Great! Here's how to deploy your OpenVoice-based Gradio app on Hugging Face Spaces using Docker.


---

1. Directory Structure

openvoice-gradio-app/
├── app.py
├── Dockerfile
├── requirements.txt
└── README.md (optional)


---

2. app.py

Here's a minimal Gradio interface using OpenVoice:

import gradio as gr
from openvoice import OpenVoice

# Load OpenVoice model (adjust to your setup)
model = OpenVoice(language="en")

def clone_and_speak(audio, text):
    output_path = "output.wav"
    model.clone_voice(
        source_audio_path=audio.name,
        target_text=text,
        output_path=output_path
    )
    return output_path

with gr.Blocks() as demo:
    gr.Markdown("# OpenVoice TTS - Hugging Face Space")
    with gr.Row():
        audio_input = gr.Audio(label="Upload voice to clone", type="file")
        text_input = gr.Textbox(label="Enter text to synthesize")
    with gr.Row():
        generate_btn = gr.Button("Generate Audio")
        audio_output = gr.Audio(label="Synthesized Output", type="filepath")

    generate_btn.click(fn=clone_and_speak, inputs=[audio_input, text_input], outputs=audio_output)

demo.launch()


---

3. requirements.txt

List all necessary dependencies:

gradio
torch
transformers
numpy
# Include the repo name if OpenVoice is pip-installable
# If using local installation, skip and use Dockerfile instead


---

4. Dockerfile

# Use official Python image
FROM python:3.10-slim

# System dependencies
RUN apt-get update && apt-get install -y ffmpeg git && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy files
COPY . .

# Install Python dependencies
RUN pip install --upgrade pip
RUN pip install -r requirements.txt

# Clone OpenVoice if not pip installable
RUN git clone https://github.com/myshell-ai/OpenVoice.git && \
    pip install -e OpenVoice

# Expose port for Gradio
EXPOSE 7860

# Launch the app
CMD ["python", "app.py"]


---

5. Push to Hugging Face Spaces

1. Create a new Space on Hugging Face.


2. Set SDK to Docker.


3. Push your files to the linked repo via Git.



git init
git remote add origin https://huggingface.co/spaces/your-username/openvoice-gradio-app
git add .
git commit -m "Initial commit"
git push -u origin main


---

Let me know if OpenVoice needs special model download steps or GPU setup. I can adjust the Dockerfile accordingly. Would you like GPU support included?