@siteed/expo-audio-stream 1.12.3 → 1.13.0

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

@@ -1173,4 +1173,8 @@ class AudioRecorderManager(
         
         return File(baseDir, "$baseFilename.$extension")
     }
+
+    fun getKeepAwakeStatus(): Boolean {
+        return recordingConfig?.keepAwake ?: false
+    }
 }

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

@@ -9,6 +9,11 @@ import android.util.Log
 import android.os.Handler
 import android.os.Looper
 import expo.modules.kotlin.Promise
+import android.app.NotificationChannel
+import android.app.NotificationManager
+import android.os.Build.VERSION_CODES
+import android.app.Notification
+import androidx.core.app.NotificationCompat
 
 class AudioRecordingService : Service() {
     private val notificationManager by lazy {
@@ -28,17 +33,33 @@ class AudioRecordingService : Service() {
         Log.d(Constants.TAG, "AudioRecordingService onStartCommand")
 
         if (!isRunning) {
-            try {
-                val notification = notificationManager.getNotification()
-                startForeground(1, notification)
-                isRunning = true
-            } catch (e: Exception) {
-                Log.e(Constants.TAG, "Error starting foreground service", e)
-                stopSelf()
+            isRunning = true
+            
+            // Start as foreground service if keepAwake is true, regardless of notification settings
+            val keepAwake = AudioRecorderManager.getInstance()?.getKeepAwakeStatus() ?: false
+            if (keepAwake) {
+                // Create a minimal notification channel if needed, but don't show the notification
+                if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.O) {
+                    val channel = NotificationChannel(
+                        "recording_service",
+                        "Recording Service",
+                        NotificationManager.IMPORTANCE_LOW
+                    )
+                    val notificationManager = getSystemService(NotificationManager::class.java)
+                    notificationManager.createNotificationChannel(channel)
+                    
+                    // Create minimal notification but don't show it
+                    val notification = NotificationCompat.Builder(this, "recording_service")
+                        .setContentTitle("")
+                        .setContentText("")
+                        .build()
+                    
+                    startForeground(1, notification)
+                }
             }
         }
-
-        return START_NOT_STICKY
+        
+        return START_STICKY
     }
 
     override fun onDestroy() {

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

@@ -52,45 +52,54 @@ class ExpoAudioStreamModule : Module(), EventSender {
         }
 
         AsyncFunction("extractAudioAnalysis") { options: Map<String, Any>, promise: Promise ->
-            val fileUri = options["fileUri"] as? String
-            val pointsPerSecond =  (options["pointsPerSecond"] as? Double) ?: 20.0
-            val algorithm = options["algorithm"] as? String ?: "peak"
-            val featuresMap = options["features"] as? Map<*, *>
-            val features = featuresMap?.filterKeys { it is String }
-                ?.filterValues { it is Boolean }
-                ?.mapKeys { it.key as String }
-                ?.mapValues { it.value as Boolean }
-                ?: emptyMap()
-            val skipWavHeader = (options["skipWavHeader"] as? Boolean) ?: true
-
-            if (fileUri == null) {
-                promise.reject("INVALID_ARGUMENTS", "fileUri is required", null)
-                return@AsyncFunction
-            }
-
             try {
-                val audioData = audioProcessor.loadAudioFile(fileUri, skipWavHeader)
-                if (audioData == null) {
-                    promise.reject("PROCESSING_ERROR", "Failed to load audio file", null)
-                    return@AsyncFunction
-                }
+                val fileUri = requireNotNull(options["fileUri"] as? String) { "fileUri is required" }
+                
+                // Get decoding options
+                val decodingOptionsMap = options["decodingOptions"] as? Map<String, Any>
+                val decodingConfig = if (decodingOptionsMap != null) {
+                    DecodingConfig(
+                        targetSampleRate = decodingOptionsMap["targetSampleRate"] as? Int,
+                        targetChannels = decodingOptionsMap["targetChannels"] as? Int,
+                        targetBitDepth = (decodingOptionsMap["targetBitDepth"] as? Int) ?: 16,
+                        normalizeAudio = (decodingOptionsMap["normalizeAudio"] as? Boolean) ?: false
+                    )
+                } else null
+
+                val audioData = audioProcessor.loadAudioFromAnyFormat(fileUri, decodingConfig)
+                    ?: throw IllegalStateException("Failed to load audio file")
+
+                val pointsPerSecond = (options["pointsPerSecond"] as? Double) ?: 20.0
+                val algorithm = options["algorithm"] as? String ?: "peak"
+                val featuresMap = options["features"] as? Map<*, *>
+                val features = featuresMap?.filterKeys { it is String }
+                    ?.filterValues { it is Boolean }
+                    ?.mapKeys { it.key as String }
+                    ?.mapValues { it.value as Boolean }
+                    ?: emptyMap()
 
                 val recordingConfig = RecordingConfig(
                     sampleRate = audioData.sampleRate,
                     channels = audioData.channels,
-                    encoding = "pcm_${audioData.bitDepth}bit",
+                    encoding = when (audioData.bitDepth) {
+                        8 -> "pcm_8bit"
+                        16 -> "pcm_16bit"
+                        32 -> "pcm_32bit"
+                        else -> throw IllegalArgumentException("Unsupported bit depth: ${audioData.bitDepth}")
+                    },
                     pointsPerSecond = pointsPerSecond,
                     algorithm = algorithm,
                     features = features
                 )
 
