This is incredibly helpful for someone who isn't needing too much in terms of AI features, because I simply want to access localized dictation for writing my notes for an electronic health record (HIPAA/privacy considerations). To be honest, I was really happy with speech notes annual plan before I switched to vivaldi browser and it no longer works in quite the same way bc was designed as chrome extension. As I've been exploring local dictation options, the biggest issue I've run into is that they all take over the sound input/output while processing speech. EG., Let's say I'm working on dictating a note while I'm waiting for a client to enter my zoom waiting room and chime that they've arrived. When the dictation is active, the chime doesn't sound!!! I discovered that I literally have to go change zoom output sound setting from my headphones to the mac speaker (even when the input for the dictation is NOT my headphone mic...). This has put a HUGE damper on my efficiency and presence while writing notes, because it means I have to constantly be checking in with myself to see if client has arrived, or remember every time to switch the zoom output to mac speaker. I'd love to know whether spokenly or voiceink or whisper might do this integration more effectively. In particular, spokenly would really support lower business costs since I definitely do not plan to use any linked AI models at this point.
Great post. One big thing that i think helps separate voice ink is the ability to quickly browse the history wav files, and the ability to quickly drag a file from the finder into the "transcribe audio" tab. You need to pre-select the An A.I. audio model which is a little clunky but overall I find this still much faster than trying to look for a file in the SuperWhispers catalog and try to reprocess it there.
With Superwhisper you can right click any audio file -> open with Superwhisper. Or from the menu bar icon. Or if you got any automation app, also you can do a quick automation to open any selected file with Superwhisper.
What a fantastic post! Thank you for sharing all those thoughts. I can relate to everything you write very well and I can see why you are somewhat stuck between Superwhisper and Spokenly. From the perspective of someone who is just getting started with these kinds of apps (and who therefore doesn't have the same "early adopter bias") I would suggest that you don't put too much hope into Superwhisper and start transitioning to Spokenly. This suggestion is biased in its own way, though: I would love to use macrowhisper with Spokenly ;-)
But here is the explanation for why there is no reason to assume that Superwhisper will be anything like it was before: "the law of the marginal user", as it is called in this video: https://www.youtube.com/watch?v=BQLVgmhgtpQ. Or the "the enthusiast trap" in this one: https://youtu.be/FJgTKx-rg18
Wow, thanks a lot for linking those two videos. Super insightful. Saw this phrase in one of those that really connects with what I've seen... "as the product grows, there's this larger and larger number of users that don't really care about it, but they end up driving all the decisions for those in the zone that do really care about the product."
Since I wrote this, a few of my biggest annoyances have improved with Superwhisper. It's definitely not back to what it used to be, but a couple UI tweaks at least made it more usable for me again.
At the same time, my biggest issues with Spokenly being sandboxed and not allowing a deeper system integration remain. So, for my specific workflow I don’t really see it overtaking Superwhisper, at least not until something changes there. We'll see where it all goes from here.
This is incredibly helpful for someone who isn't needing too much in terms of AI features, because I simply want to access localized dictation for writing my notes for an electronic health record (HIPAA/privacy considerations). To be honest, I was really happy with speech notes annual plan before I switched to vivaldi browser and it no longer works in quite the same way bc was designed as chrome extension. As I've been exploring local dictation options, the biggest issue I've run into is that they all take over the sound input/output while processing speech. EG., Let's say I'm working on dictating a note while I'm waiting for a client to enter my zoom waiting room and chime that they've arrived. When the dictation is active, the chime doesn't sound!!! I discovered that I literally have to go change zoom output sound setting from my headphones to the mac speaker (even when the input for the dictation is NOT my headphone mic...). This has put a HUGE damper on my efficiency and presence while writing notes, because it means I have to constantly be checking in with myself to see if client has arrived, or remember every time to switch the zoom output to mac speaker. I'd love to know whether spokenly or voiceink or whisper might do this integration more effectively. In particular, spokenly would really support lower business costs since I definitely do not plan to use any linked AI models at this point.
Great post. One big thing that i think helps separate voice ink is the ability to quickly browse the history wav files, and the ability to quickly drag a file from the finder into the "transcribe audio" tab. You need to pre-select the An A.I. audio model which is a little clunky but overall I find this still much faster than trying to look for a file in the SuperWhispers catalog and try to reprocess it there.
With Superwhisper you can right click any audio file -> open with Superwhisper. Or from the menu bar icon. Or if you got any automation app, also you can do a quick automation to open any selected file with Superwhisper.
Oh shoot I did not realize that woops. What I need to figure out then is how to quickly switch modes
I will say though it's still quicker to get to the history/wav file from voiceink, though it's faster only by one click.
What a fantastic post! Thank you for sharing all those thoughts. I can relate to everything you write very well and I can see why you are somewhat stuck between Superwhisper and Spokenly. From the perspective of someone who is just getting started with these kinds of apps (and who therefore doesn't have the same "early adopter bias") I would suggest that you don't put too much hope into Superwhisper and start transitioning to Spokenly. This suggestion is biased in its own way, though: I would love to use macrowhisper with Spokenly ;-)
But here is the explanation for why there is no reason to assume that Superwhisper will be anything like it was before: "the law of the marginal user", as it is called in this video: https://www.youtube.com/watch?v=BQLVgmhgtpQ. Or the "the enthusiast trap" in this one: https://youtu.be/FJgTKx-rg18
Wow, thanks a lot for linking those two videos. Super insightful. Saw this phrase in one of those that really connects with what I've seen... "as the product grows, there's this larger and larger number of users that don't really care about it, but they end up driving all the decisions for those in the zone that do really care about the product."
Since I wrote this, a few of my biggest annoyances have improved with Superwhisper. It's definitely not back to what it used to be, but a couple UI tweaks at least made it more usable for me again.
At the same time, my biggest issues with Spokenly being sandboxed and not allowing a deeper system integration remain. So, for my specific workflow I don’t really see it overtaking Superwhisper, at least not until something changes there. We'll see where it all goes from here.
I just stumbled upon Monologue but haven't tried it yet. Do you have any thoughts on it?
Looks like it does the same (or less) than most other AI dictation apps. Not worth a subscription for me. But that's just me.