D: 66.96s
00:00:00.000
00:01:06.960
📢 [HIT SPACE TO START HELP TOUR]
Hey, here's a short introduction to what this tool is about. This tool helps you edit your transcripts files once they are generated. This will not generate the transcript for you, it'll just help you edit them. If you're looking for generating transcript, then you can check the main tool wscribe Also, if I am speaking too slow, you can change the playback speed with the buttons in the bottom on the media players. Anyway, let's dive into some of the features, shall we? This supports importing transcription files from various formats, SRT, VTT, and even JSON. With JSON, you can also have word -level timestamps. On exporting, this can export to SRT, VTT, JSON, and plain old print text files.
Hey, here's a short introduction to what this tool is about. This tool helps you edit your transcripts files once they are generated. This will not generate the transcript for you, it'll just help you edit them. If you're looking for generating transcript, then you can check the main tool wscribe Also, if I am speaking too slow, you can change the playback speed with the buttons in the bottom on the media players. Anyway, let's dive into some of the features, shall we? This supports importing transcription files from various formats, SRT, VTT, and even JSON. With JSON, you can also have word -level timestamps. On exporting, this can export to SRT, VTT, JSON, and plain old print text files.
🤜
2.26s 🤛
D: 53.8s
00:01:09.220
00:02:03.020
Let's talk about editing modes. Once you load a subtitle file, the tool transforms it into both subtitle and transcript formats. You can always switch between the two modes right there from the settings pane, nestled at the cozy right bottom of your screen. Also, your changes in subtitle mode won't day crash your transcript party and vice versa. You can switch between them as the media continues to play. I would suggest you to try it right now. Um, if you have word -level confidence or hitting show confidence will color code each word below a certain threshold, making it clear where the AI generation might have been fuzzy.
🤜
0.44s 🤛
D: 52.62s
00:02:03.460
00:02:56.080
Um, this can be top of as the media is playing as. Oh, you can import media, media, um, so that while you edit the, the transcript, you can cross check with the original media. Um, uh, the space key press works for play pause, like you'd expect, um, as the media plays, the current segment will be highlighted, stealing the show. And if you've got that family of words, um, you can, you know, fancy word level timestamp data. We go full paparazzi highlighting each word. Like it's a superstar stepping onto the red carpet. Um, while your, uh, media plays a click on a segment will transport you from time
🤜
0.76s 🤛
D: 47.62s
00:02:56.840
00:03:44.460
directly to that timestamp. Um, and guess what? Uh, if you're rocking that word level, um, uh, timestamp, it's like teleporting to the exact moment the word dropped. Um, you can change offset, create new segments, delete them, et cetera. Um, check for edit buttons to the right of each segment. Um, by the way, fun fact about what you're hearing and reading right now. Um, the original transcript was written by chat GPT, then transformed into voice using Suno slash bark.
🤜
0.5s 🤛
D: 19.22s
00:03:44.960
00:04:04.180
And then I dog fooded scribe whisper to generate the transcript from it. Um, I guess that's all more or less. Um, feel free to ask, suggest, complain of things in GitHub issues. Uh, happy editing. Um,
EOT: 00:04:04.180
CUR: 00:00:00.000
SPD: 1x
SEG: 5
help 💡
- Use space to play/pause
- Edit/Add segments:
- Remove segments:
- Change playback speed with (n)x
- Toggle between transcript & subtitle
- Toggle confidence (if applicable)
- This is only a transcript editor, it does not generate. Check wscribe to generate transcripts.