-                Log.d("ExpoAudioStreamModule", "extractAudioAnalysis: $recordingConfig")
+                Log.d(Constants.TAG, "extractAudioAnalysis: $recordingConfig")
                 audioProcessor.resetCumulativeAmplitudeRange()
 
                 val analysisData = audioProcessor.processAudioData(audioData.data, recordingConfig)
                 promise.resolve(analysisData.toDictionary())
             } catch (e: Exception) {
-                promise.reject("PROCESSING_ERROR", "Failed to process audio file: ${e.message}", e)
+                Log.e(Constants.TAG, "Audio processing failed: ${e.message}", e)
+                promise.reject("PROCESSING_ERROR", e.message ?: "Unknown error", e)
             }
         }
 
@@ -174,6 +183,136 @@ class ExpoAudioStreamModule : Module(), EventSender {
             }
         }
 
+        AsyncFunction("extractPreview") { options: Map<String, Any>, promise: Promise ->
+            try {
+                val fileUri = requireNotNull(options["fileUri"] as? String) { "fileUri is required" }
+                val numberOfPoints = (options["numberOfPoints"] as? Int) ?: 100
+                val algorithm = (options["algorithm"] as? String)?.lowercase() ?: "rms"
+                val startTime = (options["startTime"] as? Number)?.toLong()
+                val endTime = (options["endTime"] as? Number)?.toLong()
+                
+                Log.d(Constants.TAG, """
+                    Extracting preview with params:
+                    - fileUri: $fileUri
+                    - numberOfPoints: $numberOfPoints
+                    - algorithm: $algorithm
+                    - startTime: ${startTime ?: "none"}
+                    - endTime: ${endTime ?: "none"}
+                """.trimIndent())
+                
+                // Get decoding options with defaults
+                val decodingOptionsMap = options["decodingOptions"] as? Map<String, Any>
+                val decodingConfig = if (decodingOptionsMap != null) {
+                    DecodingConfig(
+                        targetSampleRate = decodingOptionsMap["targetSampleRate"] as? Int ?: 22050,
+                        targetChannels = decodingOptionsMap["targetChannels"] as? Int ?: 1,
+                        targetBitDepth = (decodingOptionsMap["targetBitDepth"] as? Int) ?: 16,
+                        normalizeAudio = (decodingOptionsMap["normalizeAudio"] as? Boolean) ?: false
+                    )
+                } else DecodingConfig(
+                    targetSampleRate = 16000,
+                    targetChannels = 1,
+                    targetBitDepth = 16,
+                    normalizeAudio = false
+                )
+
+                Log.d(Constants.TAG, """
+                    Using decoding config:
+                    - targetSampleRate: ${decodingConfig.targetSampleRate}
+                    - targetChannels: ${decodingConfig.targetChannels}
+                    - targetBitDepth: ${decodingConfig.targetBitDepth}
+                    - normalizeAudio: ${decodingConfig.normalizeAudio}
+                """.trimIndent())
+
+                // Use loadAudioRange when time range is specified, otherwise fall back to loadAudioFromAnyFormat
+                val audioData = if (startTime != null && endTime != null) {
+                    audioProcessor.loadAudioRange(fileUri, startTime, endTime, decodingConfig)
+                } else {
+                    audioProcessor.loadAudioFromAnyFormat(fileUri, decodingConfig)
+                } ?: throw IllegalStateException("Failed to load audio file")
+
+                val previewConfig = RecordingConfig(
+                    sampleRate = audioData.sampleRate,
+                    channels = audioData.channels,
+                    encoding = when (audioData.bitDepth) {
+                        8 -> "pcm_8bit"
+                        16 -> "pcm_16bit"
+                        32 -> "pcm_32bit"
+                        else -> throw IllegalArgumentException("Unsupported bit depth: ${audioData.bitDepth}")
+                    },
+                    pointsPerSecond = 0.0, // Will be overridden by numberOfPoints
+                    algorithm = algorithm,
+                    features = emptyMap() // No features needed for preview
+                )
+
+                val preview = audioProcessor.generatePreview(
+                    audioData = audioData,
+                    numberOfPoints = numberOfPoints,
+                    startTimeMs = startTime,
+                    endTimeMs = endTime,
+                    config = previewConfig
+                )
+                
+                Log.d(Constants.TAG, "Preview generated successfully with ${preview.dataPoints.size} points")
+                promise.resolve(preview.toDictionary())
+            } catch (e: Exception) {
+                Log.e(Constants.TAG, "Preview generation failed: ${e.message}", e)
+                Log.e(Constants.TAG, "Stack trace: ${e.stackTraceToString()}")
+                promise.reject("PROCESSING_ERROR", e.message ?: "Unknown error", e)
+            }
+        }
+
+        AsyncFunction("trimAudio") { options: Map<String, Any>, promise: Promise ->
+            try {
+                val fileUri = requireNotNull(options["fileUri"] as? String) { "fileUri is required" }
+                val startTimeMs = requireNotNull(options["startTimeMs"] as? Number)?.toLong() 
+                    ?: throw IllegalArgumentException("startTimeMs is required")
+                val endTimeMs = requireNotNull(options["endTimeMs"] as? Number)?.toLong()
+                    ?: throw IllegalArgumentException("endTimeMs is required")
+                val outputFileName = options["outputFileName"] as? String
+                
+                // Get decoding options
+                val decodingOptionsMap = options["decodingOptions"] as? Map<String, Any>
+                val decodingConfig = if (decodingOptionsMap != null) {
+                    DecodingConfig(
+                        targetSampleRate = decodingOptionsMap["targetSampleRate"] as? Int,
+                        targetChannels = decodingOptionsMap["targetChannels"] as? Int,
+                        targetBitDepth = (decodingOptionsMap["targetBitDepth"] as? Int) ?: 16,
+                        normalizeAudio = (decodingOptionsMap["normalizeAudio"] as? Boolean) ?: false
+                    )
+                } else null
+
+                Log.d(Constants.TAG, """
+                    Trimming audio with params:
+                    - fileUri: $fileUri
+                    - startTimeMs: $startTimeMs
+                    - endTimeMs: $endTimeMs
+                    - outputFileName: ${outputFileName ?: "auto-generated"}
+                """.trimIndent())
+
+                val trimmedAudio = audioProcessor.trimAudio(
+                    fileUri = fileUri,
+                    startTimeMs = startTimeMs,
+                    endTimeMs = endTimeMs,
+                    config = decodingConfig,
+                    outputFileName = outputFileName
+                ) ?: throw IllegalStateException("Failed to trim audio")
+
+                // Create a map with the available data
+                val resultMap = mapOf<String, Any>(
+                    "sampleRate" to trimmedAudio.sampleRate,
+                    "channels" to trimmedAudio.channels,
+                    "bitDepth" to trimmedAudio.bitDepth,
+                    "dataSize" to trimmedAudio.data.size
+                )
+
+                promise.resolve(resultMap)
+            } catch (e: Exception) {
+                Log.e(Constants.TAG, "Failed to trim audio: ${e.message}", e)
+                promise.reject("TRIM_ERROR", e.message ?: "Unknown error", e)
+            }
+        }
+
         OnDestroy {
             AudioRecorderManager.destroy()
         }

