feat(kon): add audio crate — cpal capture, VAD, rubato resample, symphonia decode

- File decode via symphonia (mp3, aac, flac, wav, ogg) with mono mixdown
- Sinc interpolation resampling via rubato 0.15 (48kHz/44.1kHz → 16kHz)
- WAV I/O via hound (read/write with f32→i16 conversion)
- Microphone capture via cpal 0.17 (WASAPI on Windows) with mpsc channel output
- Voice activity detection via Silero VAD V5 (voice_activity_detector 0.2)
- Async decode_and_resample() for file transcription pipeline
- 3 tests passing (resample passthrough, duration preservation, WAV roundtrip)
- clippy clean, no ort version conflicts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/audio/Cargo.toml

@@ -6,3 +6,21 @@ description = "Audio capture (cpal), VAD, resampling (rubato), file decoding (sy
 
 [dependencies]
 kon-core = { path = "../core" }
+
+# Microphone capture
+cpal = "0.17"
+
+# Voice activity detection (Silero VAD V5)
+voice_activity_detector = "0.2"
+
+# High-quality resampling (sinc interpolation)
+rubato = "0.15"
+
+# WAV file I/O
+hound = "3.5"
+
+# Audio file decoding (mp3, aac, flac, wav, ogg, etc.)
+symphonia = { version = "0.5", features = ["mp3", "aac", "flac", "pcm", "vorbis", "wav", "ogg", "isomp4"] }
+
+# Async runtime for threading
+tokio = { version = "1", features = ["rt", "sync"] }