Instructions to use autotools/ai_video_studio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use autotools/ai_video_studio with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="autotools/ai_video_studio", filename="runtime/Auto Movie Reviewer/models/Phi-3.5-mini-balanced.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use autotools/ai_video_studio with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf autotools/ai_video_studio:Q4_K_M # Run inference directly in the terminal: llama cli -hf autotools/ai_video_studio:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf autotools/ai_video_studio:Q4_K_M # Run inference directly in the terminal: llama cli -hf autotools/ai_video_studio:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf autotools/ai_video_studio:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf autotools/ai_video_studio:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf autotools/ai_video_studio:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf autotools/ai_video_studio:Q4_K_M
Use Docker
docker model run hf.co/autotools/ai_video_studio:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use autotools/ai_video_studio with Ollama:
ollama run hf.co/autotools/ai_video_studio:Q4_K_M
- Unsloth Studio
How to use autotools/ai_video_studio with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for autotools/ai_video_studio to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for autotools/ai_video_studio to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for autotools/ai_video_studio to start chatting
- Atomic Chat new
- Docker Model Runner
How to use autotools/ai_video_studio with Docker Model Runner:
docker model run hf.co/autotools/ai_video_studio:Q4_K_M
- Lemonade
How to use autotools/ai_video_studio with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull autotools/ai_video_studio:Q4_K_M
Run and chat with the model
lemonade run user.ai_video_studio-Q4_K_M
List all available models
lemonade list
| import argparse | |
| import sys | |
| from core.cloner import KokoClone | |
| def main() -> None: | |
| """Entry point for the KokoClone command-line tool.""" | |
| parser = argparse.ArgumentParser(description="KokoClone: Zero-Shot Multilingual Voice Cloning") | |
| parser.add_argument( | |
| "--mode", | |
| choices=["tts", "convert"], | |
| default="tts", | |
| help="Operation mode: 'tts' (text → cloned speech) or 'convert' (audio → re-voiced speech)", | |
| ) | |
| parser.add_argument("--text", type=str, help="[tts mode] Text to synthesize") | |
| parser.add_argument( | |
| "--lang", | |
| type=str, | |
| default="en", | |
| help="[tts mode] Language code (en, hi, fr, ja, zh, it, pt, es)", | |
| ) | |
| parser.add_argument( | |
| "--source", | |
| type=str, | |
| help="[convert mode] Path to source audio file to re-voice (.wav)", | |
| ) | |
| parser.add_argument("--ref", type=str, required=True, help="Path to reference voice audio file (.wav)") | |
| parser.add_argument("--out", type=str, default="output.wav", help="Output file path (.wav)") | |
| args = parser.parse_args() | |
| cloner = KokoClone() | |
| if args.mode == "tts": | |
| if not args.text: | |
| parser.error("--text is required when --mode is 'tts'") | |
| cloner.generate( | |
| text=args.text, | |
| lang=args.lang, | |
| reference_audio=args.ref, | |
| output_path=args.out, | |
| ) | |
| elif args.mode == "convert": | |
| if not args.source: | |
| parser.error("--source is required when --mode is 'convert'") | |
| try: | |
| cloner.convert( | |
| source_audio=args.source, | |
| reference_audio=args.ref, | |
| output_path=args.out, | |
| ) | |
| except Exception as exc: | |
| print(f"Error during voice conversion: {exc}", file=sys.stderr) | |
| sys.exit(1) | |
| if __name__ == "__main__": | |
| main() |