Transcribe an audio/video file with Groq Whisper

whisper_groq2srt.py

# /// script
# requires-python = ">=3.13"
# dependencies = [
#     "groq",
# ]
# ///
from groq import Groq
import math

client = Groq()

filename = "input.mp3" # change file name here (40 Mb max)

with open(filename, "rb") as file:
    transcription = client.audio.transcriptions.create(
      file=(filename, file.read()),
      model="whisper-large-v3-turbo", # or "distil-whisper-large-v3-en" or "whisper-large-v3"
      response_format="verbose_json",
    )

segments = (transcription.segments)

def convert_seconds_to_hms(seconds):
    hours, remainder = divmod(seconds, 3600)
    minutes, seconds = divmod(remainder, 60)
    milliseconds = math.floor((seconds % 1) * 1000)
    output = f"{int(hours):02}:{int(minutes):02}:{int(seconds):02},{milliseconds:03}"
    return output

count = 0
with open("subs.srt", 'w') as f:
      for segment in segments:
        count +=1
        duration = f"{convert_seconds_to_hms(segment['start'])} --> {convert_seconds_to_hms(segment['end'])}\n"
        text = f"{segment['text'].lstrip()}\n\n"
        f.write(f"{count}\n{duration}{text}")

print("SRT file saved successfully!")