@siteed/expo-audio-studio 2.2.0 → 2.3.0

package/CHANGELOG.md

@@ -8,15 +8,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 
+## [2.3.0] - 2025-03-29
+### Changed
+- fix: always generate a new UUID unless filename is provided (#182) ([f98a9a5](https://github.com/deeeed/expo-audio-stream/commit/f98a9a52393829e6c4a79aee3575fbfcc9416c19))
+- refactor(audio-studio): introduce constants for silence threshold and WAV header size (#188) ([e8aa329](https://github.com/deeeed/expo-audio-stream/commit/e8aa3298bd6ba029d38898360b7df26b3fd5485f))
+- docs: enhance installation and API reference documentation for phone call handling (#187) ([fcaece1](https://github.com/deeeed/expo-audio-stream/commit/fcaece18cf046d970b9659f3f12a19deb096bceb))
 ## [2.2.0] - 2025-03-28
 ### Changed
 - refactor(audio-studio): implement platform-specific CRC32 handling ([b61a3d7](https://github.com/deeeed/expo-audio-stream/commit/b61a3d743914e66888ec6cc4cb8e010ff1992698))
 - chore: update Expo dependencies and remove invalid design-system version ([16e5007](https://github.com/deeeed/expo-audio-stream/commit/16e50077690b55977c22fbcb08be75834146ff47))
 - fix: linting issues ([741589d](https://github.com/deeeed/expo-audio-stream/commit/741589d60485a2d049e7adf529d3fd2b999fa098))
-- feat: Enhance Audio Processing and Transcription Capabilities in Playground App (#171) ([1ec6026](https://github.com/deeeed/expo-audio-stream/commit/1ec6026ff75fc3ff7122b5df72e8dcd15ce848bd))
-- feat: Enhance Essentia Integration with iOS and Android Build Improvements (#169) ([422fd50](https://github.com/deeeed/expo-audio-stream/commit/422fd501a5ec71f30df660d56559bc410084b797))
-- feat: Enhance Audio Analysis with Mel Spectrogram Comparison and Pipeline Support (#164) ([541e13c](https://github.com/deeeed/expo-audio-stream/commit/541e13c6e01b8ff9947bc69dc7c29ffed6d8ee07))
-- feat: Integrate Essentia Audio Analysis Library into React Native for Android (#163) ([4cac310](https://github.com/deeeed/expo-audio-stream/commit/4cac310e4af47ddda528dee0f2840e3a336c6823))
 - chore(expo-audio-studio): release @siteed/expo-audio-studio@2.1.1 ([1b17ac6](https://github.com/deeeed/expo-audio-stream/commit/1b17ac6e103f2ca50f29668b3ddaaf57a4b4b7d3))
 ## [2.1.1] - 2025-03-04
 ### Changed
@@ -181,7 +182,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Feature: Audio features extraction during recording.
 - Feature: Consistent WAV PCM recording format across all platforms.
 
-[unreleased]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-studio@2.2.0...HEAD
+[unreleased]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-studio@2.3.0...HEAD
+[2.3.0]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-studio@2.2.0...@siteed/expo-audio-studio@2.3.0
 [2.2.0]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-studio@2.1.1...@siteed/expo-audio-studio@2.2.0
 [2.1.1]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-studio@2.1.0...@siteed/expo-audio-studio@2.1.1
 [2.1.0]: https://github.com/deeeed/expo-audio-stream/compare/@siteed/expo-audio-stream@2.0.1...@siteed/expo-audio-stream@2.1.0

package/android/src/main/AndroidManifest.xml

@@ -1,6 +1,6 @@
+<?xml version="1.0" encoding="utf-8"?>
 <manifest xmlns:android="http://schemas.android.com/apk/res/android">
     <!-- Permissions will be merged into the app's manifest -->
-    <uses-permission android:name="android.permission.READ_PHONE_STATE" />
     <uses-permission android:name="android.permission.RECORD_AUDIO"/>
     <uses-permission android:name="android.permission.FOREGROUND_SERVICE"/>
     <uses-permission android:name="android.permission.FOREGROUND_SERVICE_MICROPHONE"/>

