Speech Model Block Reference ๐ฃ๏ธ
Whisper
The Whisper block is powered by OpenAIโs speech recognition model. This block is used to transcribe or translate any supported language into English text.
The Whisper block has 1 input and 1 output.
Inputs:
Audio
: Live or recorded audio file to transcribe or translate into English text.
Output:
Text
: The english text transcribed or translated by the audio input.