package/build/AudioAnalysis/AudioAnalysis.types.d.ts

@@ -1,3 +1,12 @@
+/**
+ * Represents the configuration for decoding audio data.
+ */
+export interface DecodingConfig {
+    targetSampleRate?: number;
+    targetChannels?: number;
+    targetBitDepth?: number;
+    normalizeAudio?: boolean;
+}
 /**
  * Represents various audio features extracted from an audio signal.
  */
@@ -71,4 +80,57 @@ export interface AudioAnalysis {
         speaker: number;
     }[];
 }
+/**
+ * Options for specifying a time range within an audio file.
+ */
+export interface AudioRangeOptions {
+    /** Start time in milliseconds */
+    startTime?: number;
+    /** End time in milliseconds */
+    endTime?: number;
+}
+/**
+ * Options for generating a quick preview of audio waveform.
+ * This is optimized for UI rendering with a specified number of points.
+ */
+export interface PreviewOptions extends AudioRangeOptions {
+    /** URI of the audio file to analyze */
+    fileUri: string;
+    /**
+     * Total number of points to generate for the preview.
+     * @default 100
+     */
+    numberOfPoints?: number;
+    /**
+     * Algorithm used to calculate amplitude values
+     * @default "rms"
+     */
+    algorithm?: AmplitudeAlgorithm;
+    /**
+     * Optional configuration for decoding the audio file.
+     * Defaults to:
+     * - targetSampleRate: undefined (keep original)
+     * - targetChannels: undefined (keep original)
+     * - targetBitDepth: 16
+     * - normalizeAudio: false
+     */
+    decodingOptions?: DecodingConfig;
+}
+/**
+ * Represents a simplified preview of audio waveform,
+ * optimized for quick visualization.
+ */
+export interface AudioPreview {
+    /** Number of data points per second */
+    pointsPerSecond: number;
+    /** Duration of the audio in milliseconds */
+    durationMs: number;
+    /** Range of amplitude values in the preview */
+    amplitudeRange: {
+        min: number;
+        max: number;
+    };
+    /** Array of data points representing the waveform */
+    dataPoints: DataPoint[];
+}
 //# sourceMappingURL=AudioAnalysis.types.d.ts.map

