# freyzamarshall02/voice-changer architecture

> Architecture diagram of the GitHub repository freyzamarshall02/voice-changer, 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/freyzamarshall02/voice-changer
- Repository: https://github.com/freyzamarshall02/voice-changer

## Overview

This Colab-focused realtime voice changer accepts an RVC model URL, loads the model on the server, and converts incoming audio for a browser client. The main runtime path spans browser audio capture and worklet processing, server request handling, model-slot setup, and RVC inference; the README specifically highlights URL downloads and RVC-only support. The source index and excerpts establish several internal calls, but do not expose the complete request/audio transport wiring, so those links are omitted rather than inferred.

Main entry points: [`server/voice_changer/RVC/pipeline/PipelineGenerator.py`](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/PipelineGenerator.py) (Pipeline creation), [`server/voice_changer/VoiceChangerManager.py`](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/VoiceChangerManager.py) (Voice changer manager), [`server/voice_changer/RVC/pipeline/Pipeline.py`](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/Pipeline.py) (RVC conversion), [`client/lib/src/VoiceChangerClient.ts`](https://github.com/freyzamarshall02/voice-changer/blob/main/client/lib/src/VoiceChangerClient.ts) (Voice changer client)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_browser["Browser audio"]
  node_client["Voice changer client"]
  node_worklet["Audio worklet node"]
end

subgraph group_server["Server runtime"]
  node_server_entry["Server startup<br/>[Okada.py]"]
  node_rest["REST API"]
  node_socket["Socket.IO service"]
  node_manager["Voice changer manager"]
  node_url_download["URL model download"]
end

subgraph group_models["RVC model pipeline"]
  node_slots[("Model slots")]
  node_slot_generation["RVC slot generation"]
  node_pipeline_generator["Pipeline creation"]
  node_pipeline["RVC conversion<br/>[Pipeline.py]"]
  node_inferencer["Inference selection"]
  node_embedder["Feature extraction<br/>[EmbedderManager.py]"]
  node_pitch["Pitch extraction"]
end

node_user(("User"))

node_user -.->|"uses"| node_client
node_client -->|"creates"| node_worklet
node_client -.->|"sends audio"| node_server_entry
node_server_entry -->|"starts"| node_rest
node_server_entry -->|"starts"| node_socket
node_rest -->|"delegates to"| node_manager
node_manager -->|"requests download"| node_url_download
node_url_download -->|"updates slots"| node_slots
node_url_download -->|"generates metadata"| node_slot_generation
node_manager -->|"manages"| node_slots
node_manager -.->|"creates pipeline"| node_pipeline_generator
node_pipeline_generator -->|"selects model"| node_inferencer
node_pipeline_generator -->|"selects extractor"| node_embedder
node_pipeline_generator -->|"selects extractor"| node_pitch
node_pipeline_generator -->|"constructs"| node_pipeline
node_pipeline -->|"runs inference"| node_inferencer
node_pipeline -->|"extracts features"| node_embedder
node_pipeline -.->|"estimates pitch"| node_pitch

