@siteed/audio-studio 3.0.2-beta.2 → 3.0.3

package/CHANGELOG.md

@@ -7,15 +7,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [3.0.1] - 2026-03-21
 
+## [3.0.3] - 2026-04-12
+### Changed
+- fix(audio-studio): convert trim ranges from Double to Long on Android (#347) (#360) ([6099e0e](https://github.com/deeeed/audiolab/commit/6099e0e81f3c8d7b1c109b415ad63e924f3f043b))
+- feat(audio-studio): web trimAudio, WASM refactor, new utilities (#344) ([3d4862a](https://github.com/deeeed/audiolab/commit/3d4862a57a5eb2496169d27f758d7628d7d3659a))
+- feat(sherpa-voice): comprehensive logging + fix Android prod model extraction (#342) ([5b20594](https://github.com/deeeed/audiolab/commit/5b20594c729a9deb703cbc2e23c07daa616149ab))
+- fix(audio-studio): remove blocking CDN poll from publish.sh, sync wasmConfig to 3.0.2 ([290409a](https://github.com/deeeed/audiolab/commit/290409aae8d1160e1952a5ee1961ce3864fbb0c8))
+- chore(audio-studio): release @siteed/audio-studio@3.0.2 ([ebd3300](https://github.com/deeeed/audiolab/commit/ebd330098d2756e6d5a555126e2dfc3fb038d155))
+## [3.0.2] - 2026-03-21
+### Changed
+- fix(audio-studio): load WASM via CDN URL instead of broken relative path ([7427f28](https://github.com/deeeed/audiolab/commit/7427f289d273ffad609a4c6b0fb45c5094445dde))
+- chore(audio-studio): disable conventionalCommits in publisher config, rewrite clean CHANGELOG ([4a2bbfa](https://github.com/deeeed/audiolab/commit/4a2bbfa605a56cab06618c0ca1afe6ff8cb19441))
+- chore(audio-studio): release @siteed/audio-studio@3.0.1 ([04fe6f7](https://github.com/deeeed/audiolab/commit/04fe6f706d372e3ced0f83b796923c490bebd64d))
+## [3.0.1] - 2026-03-21
 ### Fixed
 - Add `@expo/config-plugins` to `peerDependencies` — fixes Yarn PnP `ambiguous require` error during `expo prebuild` (#341)
 - WASM path resolution in build output — `prebuilt/` is now copied into `build/cjs/` and `build/esm/` so Metro resolves WASM imports correctly after install (#341)
 - Split WASM modules into separate web/native platform files to prevent Metro bundling issues (#338)
-
 ## [3.0.0] - 2026-03-20
-
 ### BREAKING CHANGES
 - Package renamed from `@siteed/expo-audio-studio` to `@siteed/audio-studio`. The old package continues as a backwards-compatible shim.
 - Native module renamed from `ExpoAudioStream` to `AudioStudio`
@@ -36,214 +46,140 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Performance
 - Optimized mel spectrogram C++ implementation
-
 ## [2.18.5] - 2026-02-23
-
 ### Fixed
 - Android: guard Bluetooth API calls behind permission check on API 31+ (#294)
 - Android: migrate phone state listener to `TelephonyCallback` on API 31+ (#275)
 - Android: reset `startTime` in `startRecording` and validate hardware format (#298, #223)
 - Android: gate foreground service on `enableBackgroundAudio` (#288, #294)
 - Android: sanitize options before native bridge calls to prevent crash
-
 ## [2.18.4] - 2026-02-16
-
 ### Added
 - Expo SDK 54 (React Native 0.81, React 19) support (#305)
 
 ### Fixed
 - iOS: include compression data in `onAudioStream` events
 - Android: properly emit final chunk of audio data on stop (#293)
-
 ## [2.18.1] - 2025-08-02
-
 ### Added
 - Improved memory monitoring
-
 ## [2.18.0] - 2025-08-01
-
 ### Fixed
 - Android: optimize buffer size to prevent OOM errors
 - Android: invalid paused duration calculation
-
 ## [2.17.0] - 2025-07-31
-
 ### Fixed
 - Android: fix `OutOfMemoryError` by tracking stream position correctly
-
 ## [2.16.1] - 2025-07-27
-
 ### Fixed
 - Android: audio analysis accumulation showing 0 bytes
-
 ## [2.16.0] - 2025-07-27
-
 ### Performance
 - Android: optimize stop recording performance for long recordings
-
 ## [2.15.0] - 2025-07-15
-
 ### Added
 - Android: `showPauseResumeActions` option to notification config (#282)
-
 ## [2.14.4] - 2025-07-15
-
 ### Fixed
 - Plugin: respect `enableDeviceDetection` configuration for Android permissions
 - Android: add missing `BLUETOOTH_ADMIN` permission for device detection
-
 ## [2.14.3] - 2025-06-12
-
 ### Changed
 - Remove analysis bit depth logging for cleaner debug output
-
 ## [2.14.2] - 2025-06-11
-
 ### Added
 - Platform limitations validation and documentation
 
