# phuc-nt/my-translator architecture

> Architecture diagram of the GitHub repository phuc-nt/my-translator, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/phuc-nt/my-translator
- Repository: https://github.com/phuc-nt/my-translator

## Overview

My Translator is a Tauri desktop app that captures system and/or microphone audio, translates speech through Soniox, OpenAI Realtime, Qwen, or offline MLX, and presents results in an overlay. The main path runs from user audio selection through capture and engine-specific translation to the transcript UI; optional narration and session history are separate branches. README documents broad provider and UI capabilities, while sampled source confirms only some wiring, so unverified subsystem links are omitted. The graph focuses on runtime behavior, not build or setup machinery.

Main entry points: [`src/js/app.js`](https://github.com/phuc-nt/my-translator/blob/main/src/js/app.js) (App controller), [`src-tauri/src/commands/audio.rs`](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/audio.rs) (Capture commands), [`src-tauri/src/commands/openai_realtime.rs`](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/openai_realtime.rs) (OpenAI realtime), [`src-tauri/src/lib.rs`](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/lib.rs) (Tauri runtime)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_capture["Audio capture"]
  node_audio_cmd["Capture commands<br/>[audio.rs]"]
  node_mic["Microphone capture<br/>[microphone.rs]"]
  node_system_audio["System audio capture<br/>[system_audio.rs]"]
  node_wasapi["Windows loopback<br/>[wasapi.rs]"]
  node_resampler["Audio resampler<br/>[resampler.rs]"]
end

subgraph group_translation["Translation engines"]
  node_soniox["Soniox translation<br/>[soniox.js]"]
  node_openai_client["OpenAI client"]
  node_openai_backend["OpenAI realtime<br/>[openai_realtime.rs]"]
  node_qwen_client["Qwen client"]
  node_qwen_backend["Qwen realtime<br/>[qwen_realtime.rs]"]
  node_local_pipeline["Local MLX pipeline<br/>[local_pipeline.rs]"]
end

subgraph group_experience["Overlay and history"]
  node_app["App controller<br/>[app.js]"]
  node_settings["Settings<br/>[settings.js]"]
  node_backend["Tauri runtime<br/>[lib.rs]"]
  node_ui["Transcript overlay<br/>[ui.js]"]
  node_session_js["Session manager<br/>[session-store.js]"]
  node_session_rust[("Session persistence<br/>[session_store.rs]")]
  node_transcripts[("Local transcripts")]
end

subgraph group_speech["Speech output"]
  node_reader["Read-aloud reader<br/>[reader.js]"]
  node_tts_providers["TTS providers<br/>[elevenlabs-tts.js]"]
  node_audio_player["Audio playback<br/>[audio-player.js]"]
end

node_user(("User"))
node_soniox_service{{"Soniox service"}}
node_openai_service{{"OpenAI service"}}
node_qwen_service{{"Qwen service"}}
node_local_models["Local models"]

node_user -->|"configures and starts"| node_app
node_app -->|"reads settings"| node_settings
node_app -.->|"starts capture"| node_audio_cmd
node_backend -->|"registers commands"| node_audio_cmd
node_audio_cmd -.->|"captures microphone"| node_mic
node_audio_cmd -.->|"captures system audio"| node_system_audio
node_system_audio -.->|"uses loopback"| node_wasapi
node_app -->|"routes translation"| node_soniox
node_soniox -->|"streams audio and text"| node_soniox_service
node_app -.->|"routes translation"| node_openai_client
node_openai_client -->|"invokes commands"| node_openai_backend
node_openai_backend -->|"upsamples audio"| node_resampler
node_openai_backend -.->|"streams audio and translation"| node_openai_service
node_app -.->|"routes translation"| node_qwen_client
node_qwen_client -->|"invokes commands"| node_qwen_backend
node_qwen_backend -.->|"streams audio and text"| node_qwen_service
node_app -.->|"starts local mode"| node_local_pipeline
node_local_pipeline -.->|"runs offline inference"| node_local_models
node_app -.->|"updates transcript"| node_ui
node_app -->|"starts narration"| node_reader
node_reader -->|"requests speech"| node_tts_providers
node_tts_providers -.->|"plays generated audio"| node_audio_player
node_app -.->|"records segments"| node_session_js
node_session_js -->|"saves and reads sessions"| node_session_rust
node_session_rust -->|"persists files"| node_transcripts
node_backend -->|"registers commands"| node_openai_backend
node_backend -->|"registers commands"| node_qwen_backend

click node_app "https://github.com/phuc-nt/my-translator/blob/main/src/js/app.js"
click node_settings "https://github.com/phuc-nt/my-translator/blob/main/src/js/settings.js"
click node_backend "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/lib.rs"
click node_audio_cmd "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/audio.rs"
click node_mic "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/microphone.rs"
click node_system_audio "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/system_audio.rs"
click node_wasapi "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/wasapi.rs"
click node_resampler "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/resampler.rs"
click node_soniox "https://github.com/phuc-nt/my-translator/blob/main/src/js/soniox.js"
click node_openai_client "https://github.com/phuc-nt/my-translator/blob/main/src/js/openai-realtime-client.js"
click node_openai_backend "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/openai_realtime.rs"
click node_qwen_client "https://github.com/phuc-nt/my-translator/blob/main/src/js/qwen-realtime-client.js"
click node_qwen_backend "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/qwen_realtime.rs"
click node_local_pipeline "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/local_pipeline.rs"
click node_ui "https://github.com/phuc-nt/my-translator/blob/main/src/js/ui.js"
click node_reader "https://github.com/phuc-nt/my-translator/blob/main/src/js/reader.js"
click node_tts_providers "https://github.com/phuc-nt/my-translator/blob/main/src/js/elevenlabs-tts.js"
click node_audio_player "https://github.com/phuc-nt/my-translator/blob/main/src/js/audio-player.js"
click node_session_js "https://github.com/phuc-nt/my-translator/blob/main/src/js/session-store.js"
click node_session_rust "https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/session_store.rs"