package/android/src/main/java/net/siteed/audiostream/AudioRecorderManager.kt

@@ -37,7 +37,8 @@ class AudioRecorderManager(
     private val filesDir: File,
     private val permissionUtils: PermissionUtils,
     private val audioDataEncoder: AudioDataEncoder,
-    private val eventSender: EventSender
+    private val eventSender: EventSender,
+    private val enablePhoneStateHandling: Boolean = true
 ) {
     private var audioRecord: AudioRecord? = null
     private var bufferSizeInBytes = 0
@@ -348,8 +349,10 @@ class AudioRecorderManager(
     @RequiresApi(Build.VERSION_CODES.R)
     fun startRecording(options: Map<String, Any?>, promise: Promise) {
         try {
-            // Initialize phone state listener
-            initializePhoneStateListener()
+            // Initialize phone state listener only if enabled
+            if (enablePhoneStateHandling) {
+                initializePhoneStateListener()
+            }
 
             // Request audio focus
             if (!requestAudioFocus()) {
@@ -479,7 +482,8 @@ class AudioRecorderManager(
             return false
         }
 
-        if (!permissionUtils.checkPhoneStatePermission()) {
+        // Only check phone state permission if enabled
+        if (enablePhoneStateHandling && !permissionUtils.checkPhoneStatePermission()) {
             Log.w(Constants.TAG, "READ_PHONE_STATE permission not granted, phone call interruption handling will be disabled")
             // Don't reject here, just log warning as this is optional
         }

package/android/src/main/java/net/siteed/audiostream/ExpoAudioStreamModule.kt

@@ -16,6 +16,7 @@ import java.util.zip.CRC32
 class ExpoAudioStreamModule : Module(), EventSender {
     private lateinit var audioRecorderManager: AudioRecorderManager
     private lateinit var audioProcessor: AudioProcessor
+    private var enablePhoneStateHandling: Boolean = true // Default to true for backward compatibility
 
     private val audioFileHandler by lazy { 
         AudioFileHandler(appContext.reactContext?.filesDir ?: throw IllegalStateException("React context not available")) 
@@ -174,10 +175,14 @@ class ExpoAudioStreamModule : Module(), EventSender {
         AsyncFunction("requestPermissionsAsync") { promise: Promise ->
             try {
                 val permissions = mutableListOf(
-                    Manifest.permission.RECORD_AUDIO,
-                    Manifest.permission.READ_PHONE_STATE
+                    Manifest.permission.RECORD_AUDIO
                 )
 
+                // Only add phone state permission if enabled
+                if (enablePhoneStateHandling) {
+                    permissions.add(Manifest.permission.READ_PHONE_STATE)
+                }
+
                 // Add foreground service permission for Android 14+
                 if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.UPSIDE_DOWN_CAKE) {
                     Log.d(Constants.TAG, "Adding FOREGROUND_SERVICE_MICROPHONE permission request")
@@ -198,10 +203,14 @@ class ExpoAudioStreamModule : Module(), EventSender {
 
         AsyncFunction("getPermissionsAsync") { promise: Promise ->
             val permissions = mutableListOf(
-                Manifest.permission.RECORD_AUDIO,
-                Manifest.permission.READ_PHONE_STATE
+                Manifest.permission.RECORD_AUDIO
             )
 
