Speech-to-Text
Transcribe video to timestamped text with Whisper.
Workflow
The complete transcription workflow — required pre-run setup, invocation,
output format, and troubleshooting — is documented in the packaged
reference speech_to_text_workflow.pdf.
Read that document first and follow it end-to-end. The commands and
setup order it specifies are required; the summary on this page is not
sufficient on its own.