package/build/AudioAnalysis/AudioAnalysis.types.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"AudioAnalysis.types.d.ts","sourceRoot":"","sources":["../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":"AAEA;;GAEG;AACH,MAAM,WAAW,aAAa;IAC1B,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,EAAE,CAAA;IACd,GAAG,EAAE,MAAM,CAAA;IACX,YAAY,EAAE,MAAM,CAAA;IACpB,YAAY,EAAE,MAAM,CAAA;IACpB,GAAG,EAAE,MAAM,CAAA;IACX,gBAAgB,EAAE,MAAM,CAAA;IACxB,gBAAgB,EAAE,MAAM,CAAA;IACxB,eAAe,EAAE,MAAM,CAAA;IACvB,iBAAiB,EAAE,MAAM,CAAA;IACzB,UAAU,EAAE,MAAM,EAAE,CAAA;IACpB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;CACd;AAED;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACjC,MAAM,CAAC,EAAE,OAAO,CAAA;IAChB,IAAI,CAAC,EAAE,OAAO,CAAA;IACd,GAAG,CAAC,EAAE,OAAO,CAAA;IACb,GAAG,CAAC,EAAE,OAAO,CAAA;IACb,gBAAgB,CAAC,EAAE,OAAO,CAAA;IAC1B,gBAAgB,CAAC,EAAE,OAAO,CAAA;IAC1B,eAAe,CAAC,EAAE,OAAO,CAAA;IACzB,iBAAiB,CAAC,EAAE,OAAO,CAAA;IAC3B,UAAU,CAAC,EAAE,OAAO,CAAA;IACpB,KAAK,CAAC,EAAE,OAAO,CAAA;IACf,GAAG,CAAC,EAAE,OAAO,CAAA;CAChB;AAED;;GAEG;AACH,MAAM,WAAW,SAAS;IACtB,EAAE,EAAE,MAAM,CAAA;IACV,SAAS,EAAE,MAAM,CAAA;IACjB,YAAY,CAAC,EAAE,OAAO,CAAA;IACtB,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,MAAM,CAAC,EAAE,OAAO,CAAA;IAChB,QAAQ,CAAC,EAAE,aAAa,CAAA;IACxB,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,WAAW,CAAC,EAAE,MAAM,CAAA;IAEpB,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB,OAAO,CAAC,EAAE,MAAM,CAAA;CACnB;AAED,MAAM,MAAM,kBAAkB,GAAG,MAAM,GAAG,KAAK,CAAA;AAE/C;;GAEG;AACH,MAAM,WAAW,aAAa;IAC1B,eAAe,EAAE,MAAM,CAAA;IACvB,UAAU,EAAE,MAAM,CAAA;IAClB,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;IACf,gBAAgB,EAAE,MAAM,CAAA;IACxB,UAAU,EAAE,MAAM,CAAA;IAClB,UAAU,EAAE,SAAS,EAAE,CAAA;IACvB,kBAAkB,EAAE,kBAAkB,CAAA;IACtC,cAAc,EAAE;QACZ,GAAG,EAAE,MAAM,CAAA;QACX,GAAG,EAAE,MAAM,CAAA;KACd,CAAA;IAED,cAAc,CAAC,EAAE;QACb,SAAS,EAAE,MAAM,CAAA;QACjB,OAAO,EAAE,MAAM,CAAA;KAClB,EAAE,CAAA;CACN"}
+{"version":3,"file":"AudioAnalysis.types.d.ts","sourceRoot":"","sources":["../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":"AAEA;;GAEG;AACH,MAAM,WAAW,cAAc;IAC3B,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,cAAc,CAAC,EAAE,OAAO,CAAA;CAC3B;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC1B,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,EAAE,CAAA;IACd,GAAG,EAAE,MAAM,CAAA;IACX,YAAY,EAAE,MAAM,CAAA;IACpB,YAAY,EAAE,MAAM,CAAA;IACpB,GAAG,EAAE,MAAM,CAAA;IACX,gBAAgB,EAAE,MAAM,CAAA;IACxB,gBAAgB,EAAE,MAAM,CAAA;IACxB,eAAe,EAAE,MAAM,CAAA;IACvB,iBAAiB,EAAE,MAAM,CAAA;IACzB,UAAU,EAAE,MAAM,EAAE,CAAA;IACpB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;CACd;AAED;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACjC,MAAM,CAAC,EAAE,OAAO,CAAA;IAChB,IAAI,CAAC,EAAE,OAAO,CAAA;IACd,GAAG,CAAC,EAAE,OAAO,CAAA;IACb,GAAG,CAAC,EAAE,OAAO,CAAA;IACb,gBAAgB,CAAC,EAAE,OAAO,CAAA;IAC1B,gBAAgB,CAAC,EAAE,OAAO,CAAA;IAC1B,eAAe,CAAC,EAAE,OAAO,CAAA;IACzB,iBAAiB,CAAC,EAAE,OAAO,CAAA;IAC3B,UAAU,CAAC,EAAE,OAAO,CAAA;IACpB,KAAK,CAAC,EAAE,OAAO,CAAA;IACf,GAAG,CAAC,EAAE,OAAO,CAAA;CAChB;AAED;;GAEG;AACH,MAAM,WAAW,SAAS;IACtB,EAAE,EAAE,MAAM,CAAA;IACV,SAAS,EAAE,MAAM,CAAA;IACjB,YAAY,CAAC,EAAE,OAAO,CAAA;IACtB,EAAE,CAAC,EAAE,MAAM,CAAA;IACX,MAAM,CAAC,EAAE,OAAO,CAAA;IAChB,QAAQ,CAAC,EAAE,aAAa,CAAA;IACxB,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,WAAW,CAAC,EAAE,MAAM,CAAA;IAEpB,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB,OAAO,CAAC,EAAE,MAAM,CAAA;CACnB;AAED,MAAM,MAAM,kBAAkB,GAAG,MAAM,GAAG,KAAK,CAAA;AAE/C;;GAEG;AACH,MAAM,WAAW,aAAa;IAC1B,eAAe,EAAE,MAAM,CAAA;IACvB,UAAU,EAAE,MAAM,CAAA;IAClB,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;IACf,gBAAgB,EAAE,MAAM,CAAA;IACxB,UAAU,EAAE,MAAM,CAAA;IAClB,UAAU,EAAE,SAAS,EAAE,CAAA;IACvB,kBAAkB,EAAE,kBAAkB,CAAA;IACtC,cAAc,EAAE;QACZ,GAAG,EAAE,MAAM,CAAA;QACX,GAAG,EAAE,MAAM,CAAA;KACd,CAAA;IAED,cAAc,CAAC,EAAE;QACb,SAAS,EAAE,MAAM,CAAA;QACjB,OAAO,EAAE,MAAM,CAAA;KAClB,EAAE,CAAA;CACN;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IAC9B,iCAAiC;IACjC,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,+BAA+B;IAC/B,OAAO,CAAC,EAAE,MAAM,CAAA;CACnB;AAED;;;GAGG;AACH,MAAM,WAAW,cAAe,SAAQ,iBAAiB;IACrD,uCAAuC;IACvC,OAAO,EAAE,MAAM,CAAA;IACf;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB;;;OAGG;IACH,SAAS,CAAC,EAAE,kBAAkB,CAAA;IAC9B;;;;;;;OAOG;IACH,eAAe,CAAC,EAAE,cAAc,CAAA;CACnC;AAED;;;GAGG;AACH,MAAM,WAAW,YAAY;IACzB,uCAAuC;IACvC,eAAe,EAAE,MAAM,CAAA;IACvB,4CAA4C;IAC5C,UAAU,EAAE,MAAM,CAAA;IAClB,+CAA+C;IAC/C,cAAc,EAAE;QACZ,GAAG,EAAE,MAAM,CAAA;QACX,GAAG,EAAE,MAAM,CAAA;KACd,CAAA;IACD,qDAAqD;IACrD,UAAU,EAAE,SAAS,EAAE,CAAA;CAC1B"}