+            // Only add phone state permission if enabled
+            if (enablePhoneStateHandling) {
+                permissions.add(Manifest.permission.READ_PHONE_STATE)
+            }
+
             if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.UPSIDE_DOWN_CAKE) {
                 permissions.add(Manifest.permission.FOREGROUND_SERVICE_MICROPHONE)
             }
@@ -714,20 +723,18 @@ class ExpoAudioStreamModule : Module(), EventSender {
     }
 
     private fun initializeManager() {
-        val androidContext =
-            appContext.reactContext ?: throw IllegalStateException("Android context not available")
-        val permissionUtils = PermissionUtils(androidContext)
-        val audioEncoder = AudioDataEncoder()
-        audioRecorderManager =
-            AudioRecorderManager(androidContext, androidContext.filesDir, permissionUtils, audioEncoder, this)
-        audioRecorderManager = AudioRecorderManager.initialize(
-            androidContext,
-            androidContext.filesDir,
+        val filesDir = appContext.reactContext?.filesDir ?: throw IllegalStateException("React context not available")
+        val permissionUtils = PermissionUtils(appContext.reactContext!!)
+        val audioDataEncoder = AudioDataEncoder()
+        audioRecorderManager = AudioRecorderManager(
+            appContext.reactContext!!,
+            filesDir,
             permissionUtils,
-            audioEncoder,
-            this
+            audioDataEncoder,
+            this,
+            enablePhoneStateHandling
         )
-        audioProcessor = AudioProcessor(androidContext.filesDir)
+        audioProcessor = AudioProcessor(filesDir)
     }
 
 

package/ios/AudioProcessor.swift

@@ -5,6 +5,9 @@ import Accelerate
 import AVFoundation
 import QuartzCore
 
+// Constants
+private let SILENCE_THRESHOLD_RMS: Float = 0.01
+
 public struct TrimResult {
     let uri: String
     let filename: String
@@ -416,7 +419,7 @@ public class AudioProcessor {
     ) -> DataPoint {
         let sumSquares: Float = segment.reduce(0) { $0 + $1 * $1 }
         let rms = sqrt(sumSquares / Float(segment.count))
-        let silent = rms < 0.01
+        let silent = rms < SILENCE_THRESHOLD_RMS
         let dB = Float(20 * log10(Double(rms)))
         
         let features = computeFeatures(
@@ -590,7 +593,7 @@ public class AudioProcessor {
                     amplitude: localMax,      // Always use peak amplitude
                     rms: rms,                // Use calculated RMS value
                     dB: Float(20 * log10(Double(rms))),  // Use RMS for dB calculation
-                    silent: rms < 0.01,      // Use RMS for silence detection
+                    silent: rms < SILENCE_THRESHOLD_RMS,      // Use RMS for silence detection
                     features: computeFeatures(
                         segmentData: Array(UnsafeBufferPointer(start: summedData, count: Int(framesToRead))),
                         sampleRate: sampleRate,
@@ -599,7 +602,7 @@ public class AudioProcessor {
                         segmentLength: Int(framesToRead),
                         featureOptions: featureOptions
                     ),
-                    speech: SpeechFeatures(isActive: rms >= 0.01),
+                    speech: SpeechFeatures(isActive: rms >= SILENCE_THRESHOLD_RMS),
                     startTime: startTime,
                     endTime: endTime,
                     startPosition: Int(currentFrame),
@@ -1229,7 +1232,7 @@ public class AudioProcessor {
                                             featureOptions: featureOptions)
                 
                 let rms = features.rms
-                let silent = rms < 0.01
+                let silent = rms < SILENCE_THRESHOLD_RMS
                 let dB = Float(20 * log10(Double(rms)))
                 
