Sound Design Stack Exchange is a question and answer site for sound engineers, producers, editors, and enthusiasts. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I like to record the older folks in my family. I put my recorder on the table and we just chat. Just hanging out.

Most of the resulting footage is not interesting but occasionally, I get a gem. Some story from way back told in a way that's just awesome.

I've been using google voice for some time now. It transcribes the message and texts it to me. The transcription is often entertainingly off, but usually close enough the get the gist.

So voice recognition appears to be getting pretty good.

Is there a way I can leverage this to get a rough transcript of my recordings. I figure skimming that will be easier than listening.

share|improve this question

migrated from Jan 24 '14 at 12:01

This question came from our site for engineers, producers, editors, and enthusiasts spanning the fields of video, and media creation.

If you happen to be a video editor, then the latest Premiere Pro has a respectable voice transcribing component in it.

If your recordings are very clear and high quality, then a crazy idea might be to play back the recording to Dragon Naturally Speaking. But, given current technology, I doubt any software solution would work well, and all will generate quirky sentences.

My favorite option is to send your files to a third party for transcription. Most services specialize in medical and legal, but some will transcribe any audio for you. Nuance's service Jott, the main one I knew about, was apparently just axed in May 2011. An online search for "voice transcription service" gives you a ton of options to choose from, some domestic, some offshore. Services like this may cost you, but your results will be much better than a software approach.

share|improve this answer
My experience with playing back to speech recognition systems - and I do research on this - is that it doesn't work very well. – Ankur Banerjee Jul 8 '11 at 9:22

One technique that I've tried is similar to Clint's suggestion, but instead of playing the recording into Dragon, you listen to the recording on headphones and then speak what you're hearing into Dragon. This may yield better results since voice recognition software relies on learning one person's voice to improve it's accuracy. You'll also have an opportunity, as you 'translate' to speak more clearly than the interviewee did. You can try it out by getting a free version of the Dragon iPhone App. It's probably available on other platforms as well.

There's also software for sale called Boris SoundBite that, while it doesn't do transcription, it allows you to search for a given word amongst hours and hours of video files.

share|improve this answer

There is a new USB-based group microphone that can record six separate audio channels called the Microcone which will do just what you are looking for. It has a separate app called the Microcone Recorder which is perfect for recording groups, with it you get a visual timeline with indication of who was speaking and you can tag sections of the recording on the fly.

There is also in-built audio transcription using Nuance (the company behind Dragon).

share|improve this answer

You could try using (I haven't used them personally, but they've got a good reputation).

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.