 ### Fixed
 - iOS: update compressed file size when primary output is disabled
-
 ## [2.14.1] - 2025-06-11
-
 ### Fixed
 - Android: fix duration returning 0 when primary output is disabled (#244)
-
 ## [2.14.0] - 2025-06-11
-
 ### Performance
 - Comprehensive cross-platform stop recording performance optimization
-
 ## [2.13.2] - 2025-06-10
-
 ### Fixed
 - Invalid type exports
-
 ## [2.13.1] - 2025-06-09
-
 ### Added
 - Sub-100ms audio events analysis and improvements (#270)
 
 ### Fixed
 - Update `expo-modules-core` peer dependency for Expo SDK 53 compatibility
-
 ## [2.13.0] - 2025-06-09
-
 ### Added
 - Enhanced device detection and management — configurable `enableDeviceDetection`, automatic connect/disconnect events, force refresh (#269)
-
 ## [2.12.3] - 2025-06-07
-
 ### Changed
 - Adjust audio focus request timing in `AudioRecorderManager`
-
 ## [2.12.2] - 2025-06-07
-
 ### Fixed
 - Android: audio focus strategy for background recording (#267)
-
 ## [2.12.0] - 2025-06-07
-
 ### Added
 - Android-only `audioFocusStrategy` option (#264)
 
 ### Fixed
 - Android: PCM streaming duration calculation bug (#263, #265)
-
 ## [2.11.0] - 2025-06-05
-
 ### Added
 - M4A support with `preferRawStream` option (#261)
 