package/build/AudioAnalysis/AudioAnalysis.types.js.map

@@ -1 +1 @@
-{"version":3,"file":"AudioAnalysis.types.js","sourceRoot":"","sources":["../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":"AAAA,sEAAsE","sourcesContent":["// packages/expo-audio-stream/src/AudioAnalysis/AudioAnalysis.types.ts\n\n/**\n * Represents various audio features extracted from an audio signal.\n */\nexport interface AudioFeatures {\n    energy: number // The infinite integral of the squared signal, representing the overall energy of the audio.\n    mfcc: number[] // Mel-frequency cepstral coefficients, describing the short-term power spectrum of a sound.\n    rms: number // Root mean square value, indicating the amplitude of the audio signal.\n    minAmplitude: number // Minimum amplitude value in the audio signal.\n    maxAmplitude: number // Maximum amplitude value in the audio signal.\n    zcr: number // Zero-crossing rate, indicating the rate at which the signal changes sign.\n    spectralCentroid: number // The center of mass of the spectrum, indicating the brightness of the sound.\n    spectralFlatness: number // Measure of the flatness of the spectrum, indicating how noise-like the signal is.\n    spectralRolloff: number // The frequency below which a specified percentage (usually 85%) of the total spectral energy lies.\n    spectralBandwidth: number // The width of the spectrum, indicating the range of frequencies present.\n    chromagram: number[] // Chromagram, representing the 12 different pitch classes of the audio.\n    tempo: number // Estimated tempo of the audio signal, measured in beats per minute (BPM).\n    hnr: number // Harmonics-to-noise ratio, indicating the proportion of harmonics to noise in the audio signal.\n}\n\n/**\n * Options to specify which audio features to extract.\n */\nexport interface AudioFeaturesOptions {\n    energy?: boolean\n    mfcc?: boolean\n    rms?: boolean\n    zcr?: boolean\n    spectralCentroid?: boolean\n    spectralFlatness?: boolean\n    spectralRolloff?: boolean\n    spectralBandwidth?: boolean\n    chromagram?: boolean\n    tempo?: boolean\n    hnr?: boolean\n}\n\n/**\n * Represents a single data point in the audio analysis.\n */\nexport interface DataPoint {\n    id: number\n    amplitude: number\n    activeSpeech?: boolean\n    dB?: number\n    silent?: boolean\n    features?: AudioFeatures\n    startTime?: number\n    endTime?: number\n    // start / end position in bytes\n    startPosition?: number\n    endPosition?: number\n    // number of audio samples for this point (samples size depends on bit depth)\n    samples?: number\n    // TODO: speaker detection\n    speaker?: number\n}\n\nexport type AmplitudeAlgorithm = 'peak' | 'rms'\n\n/**\n * Represents the complete data from the audio analysis.\n */\nexport interface AudioAnalysis {\n    pointsPerSecond: number // How many consolidated value per second\n    durationMs: number // Duration of the audio in milliseconds\n    bitDepth: number // Bit depth of the audio\n    samples: number // Size of the audio in bytes\n    numberOfChannels: number // Number of audio channels\n    sampleRate: number // Sample rate of the audio\n    dataPoints: DataPoint[] // Array of data points from the analysis.\n    amplitudeAlgorithm: AmplitudeAlgorithm // Algorithm used to calculate amplitude values.\n    amplitudeRange: {\n        min: number\n        max: number\n    }\n    // TODO: speaker detection\n    speakerChanges?: {\n        timestamp: number // Timestamp of the speaker change in milliseconds.\n        speaker: number // Speaker identifier.\n    }[]\n}\n"]}
+{"version":3,"file":"AudioAnalysis.types.js","sourceRoot":"","sources":["../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":"AAAA,sEAAsE","sourcesContent":["// packages/expo-audio-stream/src/AudioAnalysis/AudioAnalysis.types.ts\n\n/**\n * Represents the configuration for decoding audio data.\n */\nexport interface DecodingConfig {\n    targetSampleRate?: number\n    targetChannels?: number\n    targetBitDepth?: number\n    normalizeAudio?: boolean\n}\n\n/**\n * Represents various audio features extracted from an audio signal.\n */\nexport interface AudioFeatures {\n    energy: number // The infinite integral of the squared signal, representing the overall energy of the audio.\n    mfcc: number[] // Mel-frequency cepstral coefficients, describing the short-term power spectrum of a sound.\n    rms: number // Root mean square value, indicating the amplitude of the audio signal.\n    minAmplitude: number // Minimum amplitude value in the audio signal.\n    maxAmplitude: number // Maximum amplitude value in the audio signal.\n    zcr: number // Zero-crossing rate, indicating the rate at which the signal changes sign.\n    spectralCentroid: number // The center of mass of the spectrum, indicating the brightness of the sound.\n    spectralFlatness: number // Measure of the flatness of the spectrum, indicating how noise-like the signal is.\n    spectralRolloff: number // The frequency below which a specified percentage (usually 85%) of the total spectral energy lies.\n    spectralBandwidth: number // The width of the spectrum, indicating the range of frequencies present.\n    chromagram: number[] // Chromagram, representing the 12 different pitch classes of the audio.\n    tempo: number // Estimated tempo of the audio signal, measured in beats per minute (BPM).\n    hnr: number // Harmonics-to-noise ratio, indicating the proportion of harmonics to noise in the audio signal.\n}\n\n/**\n * Options to specify which audio features to extract.\n */\nexport interface AudioFeaturesOptions {\n    energy?: boolean\n    mfcc?: boolean\n    rms?: boolean\n    zcr?: boolean\n    spectralCentroid?: boolean\n    spectralFlatness?: boolean\n    spectralRolloff?: boolean\n    spectralBandwidth?: boolean\n    chromagram?: boolean\n    tempo?: boolean\n    hnr?: boolean\n}\n\n/**\n * Represents a single data point in the audio analysis.\n */\nexport interface DataPoint {\n    id: number\n    amplitude: number\n    activeSpeech?: boolean\n    dB?: number\n    silent?: boolean\n    features?: AudioFeatures\n    startTime?: number\n    endTime?: number\n    // start / end position in bytes\n    startPosition?: number\n    endPosition?: number\n    // number of audio samples for this point (samples size depends on bit depth)\n    samples?: number\n    // TODO: speaker detection\n    speaker?: number\n}\n\nexport type AmplitudeAlgorithm = 'peak' | 'rms'\n\n/**\n * Represents the complete data from the audio analysis.\n */\nexport interface AudioAnalysis {\n    pointsPerSecond: number // How many consolidated value per second\n    durationMs: number // Duration of the audio in milliseconds\n    bitDepth: number // Bit depth of the audio\n    samples: number // Size of the audio in bytes\n    numberOfChannels: number // Number of audio channels\n    sampleRate: number // Sample rate of the audio\n    dataPoints: DataPoint[] // Array of data points from the analysis.\n    amplitudeAlgorithm: AmplitudeAlgorithm // Algorithm used to calculate amplitude values.\n    amplitudeRange: {\n        min: number\n        max: number\n    }\n    // TODO: speaker detection\n    speakerChanges?: {\n        timestamp: number // Timestamp of the speaker change in milliseconds.\n        speaker: number // Speaker identifier.\n    }[]\n}\n\n/**\n * Options for specifying a time range within an audio file.\n */\nexport interface AudioRangeOptions {\n    /** Start time in milliseconds */\n    startTime?: number\n    /** End time in milliseconds */\n    endTime?: number\n}\n\n/**\n * Options for generating a quick preview of audio waveform.\n * This is optimized for UI rendering with a specified number of points.\n */\nexport interface PreviewOptions extends AudioRangeOptions {\n    /** URI of the audio file to analyze */\n    fileUri: string\n    /**\n     * Total number of points to generate for the preview.\n     * @default 100\n     */\n    numberOfPoints?: number\n    /**\n     * Algorithm used to calculate amplitude values\n     * @default \"rms\"\n     */\n    algorithm?: AmplitudeAlgorithm\n    /**\n     * Optional configuration for decoding the audio file.\n     * Defaults to:\n     * - targetSampleRate: undefined (keep original)\n     * - targetChannels: undefined (keep original)\n     * - targetBitDepth: 16\n     * - normalizeAudio: false\n     */\n    decodingOptions?: DecodingConfig\n}\n\n/**\n * Represents a simplified preview of audio waveform,\n * optimized for quick visualization.\n */\nexport interface AudioPreview {\n    /** Number of data points per second */\n    pointsPerSecond: number\n    /** Duration of the audio in milliseconds */\n    durationMs: number\n    /** Range of amplitude values in the preview */\n    amplitudeRange: {\n        min: number\n        max: number\n    }\n    /** Array of data points representing the waveform */\n    dataPoints: DataPoint[]\n}\n"]}