                 let dataPoint = DataPoint(

package/ios/AudioStreamManager.swift

@@ -12,6 +12,9 @@ import UIKit
 import MediaPlayer
 import UserNotifications
 
+// Constants
+internal let WAV_HEADER_SIZE: Int64 = 44  // Standard WAV header is 44 bytes
+
 // Helper to convert to little-endian byte array
 extension UInt32 {
     var littleEndianBytes: [UInt8] {
@@ -458,9 +461,8 @@ class AudioStreamManager: NSObject {
         let baseFilename: String
         if let existingFilename = recordingSettings?.filename {
             baseFilename = existingFilename
-        } else if let existingUUID = recordingUUID {
-            baseFilename = existingUUID.uuidString
         } else {
+            // Always create a new UUID for recording unless a filename is provided
             let newUUID = UUID()
             recordingUUID = newUUID
             baseFilename = newUUID.uuidString
@@ -1096,17 +1098,17 @@ class AudioStreamManager: NSObject {
                 - Exists: true
                 - Size: \(wavFileSize) bytes
                 - Duration: \(finalDuration) seconds
-                - Expected minimum size: 44 bytes (WAV header)
+                - Expected minimum size: \(WAV_HEADER_SIZE) bytes (WAV header)
                 """)
             
             // Return nil if the file is too small
-            if wavFileSize <= 44 {
-                Logger.debug("Recording file is too small (≤ 44 bytes), likely no audio data was recorded")
+            if wavFileSize <= WAV_HEADER_SIZE {
+                Logger.debug("Recording file is too small (≤ \(WAV_HEADER_SIZE) bytes), likely no audio data was recorded")
                 return nil
             }
             
             // Update the WAV header with the correct file size
-            updateWavHeader(fileURL: fileURL, totalDataSize: wavFileSize - 44)
+            updateWavHeader(fileURL: fileURL, totalDataSize: wavFileSize - WAV_HEADER_SIZE)
             
             // Validate compressed file if enabled
             var compression: CompressedRecordingInfo?
@@ -1372,7 +1374,7 @@ class AudioStreamManager: NSObject {
     ///   - fileURL: The URL of the WAV file.
     ///   - totalDataSize: The total size of the audio data.
     private func updateWavHeader(fileURL: URL, totalDataSize: Int64) {
-        // Prevent negative values - minimum WAV file size should be at least the header size (44 bytes)
+        // Prevent negative values - minimum WAV file size should be at least the header size (WAV_HEADER_SIZE bytes)
         guard totalDataSize >= 0 else {
             Logger.debug("Invalid file size: total data size is negative")
             return
@@ -1383,7 +1385,7 @@ class AudioStreamManager: NSObject {
             defer { fileHandle.closeFile() }
 
             // Calculate sizes
-            let fileSize = totalDataSize + 44 - 8 // Total file size minus 8 bytes for 'RIFF' and size field itself
+            let fileSize = totalDataSize + WAV_HEADER_SIZE - 8 // Total file size minus 8 bytes for 'RIFF' and size field itself
             let dataSize = totalDataSize // Size of the 'data' sub-chunk
 
             // Update RIFF chunk size at offset 4
@@ -1585,8 +1587,19 @@ class AudioStreamManager: NSObject {
                     guard let self = self else { return }
                     if let processor = self.audioProcessor {
                         Logger.debug("Processing audio buffer of size: \(dataToProcess.count)")
+                        
+                        // Strip WAV header from the first buffer to avoid false amplitude detection
+                        let dataToAnalyze: Data
+                        if self.totalDataSizeAnalysis == 0 && dataToProcess.count > Int(WAV_HEADER_SIZE) {
+                            // This is the first buffer and may contain the WAV header
+                            dataToAnalyze = dataToProcess.subdata(in: Int(WAV_HEADER_SIZE)..<dataToProcess.count)
+                            Logger.debug("Removed WAV header (\(WAV_HEADER_SIZE) bytes) from first buffer for analysis")
+                        } else {
+                            dataToAnalyze = dataToProcess
+                        }
+                        
                         let processingResult = processor.processAudioBuffer(
-                            data: dataToProcess,
+                            data: dataToAnalyze,
                             sampleRate: Float(settings.sampleRate),
                             segmentDurationMs: settings.segmentDurationMs,
                             featureOptions: settings.featureOptions ?? [:],
@@ -1600,9 +1613,10 @@ class AudioStreamManager: NSObject {
                             }
                         }
 
