first commit

.gitignore

@@ -0,0 +1,23 @@
+__pycache__/
+*.py[cod]
+.env
+.venv/
+venv/
+
+# Runtime directories created by the Space bootstrap.
+ComfyUI/
+models/
+outputs/
+tmp/
+
+# Hugging Face and model caches should stay outside git.
+.cache/
+hf_cache/
+
+# Local media samples and generated artifacts.
+*.mp3
+*.wav
+*.mp4
+*.mov
+*.mkv
+*.srt

README.md

@@ -0,0 +1,21 @@
+---
+title: VoiceGate
+emoji: ""
+colorFrom: blue
+colorTo: green
+sdk: gradio
+python_version: "3.10"
+app_file: app.py
+hardware: zerogpu
+pinned: false
+---
+
+# VoiceGate HF Space
+
+This repository is the Hugging Face Space deployment wrapper for VoiceGate.
+
+The upstream VoiceGate project and its ComfyUI workflow are kept under `VoiceGate/`
+for now. The Space runtime will be built around Gradio, ComfyUI, and the
+VoiceBridge custom nodes.
+
+Current status: planning and deployment scaffolding.

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+
+
+def placeholder():
+    return (
+        "VoiceGate HF Space scaffold is ready. "
+        "The ComfyUI runtime and workflow client will be wired in the next step."
+    )
+
+
+with gr.Blocks(title="VoiceGate") as demo:
+    gr.Markdown("# VoiceGate")
+    gr.Markdown("Hugging Face Space deployment scaffold for the VoiceGate ComfyUI workflow.")
+    run = gr.Button("Check scaffold")
+    output = gr.Textbox(label="Status")
+    run.click(fn=placeholder, outputs=output)
+
+
+if __name__ == "__main__":
+    demo.launch()

