serve.zone/siprouter
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(proxy-engine): upgrade the internal audio bus to 48kHz f32 with per-leg denoising and improve SIP leg routing

Browse Source
This commit is contained in:
Jürgen Kunz
2026-04-10 15:58:41 +00:00
parent 10ad432a4c
commit 73b28f5f57
10 changed files with 194 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
rust/crates/proxy-engine/src/audio_player.rs
View File

@@ -10,9 +10,9 @@ use tokio::net::UdpSocket;
use tokio::time::{self, Duration};
/// Mixing sample rate used by the mixer (must stay in sync with mixer::MIX_RATE).
const MIX_RATE: u32 = 16000;
const MIX_RATE: u32 = 48000;
/// Samples per 20ms frame at the mixing rate.
const MIX_FRAME_SIZE: usize = 320;
const MIX_FRAME_SIZE: usize = 960;
/// Play a WAV file as RTP to a destination.
/// Returns when playback is complete.
@@ -178,9 +178,9 @@ pub async fn play_beep(
Ok((seq, ts))
}
/// Load a WAV file and split it into 20ms PCM frames at 16kHz.
/// Load a WAV file and split it into 20ms f32 PCM frames at 48kHz.
/// Used by the leg interaction system to prepare prompt audio for the mixer.
pub fn load_prompt_pcm_frames(wav_path: &str) -> Result<Vec<Vec<i16>>, String> {
pub fn load_prompt_pcm_frames(wav_path: &str) -> Result<Vec<Vec<f32>>, String> {
let path = Path::new(wav_path);
if !path.exists() {
return Err(format!("WAV file not found: {wav_path}"));
@@ -191,17 +191,17 @@ pub fn load_prompt_pcm_frames(wav_path: &str) -> Result<Vec<Vec<i16>>, String> {
let spec = reader.spec();
let wav_rate = spec.sample_rate;
// Read all samples as i16.
let samples: Vec<i16> = if spec.bits_per_sample == 16 {
// Read all samples as f32 in [-1.0, 1.0].
let samples: Vec<f32> = if spec.bits_per_sample == 16 {
reader
.samples::<i16>()
.filter_map(|s| s.ok())
.map(|s| s as f32 / 32768.0)
.collect()
} else if spec.bits_per_sample == 32 && spec.sample_format == hound::SampleFormat::Float {
reader
.samples::<f32>()
.filter_map(|s| s.ok())
.map(|s| (s * 32767.0).round().clamp(-32768.0, 32767.0) as i16)
.collect()
} else {
return Err(format!(
@@ -214,24 +214,24 @@ pub fn load_prompt_pcm_frames(wav_path: &str) -> Result<Vec<Vec<i16>>, String> {
return Ok(vec![]);
}
// Resample to MIX_RATE (16kHz) if needed.
// Resample to MIX_RATE (48kHz) if needed.
let resampled = if wav_rate != MIX_RATE {
let mut transcoder = TranscodeState::new().map_err(|e| format!("codec init: {e}"))?;
transcoder
.resample(&samples, wav_rate, MIX_RATE)
.resample_f32(&samples, wav_rate, MIX_RATE)
.map_err(|e| format!("resample: {e}"))?
} else {
samples
};
// Split into MIX_FRAME_SIZE (320) sample frames.
// Split into MIX_FRAME_SIZE (960) sample frames.
let mut frames = Vec::new();
let mut offset = 0;
while offset < resampled.len() {
let end = (offset + MIX_FRAME_SIZE).min(resampled.len());
let mut frame = resampled[offset..end].to_vec();
// Pad short final frame with silence.
frame.resize(MIX_FRAME_SIZE, 0);
frame.resize(MIX_FRAME_SIZE, 0.0);
frames.push(frame);
offset += MIX_FRAME_SIZE;
}