StoryCorps is proud to partner with Google Cloud to transcribe interviews in the StoryCorps Online Archive. We understand that for our participants, this can bring up many questions about their data and privacy. Whether you’ve participated in a Signature StoryCorps recording with a StoryCorps facilitator, or recorded an interview on your own using the StoryCorps App or StoryCorps Connect, we hope that the FAQs below will answer your questions.
How are StoryCorps and Google Cloud making the StoryCorps archive accessible and searchable?
StoryCorps is collaborating with Google Cloud to digitize and unlock StoryCorps’ amazing archive using artificial intelligence (AI). To learn more about how Google Cloud, visit their website here. The result is an open, searchable and accessible audio database for everyone to find and listen to first-hand perspectives from humanity’s most important moments. Of course, StoryCorps participants will always have the ability to hide or limit access to their interviews and transcripts. For more information about privacy settings, please see below.
Diving into how this works: for an audio recording to be searchable, the audio file and “moments” or keywords within that file—needed to be tagged with terms for which you would search.
- First we used Speech-to-Text API to transcribe the audio file.
- Then Natural Language API identified keywords and their salience from the transcription.
- Resulting in a searchable transcript on the StoryCorps Online Archive.
What information does StoryCorps share with Google Cloud Platform for the transcription service?
To enable the transcription of the interview, Storycorps shares the audio file and metadata (including key proper nouns from the interview) with Google Cloud Platform’s Cloud Speech-to-Text API to convert the interview into a text transcript.
Can Google Cloud use my transcript or data?
Google Cloud Platform uses the interview and data as needed to create the transcript and provide the transcription service. Google Cloud cannot use the data further or share the transcript without permission from StoryCorps.
Click here to learn more about Google Cloud’s Enterprise Privacy Commitments.
Who owns my interview?
For Signature interviews—recorded with a StoryCorps trained facilitator or StoryKit—StoryCorps owns the copyright to your interview recording. For user-generated interviews (like those recorded with the StoryCorps App or StoryCorps Connect), the copyright holder is the user who uploaded the interview. Google does not maintain ownership of your interview transcript or your data.
Will my transcript and other interview data appear in a Google search or on other search engines?
The answer to this question depends on your privacy (or visibility) setting. Like all the information on your interview page in our archive, if you choose to set your interview privacy setting to “Public” it can be found in a Google search, and your transcript may result in it appearing in Google searches more frequently. Interviews that are set to “Private” or “StoryCorps Community” will not appear in a Google Search. You can learn more about your privacy settings here.