Installation

Requirements

• Python 3.10 or newer

• An OpenAI API key for transcription

• Optional: a Hugging Face token and pyannote.audio for speaker diarization

Install with uv

uv sync

Install with pip

pip install -e .

Optional diarization dependencies

uv sync --extra diarize

or:

pip install -e ".[diarize]"

Configuration

Set credentials in the environment:

export OPENAI_API_KEY="your_api_key_here"
export HUGGINGFACE_TOKEN="your_huggingface_token_here"

whisper-smith also loads a .env file from the project root.