How pranabesh14/calltx works
calltx is an offline command-line call-recording transcriber. The user supplies audio files or folders and options; the program decodes and resamples audio, transcribes it, optionally detects speech gaps and separates stereo speakers, then writes timestamped transcripts. The excerpts show audio decoding and gap-analysis implementations and parts of the CLI orchestration, but not all output-writing or VAD control flow; README-backed links identify those capabilities without implying unshown calls.
Main entry points: main.cpp CLI and batch workflow · audio.cpp Decode and resample · deadair.cpp Dead-air analysis
Components 13
Input and audio
- Audio recordings
- CLI and batch workflow
src/main.cpp - Decode and resample
src/audio.cpp - Channel handling
src/main.cpp
Speech recognition
- Whisper transcription
src/main.cpp - Speech-region detection
src/main.cpp - Timestamped segments
src/main.cpp
Transcript analysis
- Frame loudness
src/deadair.cpp - Dead-air analysis
src/deadair.cpp - Gap transcript entries
src/main.cpp
Transcript output
- TXT SRT JSON output
src/main.cpp - Transcript files
Other components
- CLI user
Connections 16
- CLI user → CLI and batch workflow: provides options
README.md - CLI user → Audio recordings: selects recordings
README.md - CLI and batch workflow → Audio recordings: collects inputs
src/main.cpp - CLI and batch workflow → Decode and resample: loads audio
README.md - Decode and resample → Channel handling: provides PCM channels
src/audio.cpp - CLI and batch workflow → Channel handling: routes channels
README.md - CLI and batch workflow → Whisper transcription: transcribes audio
src/main.cpp - CLI and batch workflow → Speech-region detection: optionally detects speech
README.md - Whisper transcription → Timestamped segments: returns timed segments
src/main.cpp - Decode and resample → Frame loudness: supplies PCM channels
src/deadair.cpp - Speech-region detection → Dead-air analysis: supplies speech regions
README.md - Frame loudness → Dead-air analysis: supplies loudness
src/deadair.cpp - Dead-air analysis → Gap transcript entries: returns classified gaps
src/main.cpp - Timestamped segments → TXT SRT JSON output: formats transcript data
README.md - Gap transcript entries → TXT SRT JSON output: adds gap entries
src/main.cpp - TXT SRT JSON output → Transcript files: writes files
README.md