
     }