Smart Recording brings the power of Zoom AI Companion to cloud recordings, allowing you to organize your cloud recording into sections called smart chapters, get the key takeaways in a quick and digestible format through recording highlights, identify action items to take after the meeting or webinar with next steps, and even provide the host analytics on key meeting and conversation factors, including talk speed, talk-listen ratio, longest spiel (or monologue), filler word usage, and patience.. This feature is especially useful for long meetings and webinars – such as a lecture, brainstorming session, or company all-hands – where you may want to divvy up the recording for easier viewing.
To generate recording highlights, smart chapters, and next steps, you must have a cloud recording and audio transcript processed and available to view. You will receive email notifications when the recording and transcript are finished processing. These emails include links to view your recordings and transcript. Recording highlights, smart chapters, and next steps can be edited by the owner of the cloud recording (the host) or a user with permission to manage cloud recordings.
Zoom does not use any customer audio, video, chat, screen sharing, attachments, or other communications-like content (such as poll results, whiteboard and reactions) to train Zoom’s or third-party AI models.
This article covers:
Note: Editing or adjusting the transcript, smart chapters, highlights, and next steps requires the owner of the recording (host of the meeting), or a user with permissions to manage cloud recordings
Once the cloud recording and audio transcript have finished processing, you can go to the Zoom web portal to manage and edit the recording highlights, smart chapters, and next steps. In addition to managing your recording with Smart Recording, you can trim the recording, download the files, and more.
If enabled, Zoom AI Companion will highlight the most important parts of the session. You can manually adjust highlights as needed and can save highlights as separate files to cut unnecessary parts of the recording.
To the right of the cloud recording video, in the Audio Transcript panel, you can do the following:
You can also adjust highlights using the playback bar.
Cut unnecessary parts of the recording by exporting highlights and saving them to a new clip that you can view, edit, and share. If you share this video clip, viewers can only watch the recording highlights. This will also cut the associated files (audio and transcripts).
Note: The new video clip uses your account’s recording storage capacity.
When you’re ready to share the recording with viewers, you can either save the highlights to a new video clip so viewers can only view the recording highlights, or you can share the original recording with highlights. If you share the original recording, viewers can choose to watch either the highlights only or the full video.
If enabled, Zoom AI Companion will automatically group the recording into different sections with timestamps. You can click on a chapter to watch the part of the recording starting at that timestamp. Viewers who watch the cloud recording can see the smart chapters and next steps.
If enabled, Zoom AI Companion will automatically examine the end of the recording and look for cues to identify any next steps for you. You can keep the next steps as part of the recording, as well as the text out to others.
Next Steps are located below the Audio Transcript panel of the cloud recording view. You can do either of the following as needed:
If enabled, Zoom AI Companion can analyze and provide metrics on key factors in your meeting conversations, such as talk speed, talk-listen ratio, longest spiel (or monologue), filler word usage, and your patience in discussion. These metrics can be viewed when viewing a cloud recording after it has finished processing and is available for only the host and eligible account admins.
Metrics and analytics are provided for informational purposes and may contain inaccuracies. Results are not intended to be used for employment decisions or other comparable decisions. All recommended ranges for metrics are based on publicly available research.
This shows the average percentage of total time when the host was speaking. The talk-listen ratio of the host allows them to view the proportion of time they were actively speaking in a meeting and also how well the speaker is able to engage the participants.
Our research indicates that this ratio fluctuates based on the type of information conveyed in addition to the role and relationship of the speaker to their audience. For example, while conversations involving a senior executive or a more technical topic can require more air time from the speaker, that’s not always the case. It is clear that higher ratios indicate that the speaker is not allowing enough time for their audience to voice needs, concerns, questions, and suggestions, which is critical to productive conversations.
Note: How the talk-listen ratio recommended range is measured will differ based on the number of internal participants in the call
This shows the average number of words spoken per minute by the host. The host’s talking speed allows them to determine if they are talking too fast or too slow during meetings. Ideally, they should keep the talking speed within a specific range to help keep the meeting moving while still being understood. Based on this data, they can work to increase or decrease their talking speed to improve this meeting skill.
Talking speed tends to drop when the speaker is conveying highly technical information to improve comprehension. Research also suggests that “listenability” also increases when a speaker takes more frequent and longer pauses on average. Even more, reason to be sure you are breathing steadily when pitching to customers and prospects!
Recommended range: A talking speed between 110-160 words per minute.
This shows the average number of filler words used per minute by the host. Filler words, such as ah, um, and hmm, can indicate that the speaker needs to be more familiar and confident with what they are saying. Interestingly, studies found that using filler words excessively, as well as not using any filler words, can diminish a speaker’s credibility.
AI Companion tracks the number of filler words used every minute.
Recommended range: 0.6-3.0 filler words per minute (6-30 filler words per 10 minutes)
This shows the duration of the longest speech segment of the host. A spiel, or monologue, is being the only participant speaking for a length of time, which can discourage others from participating in the conversation, impact listener comprehension, and cause fatigue. This data can help hosts be more aware of how much time they are speaking at once and creating pauses for questions or comments.
The recommended maximum for a monologue varies, depending on the topic you are presenting on or question you are answering, but recent research suggests that stopping intermittently to ask questions boosts overall learning and retention in the educational sector.
Recommended range: Avoid monologues that last more than 2:30 minutes to increase the interactivity of the call, promote engagement, and lead to better sales outcomes.
Patience reflects how much time between a question and the respondent’s answer. This can indicate how much patience is given to other meeting participants, which can affect the discussion’s progress and outcome. This can help improve the ability to control the pace of conversations.
AI Companion measures patience in seconds.
Recommended range: Waiting between ½ and 1.5 seconds for the customer to respond.