whisper audio.mp3 --model large-v3 --language en --output_format srt
Make an SRT subtitle file
Transcribes English audio with the large-v3 model and writes an .srt subtitle file with segment timings, ready for video players or caption pipelines. SRT is the format most players and editors accept. Large-v3 is the most accurate Whisper model but slowest, so reserve it for clean, important audio.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.