package/build/AudioAnalysis/extractAudioAnalysis.d.ts

@@ -1,5 +1,5 @@
 import { ConsoleLike } from '../ExpoAudioStream.types';
-import { AmplitudeAlgorithm, AudioAnalysis, AudioFeaturesOptions } from './AudioAnalysis.types';
+import { AmplitudeAlgorithm, AudioAnalysis, AudioFeaturesOptions, AudioPreview, DecodingConfig, PreviewOptions } from './AudioAnalysis.types';
 import { WavFileInfo } from '../utils/getWavFileInfo';
 export interface ExtractAudioAnalysisProps {
     fileUri?: string;
@@ -17,6 +17,15 @@ export interface ExtractAudioAnalysisProps {
     features?: AudioFeaturesOptions;
     featuresExtratorUrl?: string;
     logger?: ConsoleLike;
+    decodingOptions?: DecodingConfig;
 }
+export interface ExtractAudioFromAnyFormatProps extends ExtractAudioAnalysisProps {
+    mimeType?: string;
+    decodingOptions?: DecodingConfig;
+    startTime?: number;
+    endTime?: number;
+}
+export declare function extractAudioFromAnyFormat({ fileUri, arrayBuffer, mimeType, decodingOptions, startTime, endTime, ...restProps }: ExtractAudioFromAnyFormatProps): Promise<AudioAnalysis>;
 export declare const extractAudioAnalysis: ({ fileUri, pointsPerSecond, arrayBuffer, bitDepth, skipWavHeader, durationMs, sampleRate, numberOfChannels, algorithm, features, featuresExtratorUrl, logger, }: ExtractAudioAnalysisProps) => Promise<AudioAnalysis>;
+export declare function extractPreview({ fileUri, numberOfPoints, algorithm, startTime, endTime, decodingOptions, }: PreviewOptions): Promise<AudioPreview>;
 //# sourceMappingURL=extractAudioAnalysis.d.ts.map

