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

initial commit — SIP B2BUA + WebRTC bridge with Rust codec engine

Browse Source 
Full-featured SIP router with multi-provider trunking, browser softphone
via WebRTC, real-time Opus/G.722/PCM transcoding in Rust, RNNoise ML
noise suppression, Kokoro neural TTS announcements, and a Lit-based
web dashboard with live call monitoring and REST API.
This commit is contained in:
Jürgen Kunz
2026-04-09 23:03:55 +00:00
commit f3e1c96872
59 changed files with 18377 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
readme.ideas.md Normal file
View File

@@ -0,0 +1,12 @@
# Ideas / Future Improvements
## nnnoiseless (RNNoise) Denoiser Improvements
### VAD-gated passthrough
`process_frame()` returns an `f32` VAD probability (0.0-1.0). Currently ignored. Use it to skip denoising when VAD is low — prevents the model from suppressing non-speech audio (hold music, DTMF tones, IVR prompts).
### Pre-warm denoiser on session creation
The first `process_frame()` call on a fresh `DenoiseState` produces fade-in artifacts (documented behavior). Feed a silent 480-sample frame during `TranscodeState::new()` so the first real audio frame gets a warmed-up RNN state.
### Custom telephony-trained RNNoise model
nnnoiseless supports loading custom `.rnn` model files via `RnnModel::from_bytes()` / `RnnModel::from_static_bytes()`. The default model is trained on general audio. A model trained specifically on telephony noise profiles (codec artifacts, line noise, echo residual) would perform better. Models from https://github.com/GregorR/rnnoise-models can be converted with `train/convert_rnnoise.py`.