Speech to Text v2 - Whisper Large-v3

Speech to Text v2 API allows you to transcribe any audio file using OpenAI-Whisper Large-v3 model.

OpenAI Whisper is an open-source automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.

The large-v3 model shows improved performance over a wide variety of languages, showing 10% to 20% reduction of errors compared to Whisper large-v2.

Make sure to use Fetch Results API after process_id is received

This API supports following use-cases:

• Want to upload a file < 8MB: Checkout Whisper - Sample Code Recipe
• Want to upload a file > 8MB: Checkout File Upload > 8MB Recipe
• Want to send file url instead of upload: Checkout Whisper File URL Recipe