package/build/AudioAnalysis/extractAudioAnalysis.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"extractAudioAnalysis.d.ts","sourceRoot":"","sources":["../../src/AudioAnalysis/extractAudioAnalysis.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,WAAW,EAAE,MAAM,0BAA0B,CAAA;AAGtD,OAAO,EACH,kBAAkB,EAClB,aAAa,EACb,oBAAoB,EACvB,MAAM,uBAAuB,CAAA;AAE9B,OAAO,EAAkB,WAAW,EAAE,MAAM,yBAAyB,CAAA;AAGrE,MAAM,WAAW,yBAAyB;IACtC,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB,WAAW,CAAC,EAAE,WAAW,CAAA;IACzB,WAAW,CAAC,EAAE,WAAW,CAAA;IACzB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,aAAa,CAAC,EAAE,OAAO,CAAA;IACvB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB,SAAS,CAAC,EAAE,kBAAkB,CAAA;IAC9B,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB,QAAQ,CAAC,EAAE,oBAAoB,CAAA;IAC/B,mBAAmB,CAAC,EAAE,MAAM,CAAA;IAC5B,MAAM,CAAC,EAAE,WAAW,CAAA;CACvB;AAED,eAAO,MAAM,oBAAoB,oKAa9B,yBAAyB,KAAG,QAAQ,aAAa,CAsGnD,CAAA"}
+{"version":3,"file":"extractAudioAnalysis.d.ts","sourceRoot":"","sources":["../../src/AudioAnalysis/extractAudioAnalysis.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,WAAW,EAAE,MAAM,0BAA0B,CAAA;AAGtD,OAAO,EACH,kBAAkB,EAClB,aAAa,EACb,oBAAoB,EACpB,YAAY,EACZ,cAAc,EACd,cAAc,EACjB,MAAM,uBAAuB,CAAA;AAE9B,OAAO,EAAkB,WAAW,EAAE,MAAM,yBAAyB,CAAA;AAGrE,MAAM,WAAW,yBAAyB;IACtC,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB,WAAW,CAAC,EAAE,WAAW,CAAA;IACzB,WAAW,CAAC,EAAE,WAAW,CAAA;IACzB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,aAAa,CAAC,EAAE,OAAO,CAAA;IACvB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB,SAAS,CAAC,EAAE,kBAAkB,CAAA;IAC9B,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB,QAAQ,CAAC,EAAE,oBAAoB,CAAA;IAC/B,mBAAmB,CAAC,EAAE,MAAM,CAAA;IAC5B,MAAM,CAAC,EAAE,WAAW,CAAA;IACpB,eAAe,CAAC,EAAE,cAAc,CAAA;CACnC;AAED,MAAM,WAAW,8BACb,SAAQ,yBAAyB;IACjC,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,eAAe,CAAC,EAAE,cAAc,CAAA;IAChC,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,OAAO,CAAC,EAAE,MAAM,CAAA;CACnB;AAED,wBAAsB,yBAAyB,CAAC,EAC5C,OAAO,EACP,WAAW,EACX,QAAQ,EACR,eAAe,EACf,SAAS,EACT,OAAO,EACP,GAAG,SAAS,EACf,EAAE,8BAA8B,GAAG,OAAO,CAAC,aAAa,CAAC,CAsJzD;AAED,eAAO,MAAM,oBAAoB,oKAa9B,yBAAyB,KAAG,QAAQ,aAAa,CAsGnD,CAAA;AAED,wBAAsB,cAAc,CAAC,EACjC,OAAO,EACP,cAAc,EACd,SAAiB,EACjB,SAAS,EACT,OAAO,EACP,eAAe,GAClB,EAAE,cAAc,GAAG,OAAO,CAAC,YAAY,CAAC,CAsCxC"}