 ### Fixed
 - Enforce 10ms minimum interval on both platforms (#262)
 - Android: proper `MediaCodec` resource cleanup in `AudioProcessor`
-
 ## [2.10.6] - 2025-06-04
-
 ### Fixed
 - iOS: prevent `durationMs` returning 0 (#244, #260)
-
 ## [2.10.5] - 2025-06-04
-
 ### Fixed
 - iOS: enable audio streaming when primary output is disabled (#259)
-
 ## [2.10.4] - 2025-06-03
-
 ### Fixed
 - iOS: resolve Swift compilation scope error in `AudioStreamManager` (#256)
-
 ## [2.10.3] - 2025-06-02
-
 ### Fixed
 - Prevent `UninitializedPropertyAccessException` crash in developer menu (#250)
 - Return compression info when primary output is disabled (#244, #249)
-
 ## [2.10.2] - 2025-05-31
-
 ### Fixed
 - Buffer size calculation and duplicate emission fix (#248)
-
 ## [2.10.1] - 2025-05-27
-
 ### Fixed
 - `useAudioRecorder`: update `intervalId` type for better type safety
-
 ## [2.10.0] - 2025-05-26
-
 ### Added
 - Buffer duration control and `skipFileWriting` options
 - Enhanced testing framework with instrumented tests (#242)
-
 ## [2.9.0] - 2025-05-15
-
 ### Added
 - Web audio chunk handling improvements (#240)
-
 ## [2.8.4] - 2025-05-11
-
 ### Fixed
 - Expo plugin setup
-
 ## [2.8.3] - 2025-05-06
-
 ### Changed
 - Update plugin configuration to use ESM format
-
 ## [2.8.2] - 2025-05-06
-
 ### Changed
 - TypeScript configurations for dual module (ESM/CJS) support
-
 ## [2.8.1] - 2025-05-06
-
 ### Added
 - Dual module format (ESM/CommonJS) to resolve module resolution issues (#235)
-
 ## [2.7.0] - 2025-05-04
-
 ### Fixed
 - iOS: enhance background audio recording and audio format conversion (#228)
-
 ## [2.6.2] - 2025-05-01
-
 ### Fixed
 - Android: ensure foreground-only audio recording works with `FOREGROUND_SERVICE` (#202, #221)
-
 ## [2.6.1] - 2025-05-01
-
 ### Fixed
 - iOS: resolve hardware format mismatch crash and enhance logging (#220)
-
 ## [2.6.0] - 2025-05-01
-
 ### Fixed
 - Web: resolve audio recording issue without compression (#217, #219)
-
 ## [2.5.0] - 2025-04-30
-
 ### Added
 - Complete Android implementation for audio device API (#214)
 - Cross-platform audio device detection, selection, and fallback handling (#213)
@@ -251,49 +187,33 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 - iOS: ensure complete audio data emission on recording stop/pause (#215)
-
 ## [2.4.1] - 2025-04-08
-
 ### Added
 - Enhanced background audio handling and permission checks (#200)
-
 ## [2.4.0] - 2025-04-03
-
 ### Fixed
 - iOS: resolve sample rate mismatch and enhance recording stability (#198)
 - Android: enhance permission handling for phone state and notifications (#196)
-
 ## [2.3.1] - 2025-04-03
-
 ### Changed
 - Remove external CRC32 library dependency (#195)
-
 ## [2.3.0] - 2025-03-29
-
 ### Fixed
 - Always generate a new UUID unless filename is provided (#182)
-
 ## [2.2.0] - 2025-03-28
-
 ### Changed
 - Platform-specific CRC32 handling
-
 ## [2.1.0] - 2025-03-04
-
 ### Added
 - Mel spectrogram extraction and language detection (#157)
 - Audio import functionality and decibel visualization (#156)
 - iOS trim support with custom filename (#152)
 - Sample rate control and web trimming support (#151)
 - Audio trimming with optimized processing and detailed feedback (#150, #149)
-
 ## [2.0.1] - 2025-02-27
-
 ### Changed
 - Update background mode handling for audio stream plugin
-
 ## [2.0.0] - 2025-02-27
-
 ### Added
 - Full audio analysis with spectral features and time range controls (#132)
 - `extractAudioData` API
@@ -302,166 +222,110 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 - Audio recording reliability improvements and web IndexedDB management (#146)
-
 ## [1.17.0] - 2025-02-18
-
 ### Added
 - Interval audio analysis for web, Android, and iOS (#125, #126)
-
 ## [1.16.0] - 2025-02-17
-
 ### Fixed
 - iOS: prevent adding background modes when disabled
 - iOS: replace CallKit with `AVAudioSession` for phone call detection
-
 ## [1.15.1] - 2025-02-17
-
 ### Fixed
 - iOS: restore Opus compression support (#122)
 - Emit audio analysis without blocking the recording thread
-
 ## [1.15.0] - 2025-02-15
-
 ### Fixed
 - iOS: improve audio recording interruption handling and auto-resume (#119)
 - Android: improve background recording and call interruption handling (#118)
-
 ## [1.14.2] - 2025-02-13
-
 ### Fixed
 - Clear recording metadata on STOP action
-
 ## [1.14.1] - 2025-02-12
-
 ### Fixed
 - Enable background recording by default (#114)
-
 ## [1.14.0] - 2025-02-12
-
 ### Fixed
 - `keepAwake` issue on iOS and auto-resume after call (#113)
-
 ## [1.13.2] - 2025-02-10
-
 ### Fixed
 - Ensure foreground service starts within required timeframe
-
 ## [1.13.0] - 2025-02-09
-
 ### Added
 - Audio decode support (#104)
 
