# freyzamarshall02/aicovergen-mod architecture

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

## Overview

AICoverGen turns a YouTube link or local audio file into an AI voice cover. Users can run the generation workflow through the WebUI or CLI; the main pipeline separates vocals and instrumentals, converts the vocals with an RVC voice model, then mixes the result and produces audio output. The WebUI also supports managing voice models. Internal RVC inference uses pitch extraction and a synthesizer with selectable vocoder implementations. Several relationships are supported only by the README or SOURCE INDEX; unsampled implementation details are not inferred.

Main entry points: [`src/rvc/lib/algorithm/synthesizers.py`](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/synthesizers.py) (RVC synthesizer), [`src/webui.py`](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/webui.py) (Web UI), [`src/main.py`](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py) (Cover pipeline), [`src/rvc_module.py`](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc_module.py) (RVC wrapper)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interfaces["User interfaces"]
  node_webui["Web UI<br/>[webui.py]"]
  node_cli["CLI entry<br/>[main.py]"]
end

subgraph group_cover["Cover generation"]
  node_orchestrator["Cover pipeline<br/>[main.py]"]
  node_separation["Vocal separation<br/>[mdx.py]"]
  node_mixing["Audio mixing<br/>[main.py]"]
end

subgraph group_voice["RVC conversion"]
  node_rvc["RVC wrapper<br/>[rvc_module.py]"]
  node_pipeline["Conversion pipeline<br/>[pipeline.py]"]
  node_pitch["Pitch extraction<br/>[f0.py]"]
  node_predictors["Pitch models<br/>[RMVPE.py]"]
  node_synth["RVC synthesizer<br/>[synthesizers.py]"]
  node_encoder["Text encoder<br/>[encoders.py]"]
  node_attention["Attention layers<br/>[attentions.py]"]
  node_commons["Algorithm utilities<br/>[commons.py]"]
  node_residuals["Residual blocks<br/>[residuals.py]"]
  node_modules["WaveNet modules<br/>[modules.py]"]
  node_hifigan["HiFi-GAN vocoders<br/>[hifigan.py]"]
  node_mrf["MRF vocoder<br/>[hifigan_mrf.py]"]
  node_nsf["NSF vocoder<br/>[hifigan_nsf.py]"]
  node_refinegan["RefineGAN vocoder<br/>[refinegan.py]"]
end

subgraph group_models["Model management"]
  node_voicefiles[("Voice models")]
  node_modelmanage["Model download<br/>[download_models.py]"]
  node_mdxfiles[("Separation models")]
end

node_user(("User"))
node_input["Song source"]
node_output["Cover audio"]
node_download_service["Model hosting"]

node_user -->|"uses"| node_webui
node_user -->|"runs"| node_cli
node_user -->|"provides"| node_input
node_webui -->|"starts generation"| node_orchestrator
node_cli -->|"runs"| node_orchestrator
node_orchestrator -->|"separates stems"| node_separation
node_orchestrator -->|"converts vocals"| node_rvc
node_orchestrator -.->|"mixes audio"| node_mixing
node_mixing -->|"writes"| node_output
node_rvc -->|"calls"| node_pipeline
node_rvc -->|"loads"| node_synth
node_rvc -.->|"loads model"| node_voicefiles
node_pipeline -->|"requests pitch"| node_pitch
node_pitch -->|"uses"| node_predictors
node_synth -->|"uses"| node_encoder
node_synth -->|"selects vocoder"| node_hifigan
node_synth -->|"selects vocoder"| node_mrf
node_synth -->|"selects vocoder"| node_nsf
node_synth -->|"selects vocoder"| node_refinegan
node_encoder -->|"uses"| node_attention
node_attention -->|"uses"| node_commons
node_hifigan -->|"uses"| node_residuals
node_residuals -->|"uses"| node_modules
node_residuals -->|"uses"| node_commons
node_webui -->|"manages models"| node_voicefiles
node_webui -->|"downloads via"| node_modelmanage
node_modelmanage -.->|"downloads from"| node_download_service
node_webui -.->|"fetches base models"| node_mdxfiles

click node_webui "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/webui.py"
click node_cli "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py"
click node_orchestrator "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py"
click node_separation "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/mdx.py"
click node_mixing "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py"
click node_rvc "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc_module.py"
click node_pipeline "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/infer/pipeline.py"
click node_pitch "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/predictors/f0.py"
click node_predictors "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/predictors/RMVPE.py"
click node_synth "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/synthesizers.py"
click node_encoder "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/encoders.py"
click node_attention "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/attentions.py"
click node_commons "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/commons.py"
click node_residuals "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/residuals.py"
click node_modules "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/modules.py"
click node_hifigan "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan.py"
click node_mrf "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan_mrf.py"
click node_nsf "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan_nsf.py"
click node_refinegan "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/refinegan.py"
click node_voicefiles "https://github.com/freyzamarshall02/aicovergen-mod/tree/main/rvc_models"
click node_modelmanage "https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/download_models.py"
click node_mdxfiles "https://github.com/freyzamarshall02/aicovergen-mod/tree/main/mdxnet_models"