-                            // Update state after emission
+                        // Update state after emission
                         self.lastEmissionTimeAnalysis = currentTime
-                        self.lastEmittedSizeAnalysis = totalDataSizeAnalysis
+                        // Update the total analysis data size to mark that we've processed data
+                        self.totalDataSizeAnalysis = self.totalDataSize
                         accumulatedAnalysisData.removeAll()
                     }
                 }

package/ios/ExpoAudioStreamModule.swift

@@ -2,9 +2,11 @@
 import ExpoModulesCore
 import AVFoundation
 
-let audioDataEvent: String = "AudioData"
-let audioAnalysisEvent: String = "AudioAnalysis"
-let recordingInterruptedEvent: String = "onRecordingInterrupted"
+// Constants
+private let audioDataEvent: String = "AudioData"
+private let audioAnalysisEvent: String = "AudioAnalysis"
+private let recordingInterruptedEvent: String = "onRecordingInterrupted"
+private let DEFAULT_SEGMENT_DURATION_MS = 100
 
 public class ExpoAudioStreamModule: Module, AudioStreamManagerDelegate {
     private var streamManager = AudioStreamManager()
@@ -60,7 +62,7 @@ public class ExpoAudioStreamModule: Module, AudioStreamManagerDelegate {
             
             let features = options["features"] as? [String: Bool] ?? [:]
             let featureOptions = self.extractFeatureOptions(from: features)
-            let segmentDurationMs = options["segmentDurationMs"] as? Int ?? 100 // Default value of 100ms
+            let segmentDurationMs = options["segmentDurationMs"] as? Int ?? DEFAULT_SEGMENT_DURATION_MS // Default value of 100ms
             
             DispatchQueue.global().async(execute: {
                 do {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@siteed/expo-audio-studio",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "description": "Comprehensive audio processing library for React Native and Expo with recording, analysis, visualization, and streaming capabilities across iOS, Android, and web",
   "license": "MIT",
   "main": "build/index.js",

package/plugin/build/index.js

@@ -113,10 +113,9 @@ const withRecordingPermission = (config, props) => {
         ];
         const optionalPermissions = [
             enableNotifications && 'android.permission.POST_NOTIFICATIONS',
-            enablePhoneStateHandling && 'android.permission.READ_PHONE_STATE',
+            enablePhoneStateHandling && 'android.permission.READ_PHONE_STATE', // Only add if enabled
             enableBackgroundAudio && 'android.permission.FOREGROUND_SERVICE',
-            enableBackgroundAudio &&
-                'android.permission.FOREGROUND_SERVICE_MICROPHONE',
+            enableBackgroundAudio && 'android.permission.FOREGROUND_SERVICE_MICROPHONE',
         ].filter(Boolean);
         const permissionsToAdd = [...basePermissions, ...optionalPermissions];
         debugLog('📋 Existing Android permissions:', config.modResults.manifest['uses-permission']?.map((p) => p.$?.['android:name']) || []);

package/plugin/src/index.ts

@@ -169,10 +169,9 @@ const withRecordingPermission: ConfigPlugin<AudioStreamPluginOptions> = (
 
         const optionalPermissions = [
             enableNotifications && 'android.permission.POST_NOTIFICATIONS',
-            enablePhoneStateHandling && 'android.permission.READ_PHONE_STATE',
+            enablePhoneStateHandling && 'android.permission.READ_PHONE_STATE', // Only add if enabled
             enableBackgroundAudio && 'android.permission.FOREGROUND_SERVICE',
-            enableBackgroundAudio &&
-                'android.permission.FOREGROUND_SERVICE_MICROPHONE',
+            enableBackgroundAudio && 'android.permission.FOREGROUND_SERVICE_MICROPHONE',
         ].filter(Boolean) as string[]
 
         const permissionsToAdd = [...basePermissions, ...optionalPermissions]