Whisper API is an audio transcription API that uses openAI’s whisper models. Users can submit audio files or URLs and receive transcriptions for a price of $0.15/hour. The API supports various audio types and pyannote.audio speaker diarization. There is no free credit available, but users can contact firstname.lastname@example.org to get set up and potentially receive 30 minutes of free credit in exchange for honest feedback. Minimum purchase time is 10 hours, and billing is processed through Stripe.