Skip to the content.

Example: Speed Talking

This example transcribes an english fast-paced audio file using Whisper in TXT, VTT, SRT, TSV and JSON formats.

Input

task: Transcribe

audio_file: micro-machines.wav

use_model: medium

language: English

Output

output_formats: txt,vtt,srt,tsv,json

audio_transcription/micro-machines.txt

audio_transcription/micro-machines.vtt

audio_transcription/micro-machines.srt

audio_transcription/micro-machines.tsv

audio_transcription/micro-machines.json