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_webui,node_cli,node_user toneBlue
class node_orchestrator,node_separation,node_mixing toneAmber
class node_rvc,node_pipeline,node_pitch,node_predictors,node_synth,node_encoder,node_attention,node_commons,node_residuals,node_modules,node_hifigan,node_mrf,node_nsf,node_refinegan toneMint
class node_voicefiles,node_modelmanage,node_mdxfiles toneRose
class node_input,node_output,node_download_service toneIndigo
```

## Components

### User interfaces

- [Web UI](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/webui.py): `src/webui.py`
- [CLI entry](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py): `src/main.py`

### Cover generation

- [Cover pipeline](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py): `src/main.py`
- [Vocal separation](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/mdx.py): `src/mdx.py`
- [Audio mixing](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/main.py): `src/main.py`

### RVC conversion

- [RVC wrapper](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc_module.py): `src/rvc_module.py`
- [Conversion pipeline](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/infer/pipeline.py): `src/rvc/infer/pipeline.py`
- [Pitch extraction](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/predictors/f0.py): `src/rvc/lib/predictors/f0.py`
- [Pitch models](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/predictors/RMVPE.py): `src/rvc/lib/predictors/RMVPE.py`
- [RVC synthesizer](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/synthesizers.py): `src/rvc/lib/algorithm/synthesizers.py`
- [Text encoder](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/encoders.py): `src/rvc/lib/algorithm/encoders.py`
- [Attention layers](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/attentions.py): `src/rvc/lib/algorithm/attentions.py`
- [Algorithm utilities](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/commons.py): `src/rvc/lib/algorithm/commons.py`
- [Residual blocks](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/residuals.py): `src/rvc/lib/algorithm/residuals.py`
- [WaveNet modules](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/modules.py): `src/rvc/lib/algorithm/modules.py`
- [HiFi-GAN vocoders](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan.py): `src/rvc/lib/algorithm/generators/hifigan.py`
- [MRF vocoder](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan_mrf.py): `src/rvc/lib/algorithm/generators/hifigan_mrf.py`
- [NSF vocoder](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/hifigan_nsf.py): `src/rvc/lib/algorithm/generators/hifigan_nsf.py`
- [RefineGAN vocoder](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/rvc/lib/algorithm/generators/refinegan.py): `src/rvc/lib/algorithm/generators/refinegan.py`

### Model management

- [Voice models](https://github.com/freyzamarshall02/aicovergen-mod/tree/main/rvc_models): `rvc_models`
- [Model download](https://github.com/freyzamarshall02/aicovergen-mod/blob/main/src/download_models.py): `src/download_models.py`
- [Separation models](https://github.com/freyzamarshall02/aicovergen-mod/tree/main/mdxnet_models): `mdxnet_models`

### Other components

- **User**
- **Song source**
- **Cover audio**
- **Model hosting**

## Connections

- User → Web UI: uses (evidence: `README.md`)
- User → CLI entry: runs (evidence: `README.md`)
- User → Song source: provides (evidence: `README.md`)
- Web UI → Cover pipeline: starts generation (evidence: `README.md`)
- CLI entry → Cover pipeline: runs (evidence: `README.md`)
- Cover pipeline → Vocal separation: separates stems (evidence: `src/main.py`)
- Cover pipeline → RVC wrapper: converts vocals (evidence: `src/main.py`)
- Cover pipeline → Audio mixing: mixes audio (evidence: `src/main.py`)
- Audio mixing → Cover audio: writes (evidence: `README.md`)
- RVC wrapper → Conversion pipeline: calls (evidence: `src/rvc_module.py`)
- RVC wrapper → RVC synthesizer: loads (evidence: `src/rvc_module.py`)
- RVC wrapper → Voice models: loads model
- Conversion pipeline → Pitch extraction: requests pitch (evidence: `src/rvc/infer/pipeline.py`)
- Pitch extraction → Pitch models: uses (evidence: `src/rvc/lib/predictors/f0.py`)
- RVC synthesizer → Text encoder: uses (evidence: `src/rvc/lib/algorithm/synthesizers.py`)
- RVC synthesizer → HiFi-GAN vocoders: selects vocoder (evidence: `src/rvc/lib/algorithm/synthesizers.py`)
- RVC synthesizer → MRF vocoder: selects vocoder (evidence: `src/rvc/lib/algorithm/synthesizers.py`)
- RVC synthesizer → NSF vocoder: selects vocoder (evidence: `src/rvc/lib/algorithm/synthesizers.py`)
- RVC synthesizer → RefineGAN vocoder: selects vocoder (evidence: `src/rvc/lib/algorithm/synthesizers.py`)
- Text encoder → Attention layers: uses (evidence: `src/rvc/lib/algorithm/encoders.py`)
- Attention layers → Algorithm utilities: uses (evidence: `src/rvc/lib/algorithm/attentions.py`)
- HiFi-GAN vocoders → Residual blocks: uses (evidence: `src/rvc/lib/algorithm/generators/hifigan.py`)
- Residual blocks → WaveNet modules: uses (evidence: `src/rvc/lib/algorithm/residuals.py`)
- Residual blocks → Algorithm utilities: uses (evidence: `src/rvc/lib/algorithm/residuals.py`)
- Web UI → Voice models: manages models (evidence: `README.md`)
- Web UI → Model download: downloads via (evidence: `src/webui.py`)
- Model download → Model hosting: downloads from
- Web UI → Separation models: fetches base models
