Example: Song

This example transcribes an english song using Whisper in TXT, VTT and SRT formats.

Input

task: Transcribe

audio_file: bruce.mp3

use_model: large-v2

language: Auto-Detect (English)

Output

output_formats: txt,vtt,srt

audio_transcription/bruce.txt

audio_transcription/bruce.vtt

audio_transcription/bruce.srt