Outliner Software Forum RSS Feed Forum Posts Feed

Subscribe by Email

CRIMP Defined


Tip Jar

voice memos speech recognition / transcription

< Next Topic | Back to topic list | Previous Topic >

Pages:  1 2 3 > 

Posted by jimspoon
Jan 4, 2015 at 06:10 AM


I would like to be able to grab a voice recorder, and without even looking at it, push a button to start recording, start talking, push another button to end the recording.  Then I’d like the recording to be automatically uploaded to Google’s or Dragon’s servers, and have the recognized text appended to a text file with an appropriate time stamp.

I’ve looked for an Android app that would enable me to do this, but have not found anything very close to what I’m looking for.  I am able to enter text in android notetaking apps by dictation with real-time recognition and transcription.  But this involves steps I want to be able to avoid - (1) wake up phone; (2) find the notetaking app; (3) start a new note; (4) activate the speech recognizer; (5) monitor the speech recognition results while talking, (6) push a button to save the stop the recording, (7) name the note, etc.

In other words - the process currently involves too many steps, which discourages the making of such notes in the first place.

Has any found a device or app (on any platform) which does something like I’ve described in the first paragraph?  I haven’t found it on Android, but maybe it’s different on other platforms.

thanks in advance -


Posted by jimspoon
Jan 4, 2015 at 12:00 PM


just to clarify - I’m looking for an app or device that does NOT require that upload, recognition, and text delivery take place as I speak -  but rather is capable of uploading previously recorded sound files for recognition and text delivery - preferably automatically and unattended.  that’s the main thing that I"m looking for - that I could make a voice recording quickly, and not have to attend to the recognition and transcription.


Posted by Hugh
Jan 4, 2015 at 06:37 PM


As far as I know, a solution to meet your exact requirements doesn’t exist (yet). You could probably get near to them using Siri on an iDevice, or its equivalent on Android (I’m sorry, I’m unfamiliar with the Android platform). I gather from your post that it’s the surrounding procedures rather more than the dictation technology itself that you’re - understandably - finding frustrating. To reduce the button-pushing on an iDevice, personally I’d use Launch Center Pro, into which keyboard shortcuts can be programmed under iOS8, plus Nuance’s Dragon Dictation app (which I’ve found to be more accurate than Siri - although see below), plus email, again pre-programmed. As you’re probably aware, Nuance is the big dog in this market, with - probably - the most advanced technology and in my experience improving results - and to the best of my knowledge, others, including Apple and Microsoft, license their software, including Siri, from Nuance - Google I don’t know.

(There is reason for optimism. According to this weekend’s newspapers, AI research is starting to make some progress after a period of years when results did not match expectations. And one area in which strides are being made by several Silicon Valley enterprises is pattern recognition, including voice recognition. Possibly it isn’t too much to hope that dictation/voice-to-text and voice control of software will become ubiquitous, easy-to-use and still more precise before very long?)


Posted by Hugh
Jan 4, 2015 at 06:51 PM


Re-reading your posts, I conclude that Siri or its Android equivalent isn’t a solution. Nuance also distribute a recording app for i-devices: that, plus some form of automation for holding, uploading, transcribing and filing the resultant file, sound like the answer you need. That would probably require different kinds of automation at the levels of the mobile device, and the server; I don’t know what those would be.


Posted by Paul Korm
Jan 4, 2015 at 07:04 PM


I use Dictate + Connect on my iPhone—there’s also an Android version.


Over here, I dictate a note and it is automatically uploaded to Dropbox as a .wav.  Later, on my Mac, I open Dragon Dictate, launch a transcription profile, and then open the .wav files created with Dictate.  They are transcribed, and Dragon then asks where I want to save the transcriptions.

Not as automated flow as Jim’s requirements—but Dictate has a lot of config options (including automatically sending an email of the dictation) that might be tweaked.


Pages:  1 2 3 > 

Back to topic list