package/build/AudioAnalysis/extractAudioAnalysis.js

@@ -3,6 +3,128 @@ import { isWeb } from '../constants';
 import { convertPCMToFloat32 } from '../utils/convertPCMToFloat32';
 import { getWavFileInfo } from '../utils/getWavFileInfo';
 import { InlineFeaturesExtractor } from '../workers/InlineFeaturesExtractor.web';
+export async function extractAudioFromAnyFormat({ fileUri, arrayBuffer, mimeType, decodingOptions, startTime, endTime, ...restProps }) {
+    if (isWeb) {
+        try {
+            // Get the audio data
+            let audioBuffer;
+            if (arrayBuffer) {
+                audioBuffer = arrayBuffer;
+            }
+            else if (fileUri) {
+                const response = await fetch(fileUri);
+                if (!response.ok) {
+                    throw new Error(`Failed to fetch fileUri: ${response.statusText}`);
+                }
+                audioBuffer = await response.arrayBuffer();
+            }
+            else {
+                throw new Error('Either arrayBuffer or fileUri must be provided');
+            }
+            // Create audio context with target sample rate if specified
+            const audioContext = new (window.AudioContext ||
+                window.webkitAudioContext)({
+                sampleRate: decodingOptions?.targetSampleRate,
+            });
+            // Decode the audio data
+            const decodedAudioBuffer = await audioContext.decodeAudioData(audioBuffer);
+            // Calculate the actual duration in milliseconds
+            const fullDurationMs = decodedAudioBuffer.duration * 1000;
+            const effectiveDurationMs = endTime
+                ? endTime - (startTime || 0)
+                : fullDurationMs - (startTime || 0);
+            // Create a new buffer for the selected range
+            const rangeLength = decodedAudioBuffer.length;
+            const rangeBuffer = new AudioBuffer({
+                length: rangeLength,
+                numberOfChannels: decodedAudioBuffer.numberOfChannels,
+                sampleRate: decodedAudioBuffer.sampleRate,
+            });
+            // Copy the selected range
+            for (let channel = 0; channel < decodedAudioBuffer.numberOfChannels; channel++) {
+                const channelData = decodedAudioBuffer.getChannelData(channel);
+                const rangeData = channelData.slice(0, rangeLength);
+                rangeBuffer.copyToChannel(rangeData, channel);
+            }
+            // Use the range buffer instead of the full buffer
+            let processedBuffer = rangeBuffer;
+            // Get original properties
+            const originalSampleRate = processedBuffer.sampleRate;
+            const length = processedBuffer.length;
+            // Determine target format
+            const targetChannels = decodingOptions?.targetChannels ??
+                processedBuffer.numberOfChannels;
+            const targetSampleRate = decodingOptions?.targetSampleRate ?? processedBuffer.sampleRate;
+            // Create offline context for resampling if needed
+            if (targetSampleRate !== originalSampleRate) {
+                const offlineCtx = new OfflineAudioContext(targetChannels, (length * targetSampleRate) / originalSampleRate, targetSampleRate);
+                const source = offlineCtx.createBufferSource();
+                source.buffer = processedBuffer;
+                source.connect(offlineCtx.destination);
+                source.start();
+                processedBuffer = await offlineCtx.startRendering();
+            }
+            // Convert to the desired format
+            const newLength = processedBuffer.length;
+            let wavBuffer;
+            // Create appropriate buffer based on target bit depth
+            switch (decodingOptions?.targetBitDepth) {
+                case 16:
+                    wavBuffer = new Int16Array(newLength * targetChannels);
+                    break;
+                case 8:
+                    wavBuffer = new Int8Array(newLength * targetChannels);
+                    break;
+                case 32:
+                default:
+                    wavBuffer = new Float32Array(newLength * targetChannels);
+                    break;
+            }
+            // Interleave channels and handle bit depth conversion
+            const numChannels = Math.min(processedBuffer.numberOfChannels, targetChannels);
+            for (let channel = 0; channel < numChannels; channel++) {
+                const channelData = processedBuffer.getChannelData(channel);
+                for (let i = 0; i < newLength; i++) {
+                    let sample = channelData[i];
+                    // Normalize if requested
+                    if (decodingOptions?.normalizeAudio) {
+                        sample = Math.max(-1, Math.min(1, sample));
+                    }
+                    // Convert sample based on target bit depth
+                    if (decodingOptions?.targetBitDepth === 16) {
+                        sample = sample * 32767; // Convert to 16-bit range
+                    }
+                    else if (decodingOptions?.targetBitDepth === 8) {
+                        sample = sample * 127; // Convert to 8-bit range
+                    }
+                    wavBuffer[i * targetChannels + channel] = sample;
+                }
+            }
+            // Pass the duration to extractAudioAnalysis
+            return await extractAudioAnalysis({
+                arrayBuffer: wavBuffer.buffer,
+                bitDepth: decodingOptions?.targetBitDepth ?? 32,
+                skipWavHeader: true,
+                sampleRate: targetSampleRate,
+                numberOfChannels: targetChannels,
+                durationMs: effectiveDurationMs,
+                ...restProps,
+            });
+        }
+        catch (error) {
+            console.error('Failed to process audio:', error);
+            throw error;
+        }
+    }
+    else {
+        // For native platforms, pass through all options
+        return await extractAudioAnalysis({
+            fileUri,
+            decodingOptions,
+            ...restProps,
+        });
+    }
+}
 export const extractAudioAnalysis = async ({ fileUri, pointsPerSecond = 20, arrayBuffer, bitDepth, skipWavHeader = true, durationMs, sampleRate, numberOfChannels, algorithm = 'rms', features, featuresExtratorUrl, logger, }) => {
     if (isWeb) {
         if (!arrayBuffer && !fileUri) {
@@ -83,4 +205,40 @@ export const extractAudioAnalysis = async ({ fileUri, pointsPerSecond = 20, arra
         return res;
     }
 };
+export async function extractPreview({ fileUri, numberOfPoints, algorithm = 'rms', startTime, endTime, decodingOptions, }) {
+    if (isWeb) {
+        // For web, we can reuse the existing extractAudioFromAnyFormat with modified parameters
+        const analysis = await extractAudioFromAnyFormat({
+            fileUri,
+            algorithm,
+            decodingOptions,
+            startTime, // Pass startTime
+            endTime, // Pass endTime
+            pointsPerSecond: (numberOfPoints ?? 100) /
+                ((endTime ? endTime - (startTime || 0) : 1000) / 1000), // Adjust points per second calculation
+        });
+        // Convert AudioAnalysis to AudioPreview format and adjust duration
+        return {
+            pointsPerSecond: analysis.pointsPerSecond,
+            durationMs: endTime
+                ? endTime - (startTime || 0)
+                : analysis.durationMs, // Use range duration if specified
+            amplitudeRange: analysis.amplitudeRange,
+            dataPoints: analysis.dataPoints.map((point) => ({
+                id: point.id,
+                amplitude: point.amplitude,
+                startTime: point.startTime,
+                endTime: point.endTime,
+            })),
+        };
+    }
+    return await ExpoAudioStreamModule.extractPreview({
+        fileUri,
+        numberOfPoints,
+        algorithm,
+        startTime,
+        endTime,
+        decodingOptions,
+    });
+}
 //# sourceMappingURL=extractAudioAnalysis.js.map