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_cmd,node_mic,node_system_audio,node_wasapi,node_resampler,node_user toneBlue
class node_soniox,node_openai_client,node_openai_backend,node_qwen_client,node_qwen_backend,node_local_pipeline toneAmber
class node_app,node_settings,node_backend,node_ui,node_session_js,node_session_rust,node_transcripts toneMint
class node_reader,node_tts_providers,node_audio_player toneRose
class node_soniox_service,node_openai_service,node_qwen_service,node_local_models toneIndigo
```

## Components

### Audio capture

- [Capture commands](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/audio.rs): `src-tauri/src/commands/audio.rs`
- [Microphone capture](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/microphone.rs): `src-tauri/src/audio/microphone.rs`
- [System audio capture](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/system_audio.rs): `src-tauri/src/audio/system_audio.rs`
- [Windows loopback](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/wasapi.rs): `src-tauri/src/audio/wasapi.rs`
- [Audio resampler](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/audio/resampler.rs): `src-tauri/src/audio/resampler.rs`

### Translation engines

- [Soniox translation](https://github.com/phuc-nt/my-translator/blob/main/src/js/soniox.js): `src/js/soniox.js`
- [OpenAI client](https://github.com/phuc-nt/my-translator/blob/main/src/js/openai-realtime-client.js): `src/js/openai-realtime-client.js`
- [OpenAI realtime](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/openai_realtime.rs): `src-tauri/src/commands/openai_realtime.rs`
- [Qwen client](https://github.com/phuc-nt/my-translator/blob/main/src/js/qwen-realtime-client.js): `src/js/qwen-realtime-client.js`
- [Qwen realtime](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/qwen_realtime.rs): `src-tauri/src/commands/qwen_realtime.rs`
- [Local MLX pipeline](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/local_pipeline.rs): `src-tauri/src/commands/local_pipeline.rs`

### Overlay and history

- [App controller](https://github.com/phuc-nt/my-translator/blob/main/src/js/app.js): `src/js/app.js`
- [Settings](https://github.com/phuc-nt/my-translator/blob/main/src/js/settings.js): `src/js/settings.js`
- [Tauri runtime](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/lib.rs): `src-tauri/src/lib.rs`
- [Transcript overlay](https://github.com/phuc-nt/my-translator/blob/main/src/js/ui.js): `src/js/ui.js`
- [Session manager](https://github.com/phuc-nt/my-translator/blob/main/src/js/session-store.js): `src/js/session-store.js`
- [Session persistence](https://github.com/phuc-nt/my-translator/blob/main/src-tauri/src/commands/session_store.rs): `src-tauri/src/commands/session_store.rs`
- **Local transcripts**

### Speech output

- [Read-aloud reader](https://github.com/phuc-nt/my-translator/blob/main/src/js/reader.js): `src/js/reader.js`
- [TTS providers](https://github.com/phuc-nt/my-translator/blob/main/src/js/elevenlabs-tts.js): `src/js/elevenlabs-tts.js`
- [Audio playback](https://github.com/phuc-nt/my-translator/blob/main/src/js/audio-player.js): `src/js/audio-player.js`

### Other components

- **User**
- **Soniox service**
- **OpenAI service**
- **Qwen service**
- **Local models**

## Connections

- User → App controller: configures and starts
- App controller → Settings: reads settings (evidence: `src/js/app.js`)
- App controller → Capture commands: starts capture
- Tauri runtime → Capture commands: registers commands (evidence: `src-tauri/src/lib.rs`)
- Capture commands → Microphone capture: captures microphone
- Capture commands → System audio capture: captures system audio
- System audio capture → Windows loopback: uses loopback
- App controller → Soniox translation: routes translation (evidence: `src/js/app.js`)
- Soniox translation → Soniox service: streams audio and text
- App controller → OpenAI client: routes translation (evidence: `src/js/app.js`)
- OpenAI client → OpenAI realtime: invokes commands (evidence: `src/js/openai-realtime-client.js`)
- OpenAI realtime → Audio resampler: upsamples audio (evidence: `src-tauri/src/commands/openai_realtime.rs`)
- OpenAI realtime → OpenAI service: streams audio and translation
- App controller → Qwen client: routes translation (evidence: `src/js/app.js`)
- Qwen client → Qwen realtime: invokes commands (evidence: `src/js/qwen-realtime-client.js`)
- Qwen realtime → Qwen service: streams audio and text
- App controller → Local MLX pipeline: starts local mode
- Local MLX pipeline → Local models: runs offline inference
- App controller → Transcript overlay: updates transcript (evidence: `src/js/app.js`)
- App controller → Read-aloud reader: starts narration (evidence: `src/js/app.js`)
- Read-aloud reader → TTS providers: requests speech (evidence: `src/js/app.js`)
- TTS providers → Audio playback: plays generated audio
- App controller → Session manager: records segments (evidence: `src/js/app.js`)
- Session manager → Session persistence: saves and reads sessions (evidence: `src/js/session-store.js`)
- Session persistence → Local transcripts: persists files (evidence: `src-tauri/src/commands/session_store.rs`)
- Tauri runtime → OpenAI realtime: registers commands (evidence: `src-tauri/src/lib.rs`)
- Tauri runtime → Qwen realtime: registers commands (evidence: `src-tauri/src/lib.rs`)