 ### Fixed
 - Background recording issues and status checking (#103)
-
 ## [1.12.1] - 2025-02-01
-
 ### Fixed
 - Improve audio recording interruption handling and consistency (#98)
-
 ## [1.12.0] - 2025-01-31
-
 ### Added
 - Call state checks before starting or resuming recording (#94)
 - Custom filename and directory support for recordings (#92)
 - Compressed recording info with file size (#90)
-
 ## [1.11.3] - 2025-01-25
-
 ### Fixed
 - Disable duplicate notification alerts (#82)
-
 ## [1.11.2] - 2025-01-22
-
 ### Fixed
 - Resources not cleaned up properly on app kill (#80)
-
 ## [1.11.0] - 2025-01-22
-
 ### Added
 - Intelligent call interruption handling and compression improvements (#78)
-
 ## [1.10.0] - 2025-01-14
-
 ### Added
 - Support for pausing and resuming compressed recordings
 - Optimized notification channel settings
-
 ## [1.9.2] - 2025-01-12
-
 ### Fixed
 - iOS: bitrate verification to prevent invalid values
-
 ## [1.9.1] - 2025-01-12
-
 ### Fixed
 - iOS: potentially missing compressed file info
-
 ## [1.9.0] - 2025-01-11
-
 ### Performance
 - Optimize memory usage and streaming performance for web audio recording (#75)
-
 ## [1.8.0] - 2025-01-10
-
 ### Added
 - Audio compression support
-
 ## [1.7.2] - 2025-01-07
-
 ### Fixed
 - Web: correct WAV header handling in audio recording
-
 ## [1.7.1] - 2025-01-07
-
 ### Fixed
 - Notification: avoid triggering new alerts on update (#71)
-
 ## [1.7.0] - 2025-01-05
-
 ### Fixed
 - iOS: improve audio resampling and duration tracking (#69)
 - Handle paused state in `stopRecording` (#68)
 - Reset audio recording state properly on iOS and Android (#66)
 - Android: total size not resetting on new recording (#64)
-
 ## [1.3.1] - 2024-12-05
-
 ### Added
 - Web: throttling and optimized event processing (#49)
-
 ## [1.3.0] - 2024-11-28
-
 ### Added
 - Standardize permission status response structure across platforms (#44)
-
 ## [1.2.4] - 2024-11-05
-
 ### Changed
 - Android: minimum audio interval set to 10ms
 - Plugin: do not include `notification` config by default to prevent iOS version mismatch
 
 ### Fixed
 - Remove frequently firing log statements on web
-
 ## [1.2.0] - 2024-10-24
-
 ### Added
 - `keepAwake` — continue recording when app is in background (default: true)
 - Customizable recording notifications for Android and iOS
   - Android: rich notification with live waveform, configurable actions/colors/priorities
   - iOS: media player integration
-
 ## [1.1.17] - 2024-10-21
-
 ### Added
 - Bluetooth headset support on iOS
 
 ### Fixed
 - Android: not reading custom interval audio update
-
 ## [1.0.0] - 2024-04-01
-
 ### Added
 - Initial release
 - Real-time audio streaming across iOS, Android, and web
@@ -471,6 +335,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Audio features extraction during recording
 - Consistent WAV PCM recording format across all platforms
 
-[unreleased]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@3.0.1...HEAD
+[unreleased]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@3.0.3...HEAD
+[3.0.3]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@3.0.2...@siteed/audio-studio@3.0.3
+[3.0.2]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@3.0.2-beta.2...@siteed/audio-studio@3.0.2
 [3.0.1]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@3.0.0...@siteed/audio-studio@3.0.1
 [3.0.0]: https://github.com/deeeed/audiolab/compare/@siteed/audio-studio@2.18.5...@siteed/audio-studio@3.0.0

package/android/src/main/java/net/siteed/audiostudio/AudioStudioModule.kt

@@ -382,7 +382,13 @@ class AudioStudioModule : Module(), EventSender {
                 val endTimeMs = (options["endTimeMs"] as? Number)?.toLong()
                 
                 @Suppress("UNCHECKED_CAST")
-                val ranges = options["ranges"] as? List<Map<String, Long>>
+                val rawRanges = options["ranges"] as? List<Map<String, Any>>
+                val ranges = rawRanges?.map { range ->
+                    mapOf(
+                        "startTimeMs" to ((range["startTimeMs"] as? Number)?.toLong() ?: 0L),
+                        "endTimeMs" to ((range["endTimeMs"] as? Number)?.toLong() ?: 0L)
+                    )
+                }
                 
