Word-By-Word Timestamps for Audio Transcription
by Alexandr Wang on May 13th 2017
Starting today, we will now be sending word-by-word timestamps for all of our audio transcription requests. It was a common feature request we’ve gotten for our audio transcription API, and has enabled a wide range of applications for our customers.Successful transcriptions will now also include an alignment field, which will contain an array of time-aligned words (in the same order as the transcript), where each entry in the array has the following values:
word: The word in question
start: timestamp in the audio file at which this word begins
end: timestamp in the audio file at which this word ends
confidence: The confidence for this word’s timestamps
We are excited to see what developers decide to build using the alignment. We’ve seen customers already build custom captioning, simultaneous text-and-video editing, and more. Check out our docs to learn more! And you can sign up for an account below, and we’ll get you started with 5 free API requests!