loudgate
Provides a silence-cutting/export tool that generates OpenTimelineIO (.otio) timelines and CMX 3600 EDLs compatible with DaVinci Resolve workflows, allowing edited audio timelines to be imported into DaVinci Resolve.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
loudgate
Open-source, clean-room broadcast audio post-production engine in Python + FFmpeg, featuring a local loopback Studio GUI (loudgate ui), deterministic CLI, Python API, and stdio MCP server.
Everything runs locally on CPU with zero cloud uploads, zero model weight downloads, and zero subscription paywalls.

Documentation
English: Overview | Studio GUI Guide | CLI & Python Reference | MCP Setup
Francais: Presentation | Guide Interface Studio | Reference CLI & Python | Configuration MCP
Related MCP server: Whisper Valet
Why loudgate
Workflow | Proprietary paywalls | loudgate (MIT) |
Visual Audio Console & A/B Audition | Desktop GUI suites ($399+) | Local loopback |
Spectral denoise, de-click, HPF | Per-plugin licenses | Deterministic STFT WOLA + zero-phase Butterworth SOS |
Loudness audit & mastering | Monthly NLE add-ons ($22.99/mo) | Two-pass FFmpeg |
Silence removal + NLE cut export | Per-seat podcast editors ($24-$65/mo) | Energy/ZCR VAD + |
Automation & editor integration | Closed plugins | Scriptable CLI, Python API, and |
Requirements
Python 3.10+
ffmpegandffprobeonPATHPython packages:
numpy,scipy,soundfile
Installation
git clone https://github.com/eldertek/loudgate.git
cd loudgate
pip install -e ".[dev]"Quick Start: Studio GUI (loudgate ui)
Launch the local broadcast console (binds strictly to 127.0.0.1, default port 8742):
loudgate ui
# or standalone command:
loudgate-ui --workspace-dir ./episodes --no-openInside the browser Studio (EN / FR language toggle built in):
Click Load Built-in Broadcast Speech+Silence Sample WAV (or drop/upload any local file or select from
--workspace-dir).Inspect the interactive Canvas waveform and EBU R128 Probe meters (
LUFS,LRA,True Peak,4x OS Peak,SNR,DC offset).Clean rumble, clicks, hiss, and sibilance in STFT Spectral Denoiser, audition A vs B, or click Use as Active Source.
Normalize in Broadcast Mastering (
podcast -14,mobile -16,broadcast -23 LUFS, etc. loaded fromMASTER_PRESETS).Segment speech vs silence in Silence Cutter & Timeline with green/red waveform markers and download
.otio,.edl,.srt,.vtt, and trimmed.wav.
Quick Start (CLI)
1. Audit loudness, peaks, clipping, DC offset, and SNR
loudgate probe episode_raw.wav --jsonReports EBU R128 integrated loudness (LUFS), loudness range (LRA), FFmpeg true peak (dBTP), 4x polyphase oversampled inter-sample peak excess, DC offset per channel, clipped sample ratio, and estimated SNR (dB).
2. Clean noise, rumble, and clicks
loudgate clean episode_raw.wav episode_clean.wav --highpass-hz 80 --denoise-strength 1.0 --deessPipeline stages:
DC offset removal
Zero-phase 4th-order Butterworth high-pass filter (
scipy.signal.sosfiltfilt, zero group-delay distortion)MAD second-difference de-clicker for isolated digital impulses
Tight-frame periodic root-Hann STFT WOLA spectral Wiener denoising (
n_fft=2048,hop_length=512)Optional split-band sibilance attenuator (
--deess) and downward noise gate (--gate)
3. Master to broadcast or podcast targets
# Podcast / Web (-14 LUFS, <= -1.0 dBTP)
loudgate master episode_clean.wav episode_podcast.wav --preset podcast
# EBU R128 Broadcast (-23 LUFS, <= -1.0 dBTP)
loudgate master episode_clean.wav episode_broadcast.wav --preset broadcast
# Mobile / Stereo (-16 LUFS, <= -1.0 dBTP) + MP3 export
loudgate master episode_clean.wav episode_mobile.mp3 --preset mobile --bitrate 192kUses two-pass linear FFmpeg loudnorm followed by a post-render ebur128 verification pass and a 4x oversampled PCM true-peak safety limiter when needed.
