Fellow can enhance your in-person meetings by helping your team prepare, stay aligned, and follow up effectively. Whether your team is fully in-office or working in a hybrid setup, the AI Notetaker ensures that key decisions and actions items are captured so nothing falls through the cracks.
How does the Note Taker benefit in-person meetings?
Using Fellow for in-person meetings allows your team to prepare ahead of time by outlining the meeting structure and supporting resources in advance. This encourages collaboration and accountability before the meeting even begins.
During the meeting, the AI Note Taker records key decisions and action items in real time, so your team can stay focused on the conversation rather than manual note-taking. After the meeting, you can send a post-meeting recap or Note Taker Recap to ensure everyone leaves on the same page.
How does the Note Taker benefit in-person meetings?
When using the AI Note Taker for in-person meetings, each attendee must join the video call from their own device. If multiple attendees share a single device, the AI Note Taker will not be able to differentiate between speakers in the meeting transcript.
Voice Detection and Uploads
The AI Note Taker uses voice detection to identify and distinguish between different speakers during a meeting. For the best results, each participant should join the call from their own device in a quiet environment. Background noise, crosstalk, or multiple people speaking into the same microphone may reduce the accuracy of speaker attribution in the transcription.
If speakers cannot be identified, generic labels will be assigned, such as:
West Conference Room - A, West Conference Room - B
Jamie Smith - A, Jamie Smith - B
Fellow can automatically assign names based on past meetings, but only for users in your workspace with voice recognition enabled. Please note that this feature does not apply to external attendees.
Fellow supports uploading audio and video files directly to a meeting note, where the AI Note Taker will process the recording and generate a transcript, summarizing the meeting just as it would for a live session.
Speaker Identification: Voice detection on uploaded recordings works best when speakers are clearly audible and do not overlap. For optimal results, use a high quality microphone placed centrally in the room.
Editing Speaker Labels: If a speaker is not automatically identified or is mislabeled (pictured below), you can update their label in the transcript.
To update these to the correct speaker, you'll need to:
Click on a speaker's name in the transcript.
Select a different name from the dropdown list or type a custom name.
Choose whether to apply this change to all instances of that speaker.
Save your changes to update the transcript.
