# jasoncheng7115/jt-live-whisper architecture

> Architecture diagram of the GitHub repository jasoncheng7115/jt-live-whisper, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/jasoncheng7115/jt-live-whisper
- Repository: https://github.com/jasoncheng7115/jt-live-whisper

## Overview

jt-live-whisper is a local-first speech toolkit for live captions and translation, offline audio transcription, diarization, meeting analysis, and speech synthesis. The main user workflow captures system audio or accepts a recording, transcribes and optionally translates it, then presents captions or produces transcript and meeting outputs. A separate REST API exposes queued transcription jobs, persistent results, and webhook events; WebUI provides browser-based controls. The graph includes documented capabilities even where implementation was not sampled. Arrows are limited to README statements and source-index references; unsampled internals are not inferred.

Main entry points: [`translate_meeting.py`](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py) (Transcription Pipeline), [`jtlw_api/app.py`](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/app.py) (Job API), [`jtlw_api/engine.py`](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/engine.py) (Job Processing Engine), [`webui.py`](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/webui.py) (Browser WebUI)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_capture["Capture and Transcription"]
  node_audio["System Audio Capture"]
  node_pipeline["Transcription Pipeline"]
  node_remote["GPU Speech Server"]
  node_batch["Offline Audio Processing"]
end

subgraph group_meeting["Meeting Outputs"]
  node_diarization["Speaker Diarization"]
  node_transcript["Transcript Parsing"]
  node_insight["Meeting Analysis<br/>[meeting_insight.py]"]
  node_charts["Speaker Charts<br/>[meeting_charts.py]"]
end

subgraph group_api["REST API"]
  node_api_app["Job API<br/>[app.py]"]
  node_api_config["API Configuration<br/>[config.py]"]
  node_api_engine["Job Processing Engine<br/>[engine.py]"]
  node_store[("Job and Result Store<br/>[store.py]")]
  node_events["Events and Webhooks<br/>[events.py]"]
end

subgraph group_speech["Speech Synthesis"]
  node_tts["Speech Synthesis<br/>[engine.py]"]
  node_reading["Taiwanese Reading Rules<br/>[tw_reading.py]"]
  node_interpretation["Voice Interpretation<br/>[interp.py]"]
  node_virtual_mic["Interpreter Microphone<br/>[vmic.py]"]
end

subgraph group_interface["User Interfaces"]
  node_captions["Subtitle Overlay"]
  node_webui["Browser WebUI<br/>[webui.py]"]
end

node_user(("User"))
node_api_client(("API Client"))

node_user -->|"provides audio"| node_audio
node_audio -.->|"feeds audio"| node_pipeline
node_user -->|"submits recording"| node_batch
node_pipeline -->|"displays captions"| node_captions
node_webui -->|"starts process"| node_pipeline
node_pipeline -->|"uses remote ASR"| node_remote
node_batch -->|"supports diarization"| node_diarization
node_batch -.->|"parses transcript"| node_transcript
node_batch -->|"produces analysis"| node_insight
node_insight -.->|"includes statistics"| node_charts
node_api_client -->|"submits jobs"| node_api_app
node_api_app -->|"loads settings"| node_api_config
node_api_app -->|"dispatches jobs"| node_api_engine
node_api_app -->|"persists jobs"| node_store
node_api_engine -->|"saves progress"| node_store
node_api_engine -->|"emits progress"| node_events
node_api_engine -->|"uses speech functions"| node_pipeline
node_webui -->|"uses synthesis"| node_tts
node_tts -->|"applies reading rules"| node_reading
node_user -->|"uses interpretation"| node_interpretation
node_interpretation -.->|"sends speech"| node_virtual_mic