click node_client "https://github.com/freyzamarshall02/voice-changer/blob/main/client/lib/src/VoiceChangerClient.ts"
click node_worklet "https://github.com/freyzamarshall02/voice-changer/blob/main/client/lib/src/client/VoiceChangerWorkletNode.ts"
click node_server_entry "https://github.com/freyzamarshall02/voice-changer/blob/main/server/Okada.py"
click node_rest "https://github.com/freyzamarshall02/voice-changer/tree/main/server/restapi"
click node_socket "https://github.com/freyzamarshall02/voice-changer/tree/main/server/sio"
click node_manager "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/VoiceChangerManager.py"
click node_url_download "https://github.com/freyzamarshall02/voice-changer/blob/main/server/downloader/UrlModelDownloader.py"
click node_slots "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/ModelSlotManager.py"
click node_slot_generation "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/RVCModelSlotGenerator.py"
click node_pipeline_generator "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/PipelineGenerator.py"
click node_pipeline "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/Pipeline.py"
click node_inferencer "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/inferencer/InferencerManager.py"
click node_embedder "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/embedder/EmbedderManager.py"
click node_pitch "https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pitchExtractor/PitchExtractorManager.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_client,node_worklet,node_user toneBlue
class node_server_entry,node_rest,node_socket,node_manager,node_url_download toneAmber
class node_slots,node_slot_generation,node_pipeline_generator,node_pipeline,node_inferencer,node_embedder,node_pitch toneMint
```

## Components

### Browser audio

- [Voice changer client](https://github.com/freyzamarshall02/voice-changer/blob/main/client/lib/src/VoiceChangerClient.ts): `client/lib/src/VoiceChangerClient.ts`
- [Audio worklet node](https://github.com/freyzamarshall02/voice-changer/blob/main/client/lib/src/client/VoiceChangerWorkletNode.ts): `client/lib/src/client/VoiceChangerWorkletNode.ts`

### Server runtime

- [Server startup](https://github.com/freyzamarshall02/voice-changer/blob/main/server/Okada.py): `server/Okada.py`
- [REST API](https://github.com/freyzamarshall02/voice-changer/tree/main/server/restapi): `server/restapi`
- [Socket.IO service](https://github.com/freyzamarshall02/voice-changer/tree/main/server/sio): `server/sio`
- [Voice changer manager](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/VoiceChangerManager.py): `server/voice_changer/VoiceChangerManager.py`
- [URL model download](https://github.com/freyzamarshall02/voice-changer/blob/main/server/downloader/UrlModelDownloader.py): `server/downloader/UrlModelDownloader.py`

### RVC model pipeline

- [Model slots](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/ModelSlotManager.py): `server/voice_changer/ModelSlotManager.py`
- [RVC slot generation](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/RVCModelSlotGenerator.py): `server/voice_changer/RVC/RVCModelSlotGenerator.py`
- [Pipeline creation](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/PipelineGenerator.py): `server/voice_changer/RVC/pipeline/PipelineGenerator.py`
- [RVC conversion](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pipeline/Pipeline.py): `server/voice_changer/RVC/pipeline/Pipeline.py`
- [Inference selection](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/inferencer/InferencerManager.py): `server/voice_changer/RVC/inferencer/InferencerManager.py`
- [Feature extraction](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/embedder/EmbedderManager.py): `server/voice_changer/RVC/embedder/EmbedderManager.py`
- [Pitch extraction](https://github.com/freyzamarshall02/voice-changer/blob/main/server/voice_changer/RVC/pitchExtractor/PitchExtractorManager.py): `server/voice_changer/RVC/pitchExtractor/PitchExtractorManager.py`

### Other components

- **User**

## Connections

- User → Voice changer client: uses (evidence: `README.md`)
- Voice changer client → Audio worklet node: creates (evidence: `client/lib/src/VoiceChangerClient.ts`)
- Voice changer client → Server startup: sends audio
- Server startup → REST API: starts (evidence: `server/Okada.py`)
- Server startup → Socket.IO service: starts (evidence: `server/Okada.py`)
- REST API → Voice changer manager: delegates to (evidence: `server/restapi/MMVC_Rest_Fileuploader.py`)
- Voice changer manager → URL model download: requests download (evidence: `server/voice_changer/VoiceChangerManager.py`)
- URL model download → Model slots: updates slots (evidence: `server/downloader/UrlModelDownloader.py`)
- URL model download → RVC slot generation: generates metadata (evidence: `server/downloader/UrlModelDownloader.py`)
- Voice changer manager → Model slots: manages (evidence: `server/voice_changer/VoiceChangerManager.py`)
- Voice changer manager → Pipeline creation: creates pipeline
- Pipeline creation → Inference selection: selects model (evidence: `server/voice_changer/RVC/pipeline/PipelineGenerator.py`)
- Pipeline creation → Feature extraction: selects extractor (evidence: `server/voice_changer/RVC/pipeline/PipelineGenerator.py`)
- Pipeline creation → Pitch extraction: selects extractor (evidence: `server/voice_changer/RVC/pipeline/PipelineGenerator.py`)
- Pipeline creation → RVC conversion: constructs (evidence: `server/voice_changer/RVC/pipeline/PipelineGenerator.py`)
- RVC conversion → Inference selection: runs inference (evidence: `server/voice_changer/RVC/pipeline/Pipeline.py`)
- RVC conversion → Feature extraction: extracts features (evidence: `server/voice_changer/RVC/pipeline/Pipeline.py`)
- RVC conversion → Pitch extraction: estimates pitch
