a30c9cc107
- 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>
27 lines
681 B
TOML
27 lines
681 B
TOML
[package]
|
|
name = "kon-audio"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Audio capture (cpal), VAD, resampling (rubato), file decoding (symphonia), WAV I/O (hound) for Kon"
|
|
|
|
[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"] }
|