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

21
rust/crates/proxy-engine/src/tool_leg.rs
View File

@@ -2,7 +2,7 @@
//!
//! Tool legs are observer legs that receive individual audio streams from each
//! participant in a call. The mixer pipes `ToolAudioBatch` every 20ms containing
//! each participant's decoded PCM@16kHz tagged with source leg ID.
//! each participant's decoded PCM@48kHz f32 tagged with source leg ID.
//!
//! Consumers:
//! - **Recording**: writes per-source WAV files for speaker-separated recording.
@@ -37,20 +37,25 @@ pub fn spawn_recording_tool(
while let Some(batch) = rx.recv().await {
for source in &batch.sources {
// Skip silence-only frames (all zeros = no audio activity).
let has_audio = source.pcm_16k.iter().any(|&s| s != 0);
// Skip silence-only frames (near-zero = no audio activity).
let has_audio = source.pcm_48k.iter().any(|&s| s.abs() > 1e-6);
if !has_audio && !recorders.contains_key(&source.leg_id) {
continue; // Don't create a file for silence-only sources.
}
let recorder = recorders.entry(source.leg_id.clone()).or_insert_with(|| {
let path = format!("{}/{}-{}.wav", base_dir, call_id, source.leg_id);
Recorder::new_pcm(&path, 16000, None).unwrap_or_else(|e| {
Recorder::new_pcm(&path, 48000, None).unwrap_or_else(|e| {
panic!("failed to create recorder for {}: {e}", source.leg_id);
})
});
if !recorder.write_pcm(&source.pcm_16k) {
// Convert f32 [-1.0, 1.0] to i16 for WAV writing.
let pcm_i16: Vec<i16> = source.pcm_48k
.iter()
.map(|&s| (s * 32767.0).round().clamp(-32768.0, 32767.0) as i16)
.collect();
if !recorder.write_pcm(&pcm_i16) {
// Max duration reached — stop recording this source.
break;
}
@@ -88,7 +93,7 @@ pub fn spawn_recording_tool(
/// Spawn a transcription tool leg.
///
/// The plumbing is fully real: it receives per-source unmerged PCM@16kHz from
/// The plumbing is fully real: it receives per-source unmerged PCM@48kHz f32 from
/// the mixer every 20ms. The consumer is a stub that accumulates audio and
/// reports metadata on close. Future: will stream to a Whisper HTTP endpoint.
pub fn spawn_transcription_tool(
@@ -105,7 +110,7 @@ pub fn spawn_transcription_tool(
while let Some(batch) = rx.recv().await {
for source in &batch.sources {
*source_samples.entry(source.leg_id.clone()).or_insert(0) +=
source.pcm_16k.len() as u64;
source.pcm_48k.len() as u64;
// TODO: Future — accumulate chunks and stream to Whisper endpoint.
// For now, the audio is received and counted but not processed.
@@ -118,7 +123,7 @@ pub fn spawn_transcription_tool(
.map(|(leg_id, samples)| {
serde_json::json!({
"source_leg_id": leg_id,
"duration_ms": (samples * 1000) / 16000,
"duration_ms": (samples * 1000) / 48000,
})
})
.collect();