assets/.gitkeep

@@ -0,0 +1 @@
+

custom_nodes/.gitkeep

@@ -0,0 +1 @@
+

docs/deployment-plan.md

@@ -0,0 +1,183 @@
+# VoiceGate HF Space Deployment Plan
+
+## Goal
+
+Deploy VoiceGate to a Hugging Face Space with a Gradio interface, using ZeroGPU
+for the GPU-heavy inference path.
+
+The initial target is a short-audio workflow that proves the full chain:
+audio input -> source separation -> ASR/SRT -> LLM translation -> VoxCPM TTS ->
+SRT-aligned audio merge -> audio and subtitle outputs.
+
+## Repository Roles
+
+Use three clear ownership boundaries:
+
+- `VoiceGate`: upstream project assets, README, diagrams, and source workflows.
+- `comfyui_voicebridge`: the VoiceBridge ComfyUI custom node repository.
+- `VoiceGate-hf`: this repository, the Hugging Face Space deployment wrapper.
+
+The Space repository should not depend on nested git repositories at runtime.
+For deployment, copy or vendor only the required workflow files, custom nodes,
+bootstrap scripts, and Gradio application code into the Space layout.
+
+Current local state:
+
+- The outer `VoiceGate-hf` repository has no commits yet.
+- `VoiceGate/` is present as a nested upstream repository.
+- `VoiceGate/.gitmodules` references `comfyui_voicebridge`, but the local
+  `VoiceGate/comfyui_voicebridge/` directory is currently empty.
+- `VoiceGate/workflows/VoiceGate-Workflow.json` is the UI workflow.
+- `VoiceGate/workflows/VoiceGate-Workflow_api.json` exists, but currently fails
+  JSON parsing and must be re-exported or repaired before API execution.
+
+## Hugging Face Space Constraints
+
+ZeroGPU Spaces are intended for Gradio SDK Spaces. The Gradio app should expose
+a normal `app.py`, and GPU-heavy functions should be wrapped with `@spaces.GPU`.
+
+This means the first implementation should prefer:
+
+- Gradio Space root files: `README.md`, `app.py`, `requirements.txt`,
+  `packages.txt`.
+- A Python bootstrap that installs or prepares ComfyUI and custom nodes.
+- A workflow client that calls the local ComfyUI API from inside the Gradio
+  handler.
+
+Avoid starting with a Docker Space for ZeroGPU, even though Docker would be a
+cleaner fit for a long-running ComfyUI service.
+
+## Proposed Space Layout
+
+```text
+VoiceGate-hf/
+|-- README.md
+|-- app.py
+|-- requirements.txt
+|-- packages.txt
+|-- scripts/
+|   |-- bootstrap_comfy.py
+|   |-- run_comfy.py
+|   `-- workflow_client.py
+|-- workflows/
+|   |-- voicegate_api.json
+|   `-- voicegate_ui.json
+|-- custom_nodes/
+|   `-- comfyui_voicebridge/
+|-- assets/
+`-- docs/
+    `-- deployment-plan.md
+```
+
+The current repository has only the root scaffold and this plan. The later
+steps should move/copy deployment-ready workflow files into `workflows/` and
+custom nodes into `custom_nodes/`.
+
+## Known Workflow Nodes
+
+The API workflow references these important node classes:
+
+- `LoadAudio`
+- `MelBandRoFormerModelLoader`
+- `MelBandRoFormerSampler`
+- `VoiceBridgeASRLoader`
+- `VoiceBridgeASRTranscribe`
+- `GenerateSRT`
+- `RH_LLMAPI_NODE`
+- `VoiceBridgeSRTSplitter`
+- `RunningHub_VoxCPM_LoadModel`
+- `RunningHub_VoxCPM_Generate`
+- `VoiceBridgeAudioListMergerBySRT`
+- `MergeAudioMW`
+- `SaveAudioMP3`
+- `SaveSRTFromString`
+- `TrimAudioDuration`
+- `Any Switch (rgthree)`
+- `easy showAnything`
+- `easy string`
+- `CR Text`
+- `ReplaceText`
+
+This implies dependencies on VoiceBridge, VoxCPM/RunningHub nodes,
+MelBandRoFormer nodes/models, rgthree, easy-use, and the LLM API node package.
+
+## Model and Secret Inventory
+
+Expected model assets:
+
+- `Qwen/Qwen3-ASR-1.7B`
+- `Qwen/Qwen3-ForcedAligner-0.6B`
+- `VoxCPM2`
+- `MelBandRoFormer_comfy/MelBandRoformer_fp32.safetensors`
+
+Expected Space secrets:
+
+- `HF_TOKEN`, if private or gated model downloads are needed.
+- `DEEPSEEK_API_KEY` or another LLM provider key.
+- Optional LLM base URL and model name configuration.
+
+Do not commit model weights, API keys, generated audio, or generated subtitles.
+
+## Implementation Phases
+
+### Phase 1: Scaffold and Planning
+
+Done in this step:
+
+- Add HF Space root files.
+- Add minimal Gradio placeholder.
+- Add deployment plan.
+- Add ignore rules for runtime and generated artifacts.
+
+### Phase 2: Runtime Bootstrap
+
+Create scripts that can:
+
+- Clone or install ComfyUI.
+- Install Python dependencies.
+- Install required custom nodes at pinned commits.
+- Download or locate required model files.
+- Start ComfyUI locally inside the Space process.
+
+### Phase 3: Workflow Hygiene
+
+Repair or re-export `VoiceGate-Workflow_api.json` so it is valid API JSON.
+
+Required edits:
+
+- Remove stale demo file references.
+- Replace hard-coded audio filenames with Gradio-uploaded input paths.
+- Replace empty API keys with environment variables.
+- Parameterize target language, LLM model, and provider base URL.
+- Ensure output nodes produce deterministic file paths.
+
+### Phase 4: Gradio Integration
+
+Build the first real interface:
+
+- Input audio file.
+- Target language selector/text input.
+- Source language, default `auto`.
+- Optional prompt override.
+- Output audio.
+- Output translated/adjusted SRT.
+- Runtime log.
+
+Wrap the end-to-end function with `@spaces.GPU(duration=...)` and start with a
+short maximum input duration.
+
+### Phase 5: Verification
+
+Verify in this order:
+
+1. ComfyUI starts and exposes its local API.
+2. TTS-only minimal workflow runs.
+3. ASR-only short audio workflow runs.
+4. SRT splitter + VoxCPM + merger runs.
+5. Full VoiceGate short-audio workflow runs.
+6. Video input support is added after the audio path is stable.
+
+## Immediate Next Step
+
+Prepare the runtime bootstrap scripts and decide whether to vendor custom nodes
+into `custom_nodes/` or download pinned commits during Space startup.

packages.txt

@@ -0,0 +1,2 @@
+ffmpeg
+git

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+spaces
+requests
+websocket-client
+huggingface_hub

scripts/.gitkeep

@@ -0,0 +1 @@
+

workflows/.gitkeep

@@ -0,0 +1 @@
+