A multi-tool audio studio for text-to-speech, voice cloning, music generation, stem splitting, and other audio workflows.
Generate realistic speech from text prompts.
Compatible Models
Laboratory OS Installation Details
Environment
Environment Variables
Install & Run
#!/bin/bash set -e export PATH="/opt/conda/bin:/root/.local/bin:$PATH" # Clone the GitHub repository into the directory when needed mkdir -p "/workspace/audio-webui" if [ -d "/workspace/audio-webui/.git" ]; then echo "Git repository already initialized in /workspace/audio-webui" elif [ -z "$(ls -A "/workspace/audio-webui" 2>/dev/null)" ]; then git clone --progress "https://github.com/gitmylo/audio-webui" "/workspace/audio-webui" else echo "Working directory /workspace/audio-webui already exists and is not a git repository." echo "Leaving existing files untouched and skipping clone of https://github.com/gitmylo/audio-webui." fi # Change to the app directory cd "/workspace/audio-webui" # Install the requested Python version and create a virtual environment when needed uv python install 3.11 if [ ! -d ".venv" ]; then uv venv --seed --python 3.11 .venv else echo "Virtual environment already exists at /workspace/audio-webui/.venv" fi # Activate the virtual environment source .venv/bin/activate # Install PyTorch uv pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu128 # Environment setup complete echo "Environment setup complete!" uv pip install wheel uv pip install soxr uv pip install numpy torch --upgrade uv pip install fairseq # Run with an invalid port to do setup and exit bash ./run.sh --port -1 bash ./run.sh --listen --port $AUDIO_WEB_UI_PORT --no-data-cache -v $OPENLAB_EXTRA_ARGS