After install, you can also use the console entry point:
Run:
Route requests through LiteLLM to access 100+ providers with unified calling:
Then set base_url: litellm in summarizer.yaml and use provider-prefixed models:
See Transcription for GPU setup.
Tip: Install with
pip install -e .[litellm]to route through LiteLLM and access 100+ providers with unified calling.