                 val outputFileName = options["outputFileName"] as? String
                 

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

@@ -1 +1 @@
-{"version":3,"file":"AudioAnalysis.types.js","sourceRoot":"","sources":["../../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":";AAAA,iEAAiE","sourcesContent":["// packages/audio-studio/src/AudioAnalysis/AudioAnalysis.types.ts\n\nimport { BitDepth, ConsoleLike } from '../AudioStudio.types'\n\n/**\n * Represents the configuration for decoding audio data.\n */\nexport interface DecodingConfig {\n    /** Target sample rate for decoded audio (Android and Web) */\n    targetSampleRate?: number\n    /** Target number of channels (Android and Web) */\n    targetChannels?: number\n    /** Target bit depth (Android and Web) */\n    targetBitDepth?: BitDepth\n    /** Whether to normalize audio levels (Android and Web) */\n    normalizeAudio?: boolean\n}\n\n/**\n * Represents speech-related features extracted from audio.\n */\nexport interface SpeechFeatures {\n    isActive: boolean // Whether speech is detected in this segment\n    speakerId?: number // Optional speaker identification\n    // Could add more speech-related features here like:\n    // confidence: number\n    // language?: string\n    // sentiment?: number\n    // etc.\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    melSpectrogram?: number[] // Mel-scaled spectrogram representation of the audio.\n    spectralContrast?: number[] // Spectral contrast features representing the difference between peaks and valleys.\n    tonnetz?: number[] // Tonal network features representing harmonic relationships.\n    pitch?: number // Pitch of the audio signal, measured in Hertz (Hz).\n    crc32?: number // crc32 checksum of the audio signal, used to verify the integrity of the audio.\n}\n\n/**\n * Options to specify which audio features to extract.\n * Note: Advanced features (spectral features, chromagram, pitch, etc.) are experimental,\n * especially during live recording, due to high processing requirements.\n */\nexport interface AudioFeaturesOptions {\n    // Basic features - well optimized\n    energy?: boolean\n    rms?: boolean\n    zcr?: boolean\n\n    // Advanced features - experimental, may impact performance in live recording\n    mfcc?: boolean\n    spectralCentroid?: boolean\n    spectralFlatness?: boolean\n    spectralRolloff?: boolean\n    spectralBandwidth?: boolean\n    chromagram?: boolean\n    tempo?: boolean\n    hnr?: boolean\n    melSpectrogram?: boolean\n    spectralContrast?: boolean\n    tonnetz?: boolean\n    pitch?: boolean\n\n    // Utility\n    crc32?: boolean\n}\n\n/**\n * Represents a single data point in the audio analysis.\n */\nexport interface DataPoint {\n    id: number\n    amplitude: number // Peak amplitude for the segment\n    rms: number // Root mean square value\n    dB: number // dBFS (decibels relative to full scale) computed from RMS value\n    silent: boolean // Always computed\n    features?: AudioFeatures\n    speech?: SpeechFeatures\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}\n\n/**\n * Represents the complete data from the audio analysis.\n */\nexport interface AudioAnalysis {\n    segmentDurationMs: number // Duration of each segment in milliseconds\n    durationMs: number // Duration of the audio in milliseconds\n    /**\n     * Bit depth used for audio analysis processing.\n     *\n     * **Important**: This represents the internal processing bit depth, which may differ\n     * from the recording bit depth. Audio is typically converted to 32-bit float for\n     * analysis to ensure precision in calculations, regardless of the original recording format.\n     *\n     * Platform behavior:\n     * - iOS: Always 32 (float processing)\n     * - Android: Always 32 (float processing)\n     * - Web: Always 32 (Web Audio API standard)\n     *\n     * The actual recorded file will maintain the requested bit depth (8, 16, or 32).\n     */\n    bitDepth: number\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    amplitudeRange: {\n        min: number\n        max: number\n    }\n    rmsRange: {\n        min: number\n        max: number\n    }\n    extractionTimeMs: number // Time taken to extract/process the analysis in milliseconds\n    // TODO: speaker changes into a broader speech analysis section\n    speechAnalysis?: {\n        speakerChanges: {\n            timestamp: number\n            speakerId: number\n        }[]\n        // Could add more speech analysis data here like:\n        // dominantSpeaker?: number\n        // totalSpeechDuration?: number\n        // speakerStats?: { [speakerId: number]: { duration: number, segments: number } }\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    startTimeMs?: number\n    /** End time in milliseconds */\n    endTimeMs?: 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     * Optional logger for debugging.\n     */\n    logger?: ConsoleLike\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 * Options for mel-spectrogram extraction\n *\n * @experimental This feature is experimental and currently only available on Android.\n * The API may change in future versions.\n */\nexport interface ExtractMelSpectrogramOptions {\n    fileUri?: string // Path to audio file\n    arrayBuffer?: ArrayBuffer // Raw audio buffer\n    windowSizeMs: number // Window size in ms (e.g., 25)\n    hopLengthMs: number // Hop length in ms (e.g., 10)\n    nMels: number // Number of mel filters (e.g., 60)\n    fMin?: number // Min frequency (default: 0)\n    fMax?: number // Max frequency (default: sampleRate / 2)\n    windowType?: 'hann' | 'hamming' // Window function (default: 'hann')\n    normalize?: boolean // Mean normalization (default: false)\n    logScale?: boolean // Log scaling of mel energies (default: true)\n    decodingOptions?: DecodingConfig // Audio decoding settings\n    /** Optional start time in ms. If neither startTimeMs nor endTimeMs is set, defaults to 0. */\n    startTimeMs?: number\n    /** Optional end time in ms. Clamped so that the range does not exceed MAX_DURATION_MS (30 s). */\n    endTimeMs?: number\n    logger?: ConsoleLike\n}\n\n/**\n * Return type for mel spectrogram extraction\n *\n * @experimental This feature is experimental and currently only available on Android.\n * The API may change in future versions.\n */\nexport interface MelSpectrogram {\n    spectrogram: number[][] // 2D array [time][mel]\n    sampleRate: number // Audio sample rate\n    nMels: number // Number of mel filters\n    timeSteps: number // Number of time frames\n    durationMs: number // Audio duration in ms\n}\n"]}
