Direct AllStarLink capture
Audio is recorded from AllStarLink hub activity through Asterisk, with no physical sound card input or speaker loopback required.
Amateur radio. AllStarLink. Local AI.
A self-contained radio analysis stack for AllStarLink hub nodes. The system records node audio directly from Asterisk, transcribes traffic locally, detects callsigns, verifies operators through QRZ, and groups conversations into searchable net logs.
Project overview
Audio is recorded from AllStarLink hub activity through Asterisk, with no physical sound card input or speaker loopback required.
The main Z840 server handles hub coordination, storage, and Whisper transcription using its RTX 3060 GPU.
Sable runs the deeper analysis jobs, including callsign extraction, wider net grouping, and large-language-model passes.
Detected callsigns, transcript segments, receive state, connections, and analysis passes are tracked for review and later search.
Analysis pipeline
The project keeps a verbose record of each analysis step so operators can see how a transcript moved through the system. Steps can be extended later as new modules are added.
Growing AllStarLink recordings are split into processable chunks.
Speech becomes text, confidence, timing, and processing metadata.
Candidate callsigns are detected and checked before being stored.
Known operators can be enriched with public QRZ profile data.
Recent transcript context helps collect a whole net instead of isolated fragments.
Large-model analysis can summarize, classify, and prepare future reports.
Monitored hub targets
Hub node connected toward PSRG activity for recording and net detection.
Hub node monitored with duplicate-aware grouping when traffic crosses linked systems.
Hub node tracked alongside related nets so repeated linked audio can be recognized.
Public status
The live dashboard is kept private on the local network while this public page documents the project for operators, search crawlers, and anyone curious about the build.