Analyzing highlights of call center recordings
In this guide, we will explore how AssemblyAI's API can help call and contact centers unlock valuable insights from their audio data, providing powerful and actionable information for enhancing their operations.
Step-by-step instructions
- 1
Create a new file and import the necessary libraries for making an HTTP request.
- 2
Set up the API endpoint and headers. The headers should include your API token.
- 3
Upload your local file to the AssemblyAI API.
- 4
Use the
upload_url
returned by the AssemblyAI API to create a JSON payload containing theaudio_url
parameter. - 5
Make a
POST
request to the AssemblyAI API endpoint with the payload and headers. - 6
After making the request, you will receive an ID for the transcription. Use it to poll the API every few seconds to check the status of the transcript job. Once the status is
completed
, you can retrieve the transcript from the API response, as well as the auto highlight results.
Understanding the response
The auto_highlights_result
key in the response contains a list of all the highlights found in the transcription text. For each entry, the results include the text of the phrase or word detected, how many times it occurred in the text, its relevancy score, and a list of all the timestamps, in milliseconds, in the audio where the phrase or word is spoken.
For more information about the API response, refer to the API reference
Conclusion
Adding AI to Conversation Intelligence tools can help you generate actionable summaries to speed up call review, generate insights, monitor for concerns, increase engagement, and more. Our AI summarization model has several customizable parameters that you can experiment with for other types of recordings.
To learm more about how to use AI summarization for call coaching, check out the AssemblyAI blog.