+{"version":3,"file":"AudioAnalysis.types.js","sourceRoot":"","sources":["../../../src/AudioAnalysis/AudioAnalysis.types.ts"],"names":[],"mappings":";AAAA,iEAAiE","sourcesContent":["// packages/audio-studio/src/AudioAnalysis/AudioAnalysis.types.ts\n\nimport { BitDepth, ConsoleLike } from '../AudioStudio.types'\n\n/**\n * Represents the configuration for decoding audio data.\n */\nexport interface DecodingConfig {\n    /** Target sample rate for decoded audio (Android and Web) */\n    targetSampleRate?: number\n    /** Target number of channels (Android and Web) */\n    targetChannels?: number\n    /** Target bit depth (Android and Web) */\n    targetBitDepth?: BitDepth\n    /** Whether to normalize audio levels (Android and Web) */\n    normalizeAudio?: boolean\n}\n\n/**\n * Represents speech-related features extracted from audio.\n */\nexport interface SpeechFeatures {\n    isActive: boolean // Whether speech is detected in this segment\n    speakerId?: number // Optional speaker identification\n    // Could add more speech-related features here like:\n    // confidence: number\n    // language?: string\n    // sentiment?: number\n    // etc.\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    melSpectrogram?: number[] // Mel-scaled spectrogram representation of the audio.\n    spectralContrast?: number[] // Spectral contrast features representing the difference between peaks and valleys.\n    tonnetz?: number[] // Tonal network features representing harmonic relationships.\n    pitch?: number // Pitch of the audio signal, measured in Hertz (Hz).\n    crc32?: number // crc32 checksum of the audio signal, used to verify the integrity of the audio.\n}\n\n/**\n * Options to specify which audio features to extract.\n * Note: Advanced features (spectral features, chromagram, pitch, etc.) are experimental,\n * especially during live recording, due to high processing requirements.\n */\nexport interface AudioFeaturesOptions {\n    // Basic features - well optimized\n    energy?: boolean\n    rms?: boolean\n    zcr?: boolean\n\n    // Advanced features - experimental, may impact performance in live recording\n    mfcc?: boolean\n    spectralCentroid?: boolean\n    spectralFlatness?: boolean\n    spectralRolloff?: boolean\n    spectralBandwidth?: boolean\n    chromagram?: boolean\n    tempo?: boolean\n    hnr?: boolean\n    melSpectrogram?: boolean\n    spectralContrast?: boolean\n    tonnetz?: boolean\n    pitch?: boolean\n\n    // Utility\n    crc32?: boolean\n}\n\n/**\n * Represents a single data point in the audio analysis.\n */\nexport interface DataPoint {\n    id: number\n    amplitude: number // Peak amplitude for the segment\n    rms: number // Root mean square value\n    dB: number // dBFS (decibels relative to full scale) computed from RMS value\n    silent: boolean // Always computed\n    features?: AudioFeatures\n    speech?: SpeechFeatures\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}\n\n/**\n * Represents the complete data from the audio analysis.\n */\nexport interface AudioAnalysis {\n    segmentDurationMs: number // Duration of each segment in milliseconds\n    durationMs: number // Duration of the audio in milliseconds\n    /**\n     * Bit depth used for audio analysis processing.\n     *\n     * **Important**: This represents the internal processing bit depth, which may differ\n     * from the recording bit depth. Audio is typically converted to 32-bit float for\n     * analysis to ensure precision in calculations, regardless of the original recording format.\n     *\n     * Platform behavior:\n     * - iOS: Always 32 (float processing)\n     * - Android: Always 32 (float processing)\n     * - Web: Always 32 (Web Audio API standard)\n     *\n     * The actual recorded file will maintain the requested bit depth (8, 16, or 32).\n     */\n    bitDepth: number\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    amplitudeRange: {\n        min: number\n        max: number\n    }\n    rmsRange: {\n        min: number\n        max: number\n    }\n    extractionTimeMs: number // Time taken to extract/process the analysis in milliseconds\n    // TODO: speaker changes into a broader speech analysis section\n    speechAnalysis?: {\n        speakerChanges: {\n            timestamp: number\n            speakerId: number\n        }[]\n        // Could add more speech analysis data here like:\n        // dominantSpeaker?: number\n        // totalSpeechDuration?: number\n        // speakerStats?: { [speakerId: number]: { duration: number, segments: number } }\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    startTimeMs?: number\n    /** End time in milliseconds */\n    endTimeMs?: 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     * Optional logger for debugging.\n     */\n    logger?: ConsoleLike\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 * Options for mel-spectrogram extraction\n *\n * @experimental This feature is experimental and currently only available on Android.\n * The API may change in future versions.\n */\nexport interface ExtractMelSpectrogramOptions {\n    fileUri?: string // Path to audio file\n    arrayBuffer?: ArrayBuffer // Raw audio buffer\n    windowSizeMs: number // Window size in ms (e.g., 25)\n    hopLengthMs: number // Hop length in ms (e.g., 10)\n    nMels: number // Number of mel filters (e.g., 60)\n    fMin?: number // Min frequency (default: 0)\n    fMax?: number // Max frequency (default: sampleRate / 2)\n    windowType?: 'hann' | 'hamming' // Window function (default: 'hann')\n    normalize?: boolean // Mean normalization (default: false)\n    logScale?: boolean // Log scaling of mel energies (default: true)\n    decodingOptions?: DecodingConfig // Audio decoding settings\n    /** Optional start time in ms. If neither startTimeMs nor endTimeMs is set, defaults to 0. */\n    startTimeMs?: number\n    /** Optional end time in ms. Clamped so that the range does not exceed MAX_DURATION_MS (30 s). */\n    endTimeMs?: number\n    logger?: ConsoleLike\n}\n\n/**\n * Result type for WASM-based audio feature extraction.\n */\nexport interface AudioFeaturesWasmResult {\n    spectralCentroid: number\n    spectralFlatness: number\n    spectralRolloff: number\n    spectralBandwidth: number\n    mfcc: number[]\n    chromagram: number[]\n}\n\n/**\n * Return type for mel spectrogram extraction\n *\n * @experimental This feature is experimental and currently only available on Android.\n * The API may change in future versions.\n */\nexport interface MelSpectrogram {\n    spectrogram: number[][] // 2D array [time][mel]\n    sampleRate: number // Audio sample rate\n    nMels: number // Number of mel filters\n    timeSteps: number // Number of time frames\n    durationMs: number // Audio duration in ms\n}\n"]}

