One key feature I’m looking for in Transcription software is the creative editing of the ensuingly generated Titles. I believe most, including Simonsays, come in as Basic Title which has limited animation functions.
Alex from Ulti.Media has said that their Transcriber will support using Titles other than Basic in a future update. I would love for Titles to come in as Custom for example which would allow very flexible animation.
As the professional demands for marketing and advertising on Instagram and TikTok increase, creative title editing will also increase. Consider what CapCut or Instagram’s built-in titling can do now.
BTW I do think the subscription services (Simonsays, Speedscriber, etc.) are going to have to focus on more value-added features as Transcriber and Captionator are based on Whisper so there’s no per word or duration cost (beyond the cost of the module).
I agree, and are already seeing most of those features happening in Premiere Pro, at no extra cost. Although not perfect, it is developing.
The next holy grail in transcription and subtitling, is translation, and text to voice audio replacement. Again, not perfect, as you still need a native speaker to make sure that the language is right (Think subtle difference in the meaning between “Here” and “Hear”).
Should for transparency state that I am a customer, and have recently helped them with a video for Seedrs crowd-investment platform, where we did: English -> Transcribe -> English subtitles -> Translate to Spanish -> Copy to “Text-to-Speech” -> insert Spanish voice on video -> Interviewee (investor) speaking in Spanish with English subtitles.
This is only a small peek into the near-future of what is to come in improved features (inside NLE software or as an external resource) that will help us in the editing process, making videos more inclusive for a wider audience.
Kyrina, the 3rd-party MacWhisper utility can not only transcribe with high accuracy to an SRT file, but it can also translate at the same time. You can easily produce English and Spanish SRT files, import those to FCP via File>Import>Captions, and flip between them. Each one automatically becomes a separate audio role, visible in the timeline index. You switch subtitles by opening the Timeline Index (SHFT+CMD+2 toggles), then press “Roles”. The English and Spanish subtitles will have a separate button to enable or disable them. I’ve used MacWhisper extensively and it works well: https://goodsnooze.gumroad.com/l/macwhisper
The latest version has an optional translation feature using the DeepL AI tool. It supposedly produces higher-quality translations than the built-in MacWhisper translation. That is a paid upgrade but you get 500,000 words per year free.
I think the most recent update to MacWhisper requires Ventura.
Another item I recently found (but have not tested) is SRT Importer 2, which lets FCP import SRT captions as titles. That’s in case you want the flexibility of a subtitled presentation vs the more restrictive caption display options. In theory, if the SRT output of MacWhisper was good enough quality, you could then convert it from captions to subtitles. FCP SRT Importer 2: https://ulti.media/fcp-srt-importer-2/
ulti.media Transcriber is built on MacWhisper. I’ve also used MacWhisper. Transcriber uses the “Large” transcription model from Whisper (MacWhisper Pro) which improves transcription reliability and adds many Caption features. They’ll be adding even more caption features. BTW it’s also Adobe PremierePro compatible so I suspect they feel their offering is even better than Premiere’s built-in equivalent.
Trint.com is an AI-powered transcription service with useful capabilities. Amongst other things, you can do paper edits and string outs. I believe it will emit an xml you can load into several edit apps.