Add voice notes: on-device transcription, multi-language, watch capture
- Schema v2: Note.AudioInfo, .m4a sidecar next to the note JSON in iCloud - AudioRecorderService (iOS/macOS) + SpeechAnalyzer transcription pipeline with enabled-language set and confidence-based auto-pick, re-transcribe menu - Settings > Transcription > Languages with asset download/reserve handling - watchOS app + accessory complication: one-button recorder, WCSession transferFile to phone, WatchInbox staging, direct-upsert ingestion - Player UI, transcription status chips, quick-capture mic in notes list - Version 0.2, changelog + README updated
This commit is contained in:
@@ -0,0 +1,73 @@
|
||||
import Foundation
|
||||
|
||||
/// Versioned metadata carried alongside a watch audio recording over
|
||||
/// `WCSession.transferFile(_:metadata:)`. The watch encodes it into the
|
||||
/// transfer's metadata dictionary; the phone decodes it on delivery.
|
||||
///
|
||||
/// Versioned so a newer watch build can extend the field set without an older
|
||||
/// phone build silently misreading it: a missing, unknown, or newer version
|
||||
/// decodes to `nil` (a forward gate). On that outcome the phone still stages the
|
||||
/// audio bytes but skips ingest, so a future phone build can pick them up.
|
||||
///
|
||||
/// Lives in `Shared/`, compiled into the iOS app and the watch app (not the Mac
|
||||
/// app). Foundation-only, so it is safe on both platforms.
|
||||
struct AudioNotePayload: Equatable, Sendable {
|
||||
/// The wire version this build writes. Bump only when the field set changes
|
||||
/// in a way an older decoder can't interpret.
|
||||
static let currentVersion = 1
|
||||
|
||||
/// ULID string minted on the watch at record start — the note's identity and
|
||||
/// its UTC time bucket. Also the staged filename base on the phone.
|
||||
let id: String
|
||||
/// Wall-clock instant recording started.
|
||||
let recordedAt: Date
|
||||
/// Recording length in seconds.
|
||||
let duration: TimeInterval
|
||||
/// IANA time-zone identifier the recording was made in (e.g. "Europe/Berlin"),
|
||||
/// or nil if unknown.
|
||||
let timeZoneID: String?
|
||||
|
||||
private enum Key {
|
||||
static let version = "v"
|
||||
static let id = "id"
|
||||
static let recordedAt = "recordedAt"
|
||||
static let duration = "duration"
|
||||
static let timeZone = "tz"
|
||||
}
|
||||
|
||||
init(id: String, recordedAt: Date, duration: TimeInterval, timeZoneID: String?) {
|
||||
self.id = id
|
||||
self.recordedAt = recordedAt
|
||||
self.duration = duration
|
||||
self.timeZoneID = timeZoneID
|
||||
}
|
||||
|
||||
/// A plist-serializable dictionary for `WCSession.transferFile(_:metadata:)`.
|
||||
/// Every value type (Int, String, Date, Double) survives WatchConnectivity's
|
||||
/// metadata plist encoding.
|
||||
func metadata() -> [String: Any] {
|
||||
var dict: [String: Any] = [
|
||||
Key.version: Self.currentVersion,
|
||||
Key.id: id,
|
||||
Key.recordedAt: recordedAt,
|
||||
Key.duration: duration,
|
||||
]
|
||||
if let timeZoneID { dict[Key.timeZone] = timeZoneID }
|
||||
return dict
|
||||
}
|
||||
|
||||
/// Decode a received metadata dictionary. Returns `nil` when the version is
|
||||
/// missing, unknown, or newer than this build understands (the forward gate),
|
||||
/// or when a required field is absent or malformed.
|
||||
init?(metadata: [String: Any]) {
|
||||
guard let version = metadata[Key.version] as? Int,
|
||||
version >= 1, version <= Self.currentVersion,
|
||||
let id = metadata[Key.id] as? String,
|
||||
let recordedAt = metadata[Key.recordedAt] as? Date,
|
||||
let duration = metadata[Key.duration] as? Double else { return nil }
|
||||
self.id = id
|
||||
self.recordedAt = recordedAt
|
||||
self.duration = duration
|
||||
self.timeZoneID = metadata[Key.timeZone] as? String
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user