# ombharatiya/transcript-ai architecture

> Architecture diagram of the GitHub repository ombharatiya/transcript-ai, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ombharatiya/transcript-ai
- Repository: https://github.com/ombharatiya/transcript-ai

## Overview

TranscriptAI provides two transcription interfaces: a browser app with demo or OpenAI API mode, and a Python CLI using local Whisper. The CLI workflow accepts files and options, transcribes singly or in batches, then saves text and optional detailed JSON; the web workflow selects a file and settings, calls the chosen mode, presents results, and offers downloads. The README documents multilingual translation, model selection, and batch support. Evidence is limited to the README and sampled source excerpts, so unsampled subsystem links are omitted.

Main entry points: [`cli/src/audio_transcriber.py`](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py) (Transcription engine), [`web/src/app.js`](https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js) (Web interface)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_web["Browser interface"]
  node_web_app["Web interface<br/>[app.js]"]
end

subgraph group_cli["CLI transcription"]
  node_cli_entry["CLI arguments"]
  node_batch["Batch processing"]
  node_audio_info["Audio inspection"]
  node_transcriber["Transcription engine"]
end

subgraph group_output["Results and export"]
  node_text_output["Text and JSON files"]
  node_browser_result["Browser result view<br/>[app.js]"]
  node_download["Text download<br/>[app.js]"]
end

node_browser_user(("Browser user"))
node_openai{{"OpenAI transcription API"}}
node_cli_user(("CLI user"))
node_whisper{{"Whisper model"}}
node_ffmpeg{{"FFmpeg"}}

node_browser_user -->|"selects audio"| node_web_app
node_web_app -->|"posts audio"| node_openai
node_web_app -->|"shows result"| node_browser_result
node_browser_result -->|"exports text"| node_download
node_cli_user -->|"provides files"| node_cli_entry
node_cli_entry -->|"dispatches batch"| node_batch
node_cli_entry -->|"requests details"| node_audio_info
node_cli_entry -->|"transcribes files"| node_transcriber
node_batch -->|"processes files"| node_transcriber
node_transcriber -->|"loads and runs"| node_whisper
node_transcriber -->|"checks availability"| node_ffmpeg
node_transcriber -->|"writes results"| node_text_output

click node_web_app "https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js"
click node_cli_entry "https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py"
click node_batch "https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py"
click node_audio_info "https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py"
click node_transcriber "https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py"
click node_text_output "https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py"
click node_browser_result "https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js"
click node_download "https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js"

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_web_app,node_browser_user,node_cli_user toneBlue
class node_cli_entry,node_batch,node_audio_info,node_transcriber toneAmber
class node_text_output,node_browser_result,node_download,node_openai toneMint
class node_whisper,node_ffmpeg toneIndigo
```

## Components

### Browser interface

- [Web interface](https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js): `web/src/app.js`

### CLI transcription

- [CLI arguments](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py): `cli/src/audio_transcriber.py`
- [Batch processing](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py): `cli/src/audio_transcriber.py`
- [Audio inspection](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py): `cli/src/audio_transcriber.py`
- [Transcription engine](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py): `cli/src/audio_transcriber.py`

### Results and export

- [Text and JSON files](https://github.com/ombharatiya/transcript-ai/blob/main/cli/src/audio_transcriber.py): `cli/src/audio_transcriber.py`
- [Browser result view](https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js): `web/src/app.js`
- [Text download](https://github.com/ombharatiya/transcript-ai/blob/main/web/src/app.js): `web/src/app.js`

### Other components

- **Browser user**
- **OpenAI transcription API**
- **CLI user**
- **Whisper model**
- **FFmpeg**

## Connections

- Browser user → Web interface: selects audio (evidence: `README.md`)
- Web interface → OpenAI transcription API: posts audio (evidence: `web/src/app.js`)
- Web interface → Browser result view: shows result (evidence: `web/src/app.js`)
- Browser result view → Text download: exports text (evidence: `web/src/app.js`)
- CLI user → CLI arguments: provides files (evidence: `README.md`)
- CLI arguments → Batch processing: dispatches batch (evidence: `cli/src/audio_transcriber.py`)
- CLI arguments → Audio inspection: requests details (evidence: `cli/src/audio_transcriber.py`)
- CLI arguments → Transcription engine: transcribes files (evidence: `cli/src/audio_transcriber.py`)
- Batch processing → Transcription engine: processes files (evidence: `cli/src/audio_transcriber.py`)
- Transcription engine → Whisper model: loads and runs (evidence: `cli/src/audio_transcriber.py`)
- Transcription engine → FFmpeg: checks availability (evidence: `cli/src/audio_transcriber.py`)
- Transcription engine → Text and JSON files: writes results (evidence: `cli/src/audio_transcriber.py`)