package/build/cjs/AudioAnalysis/audioFeaturesWasm.js

@@ -1,15 +1,18 @@
 "use strict";
 // Native stub — WASM audio features is web-only.
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.initAudioFeaturesWasm = initAudioFeaturesWasm;
-exports.computeAudioFeaturesFrameWasm = computeAudioFeaturesFrameWasm;
+exports.AudioFeaturesStreamingSession = void 0;
 exports.computeAudioFeaturesWasm = computeAudioFeaturesWasm;
-async function initAudioFeaturesWasm(_sampleRate, _fftLength, _nMfcc, _nMelFilters, _computeMfcc, _computeChroma) {
-    throw new Error('WASM audio features is not available on native');
-}
-function computeAudioFeaturesFrameWasm(_samples) {
-    return null;
+class AudioFeaturesStreamingSession {
+    static async create(_sampleRate, _fftLength, _nMfcc, _nMelFilters, _computeMfcc, _computeChroma) {
+        throw new Error('WASM audio features is not available on native');
+    }
+    computeFrame(_samples) {
+        return null;
+    }
+    dispose() { }
 }
+exports.AudioFeaturesStreamingSession = AudioFeaturesStreamingSession;
 async function computeAudioFeaturesWasm(_audioData, _sampleRate, _fftLength, _nMfcc, _nMelFilters, _computeMfcc, _computeChroma) {
     throw new Error('WASM audio features is not available on native');
 }