4. Cut silences and export NLE timelines + subtitles
loudgate cut episode_podcast.wav ./cuts/ --thresh-db -40 --min-silence-ms 400 --pad-ms 80 --fps 25Outputs into ./cuts/:
episode_podcast.otio(OpenTimelineIO JSON timeline for DaVinci Resolve / Premiere workflows)episode_podcast.edl(CMX 3600 EDL)episode_podcast.srtandepisode_podcast.vtt(cue timestamps aligned to the trimmed timeline)episode_podcast_cut.wav(rendered via FFmpegatrim+ micro-fades +concat)
5. Run as an MCP stdio server
loudgate mcpExposed MCP tools:
probe_loudnessclean_spectralmaster_broadcastcut_silences_otio
Example MCP client configuration:
{
"mcpServers": {
"loudgate": {
"command": "loudgate",
"args": ["mcp"]
}
}
}Python API
from loudgate import CleanConfig, MasterConfig, clean_file, cut_silences, master_file, probe_file
report = probe_file("raw.wav")
clean_file("raw.wav", "clean.wav", CleanConfig(highpass_hz=80.0, denoise_strength=1.0))
master = master_file("clean.wav", "master.wav", MasterConfig(preset="podcast"))
cuts = cut_silences("master.wav", "exports/")v0.1 Scope and Known Limitations
The STFT Wiener denoiser targets stationary background noise (room floor, fan hiss, hum) rather than heavy room dereverberation or overlapping-speaker separation.
Silence cutting uses RMS energy + zero-crossing rate VAD; it does not perform ASR transcription or speaker diarization.
Mastering and container transcoding rely on a local
ffmpeg/ffprobebinary installed onPATH.
Running Tests
pytest -vThe test suite verifies DSP invariants and UI integration:
Parseval energy conservation across the tight-frame STFT/ISTFT (
relative error < 1e-12)Zero-phase high-pass attenuation and impulse click repair
Real FFmpeg
ebur128verification before and after two-passloudnormat-14,-16, and-23 LUFSwithtrue_peak_dbtp <= -1.0VAD/silence segmentation, valid OTIO/EDL/SRT/VTT generation, and FFmpeg
atrimrenderingMCP JSON-RPC 2.0
stdioprotocol round-tripsStudio UI loopback HTTP endpoints, CSP & path traversal rejections, byte-range streaming, and full DSP round-trips
Commercial Support & Custom Pipelines
Need custom audio post-production automation, broadcast QA integration, or dedicated maintenance? See Eclipse Technology Open Source Pro.
License
MIT License. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Remote MCP server for audio stem separation, denoise, reverb, and MIDI export.
Audio analysis and production jobs: BPM, key, fingerprint, tags, stems, cleanup, mastering.
Hosted MCP tools for FFmpeg-style video and audio processing through FFMPEG API.
QC, conform and AI video, image and sound generation for film. Priced before every run.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to programmatically edit, analyze, and export audio projects through MCP tools, including multi-track editing, effects, transcription, and semantic search.1-
- AlicenseAqualityDmaintenanceEnables automated audio restoration, transcription, and speaker diarization via MCP tools for queuing files, monitoring progress, and retrieving speaker-labeled transcripts.9MIT
- AlicenseCqualityAmaintenanceEnables podcast producers and agents to manage multitrack projects, run per-track transcription, perform transcript-driven edits, process audio via FFmpeg, and inspect a read-only DAW timeline over MCP.218AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables local, CPU-only audio post-production through tools for denoising, LUFS loudness normalization, silence removal, format conversion, pitch shifting, and speed changes. Supports podcast and video platform loudness compliance workflows.MIT