click node_audio "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/sck_audio_capture.swift"
click node_pipeline "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py"
click node_remote "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/remote_whisper_server.py"
click node_captions "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/subtitle_overlay.py"
click node_webui "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/webui.py"
click node_batch "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py"
click node_diarization "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py"
click node_transcript "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/transcript_parse.py"
click node_insight "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/meeting_insight.py"
click node_charts "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/meeting_charts.py"
click node_api_app "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/app.py"
click node_api_config "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/config.py"
click node_api_engine "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/engine.py"
click node_store "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/store.py"
click node_events "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/events.py"
click node_tts "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/engine.py"
click node_reading "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/tw_reading.py"
click node_interpretation "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/interp.py"
click node_virtual_mic "https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/vmic.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_audio,node_pipeline,node_remote,node_batch,node_user,node_api_client toneBlue
class node_diarization,node_transcript,node_insight,node_charts toneAmber
class node_api_app,node_api_config,node_api_engine,node_store,node_events toneMint
class node_tts,node_reading,node_interpretation,node_virtual_mic toneRose
class node_captions,node_webui toneIndigo
```

## Components

### Capture and Transcription

- [System Audio Capture](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/sck_audio_capture.swift): `sck_audio_capture.swift`
- [Transcription Pipeline](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py): `translate_meeting.py`
- [GPU Speech Server](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/remote_whisper_server.py): `remote_whisper_server.py`
- [Offline Audio Processing](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py): `translate_meeting.py`

### Meeting Outputs

- [Speaker Diarization](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/translate_meeting.py): `translate_meeting.py`
- [Transcript Parsing](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/transcript_parse.py): `jtdt_meeting/transcript_parse.py`
- [Meeting Analysis](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/meeting_insight.py): `jtdt_meeting/meeting_insight.py`
- [Speaker Charts](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtdt_meeting/meeting_charts.py): `jtdt_meeting/meeting_charts.py`

### REST API

- [Job API](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/app.py): `jtlw_api/app.py`
- [API Configuration](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/config.py): `jtlw_api/config.py`
- [Job Processing Engine](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/engine.py): `jtlw_api/engine.py`
- [Job and Result Store](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/store.py): `jtlw_api/store.py`
- [Events and Webhooks](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_api/events.py): `jtlw_api/events.py`

### Speech Synthesis

- [Speech Synthesis](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/engine.py): `jtlw_tts/engine.py`
- [Taiwanese Reading Rules](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/tw_reading.py): `jtlw_tts/tw_reading.py`
- [Voice Interpretation](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/interp.py): `jtlw_tts/interp.py`
- [Interpreter Microphone](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/jtlw_tts/vmic.py): `jtlw_tts/vmic.py`

### User Interfaces

- [Subtitle Overlay](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/subtitle_overlay.py): `subtitle_overlay.py`
- [Browser WebUI](https://github.com/jasoncheng7115/jt-live-whisper/blob/main/webui.py): `webui.py`

### Other components

- **User**
- **API Client**

## Connections

- User → System Audio Capture: provides audio (evidence: `README.md`)
- System Audio Capture → Transcription Pipeline: feeds audio
- User → Offline Audio Processing: submits recording (evidence: `README.md`)
- Transcription Pipeline → Subtitle Overlay: displays captions (evidence: `README.md`)
- Browser WebUI → Transcription Pipeline: starts process (evidence: `webui.py`)
- Transcription Pipeline → GPU Speech Server: uses remote ASR (evidence: `README.md`)
- Offline Audio Processing → Speaker Diarization: supports diarization (evidence: `README.md`)
- Offline Audio Processing → Transcript Parsing: parses transcript
- Offline Audio Processing → Meeting Analysis: produces analysis (evidence: `README.md`)
- Meeting Analysis → Speaker Charts: includes statistics
- API Client → Job API: submits jobs (evidence: `README.md`)
- Job API → API Configuration: loads settings (evidence: `jtlw_api/app.py`)
- Job API → Job Processing Engine: dispatches jobs (evidence: `jtlw_api/app.py`)
- Job API → Job and Result Store: persists jobs (evidence: `jtlw_api/app.py`)
- Job Processing Engine → Job and Result Store: saves progress (evidence: `jtlw_api/engine.py`)
- Job Processing Engine → Events and Webhooks: emits progress (evidence: `jtlw_api/engine.py`)
- Job Processing Engine → Transcription Pipeline: uses speech functions (evidence: `jtlw_api/engine.py`)
- Browser WebUI → Speech Synthesis: uses synthesis (evidence: `webui.py`)
- Speech Synthesis → Taiwanese Reading Rules: applies reading rules (evidence: `jtlw_tts/engine.py`)
- User → Voice Interpretation: uses interpretation (evidence: `README.md`)
- Voice Interpretation → Interpreter Microphone: sends speech