package/build/cjs/AudioAnalysis/audioFeaturesWasm.js.map

@@ -1 +1 @@
-{"version":3,"file":"audioFeaturesWasm.js","sourceRoot":"","sources":["../../../src/AudioAnalysis/audioFeaturesWasm.ts"],"names":[],"mappings":";AAAA,iDAAiD;;AAWjD,sDASC;AAED,sEAIC;AAED,4DAUC;AA3BM,KAAK,UAAU,qBAAqB,CACvC,WAAmB,EACnB,UAAmB,EACnB,MAAe,EACf,YAAqB,EACrB,YAAsB,EACtB,cAAwB;IAExB,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;AACrE,CAAC;AAED,SAAgB,6BAA6B,CACzC,QAAsB;IAEtB,OAAO,IAAI,CAAA;AACf,CAAC;AAEM,KAAK,UAAU,wBAAwB,CAC1C,UAAwB,EACxB,WAAmB,EACnB,UAAmB,EACnB,MAAe,EACf,YAAqB,EACrB,YAAsB,EACtB,cAAwB;IAExB,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;AACrE,CAAC","sourcesContent":["// Native stub — WASM audio features is web-only.\n\nexport interface AudioFeaturesWasmResult {\n    spectralCentroid: number\n    spectralFlatness: number\n    spectralRolloff: number\n    spectralBandwidth: number\n    mfcc: number[]\n    chromagram: number[]\n}\n\nexport async function initAudioFeaturesWasm(\n    _sampleRate: number,\n    _fftLength?: number,\n    _nMfcc?: number,\n    _nMelFilters?: number,\n    _computeMfcc?: boolean,\n    _computeChroma?: boolean\n): Promise<void> {\n    throw new Error('WASM audio features is not available on native')\n}\n\nexport function computeAudioFeaturesFrameWasm(\n    _samples: Float32Array\n): AudioFeaturesWasmResult | null {\n    return null\n}\n\nexport async function computeAudioFeaturesWasm(\n    _audioData: Float32Array,\n    _sampleRate: number,\n    _fftLength?: number,\n    _nMfcc?: number,\n    _nMelFilters?: number,\n    _computeMfcc?: boolean,\n    _computeChroma?: boolean\n): Promise<AudioFeaturesWasmResult> {\n    throw new Error('WASM audio features is not available on native')\n}\n"]}
+{"version":3,"file":"audioFeaturesWasm.js","sourceRoot":"","sources":["../../../src/AudioAnalysis/audioFeaturesWasm.ts"],"names":[],"mappings":";AAAA,iDAAiD;;;AAuBjD,4DAUC;AA7BD,MAAa,6BAA6B;IACtC,MAAM,CAAC,KAAK,CAAC,MAAM,CACf,WAAmB,EACnB,UAAmB,EACnB,MAAe,EACf,YAAqB,EACrB,YAAsB,EACtB,cAAwB;QAExB,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;IACrE,CAAC;IAED,YAAY,CAAC,QAAsB;QAC/B,OAAO,IAAI,CAAA;IACf,CAAC;IAED,OAAO,KAAU,CAAC;CACrB;AAjBD,sEAiBC;AAEM,KAAK,UAAU,wBAAwB,CAC1C,UAAwB,EACxB,WAAmB,EACnB,UAAmB,EACnB,MAAe,EACf,YAAqB,EACrB,YAAsB,EACtB,cAAwB;IAExB,MAAM,IAAI,KAAK,CAAC,gDAAgD,CAAC,CAAA;AACrE,CAAC","sourcesContent":["// Native stub — WASM audio features is web-only.\n\nimport type { AudioFeaturesWasmResult } from './AudioAnalysis.types'\n\nexport class AudioFeaturesStreamingSession {\n    static async create(\n        _sampleRate: number,\n        _fftLength?: number,\n        _nMfcc?: number,\n        _nMelFilters?: number,\n        _computeMfcc?: boolean,\n        _computeChroma?: boolean\n    ): Promise<AudioFeaturesStreamingSession> {\n        throw new Error('WASM audio features is not available on native')\n    }\n\n    computeFrame(_samples: Float32Array): AudioFeaturesWasmResult | null {\n        return null\n    }\n\n    dispose(): void {}\n}\n\nexport async function computeAudioFeaturesWasm(\n    _audioData: Float32Array,\n    _sampleRate: number,\n    _fftLength?: number,\n    _nMfcc?: number,\n    _nMelFilters?: number,\n    _computeMfcc?: boolean,\n    _computeChroma?: boolean\n): Promise<AudioFeaturesWasmResult> {\n    throw new Error('WASM audio features is not available on native')\n}\n"]}