Nieman Foundation at Harvard
HOME
          
LATEST STORY
Don’t click this: When should news organizations use “nofollow” links?
ABOUT                    SUBSCRIBE
Oct. 31, 2016, 11:17 a.m.
Reporting & Production
LINK: opennewslabs.github.io  ➚   |   Posted by: Shan Wang   |   October 31, 2016

Transcribing and then trying to edit audio or video makes me want to tear my hair out. While there are free tools out there to simplify the process — oTranscribe, Draft — finding the right quotes from a long speech or cleaning up a Q&A still feels interminable.

autoEdit, an open source editor being developed by Knight-Mozilla fellow Pietro Passarelli during his time at Vox Media, shaves some time off a lot of post-production tasks, such as captioning videos.

At the moment, autoEdit work with either IBM Watson’s speech-to-text API (supports several languages) or Gentle (free and works offline; English only) to generate a transcript. (For what it’s worth, I tried this a few times and found Gentle to be perfectly serviceable.) Once the transcript is generated, autoEdit offers a number of intuitive editing features, such as exporting select quotes with the corresponding video clip into Adobe Premiere.

3_transcription

The Vox team has already been using it, for instance, to pick out highlights from Michelle Obama’s speech earlier this month in Phoenix on the stump for Hillary Clinton and caption a short Facebook video on her speech (a case where video of the speech wasn’t available on television, so wasn’t available on Snapstream).

Based on user feedback, Passarelli is still tinkering with things like word-by-word versus line or sentence-level editing of transcripts, and the option to select quotes from multiple different transcriptions and bring them together into a story script at the paper edit level.

You can try it out here.

Show tags Show comments / Leave a comment
 
Join the 50,000 who get the freshest future-of-journalism news in our daily email.
Don’t click this: When should news organizations use “nofollow” links?
Plus, a new free course for online fact-checking taught via workspace app Notion.
One potential route to flagging fake news at scale: Linguistic analysis
It’s not perfect, but legitimate and faked news articles use language differently in ways that can be detected algorithmically: “On average, fake news articles use more expressions that are common in hate speech, as well as words related to sex, death, and anxiety.”
Finally, Instagram is getting fact-checked (in a limited way and just in the U.S., for now)
“The potential to prevent harm is high here, particularly with the widespread existence of health misinformation on the platform.”