Audio Transcription Exerciser

This example, which is available on GitHub, lets you test various configurations and options when using the Deepgram speech recognition API in batch mode, which processes prerecorded audio rather than streamed audio.

Authentication

Username:

Password:

Options

Transcription model:

Language:

Use punctuation

Enable diarization
(Identify speakers)

Audio Source

Capture microphone (if supported):

Choose an audio file:

Enter audio URL:

Progress:

Transcription

Words

#	Word	Start Time (sec)	Speaker