Overview
There are three captioning/transcription tools that should be considered when using Zoom meetings and webinars. Based on your specific need, this guide can assist with the process of finding the right tool for your audience. The transcription tools include:
- Live (auto-generated) transcription
- Communication Access Realtime Transcription (CART)
- Audio transcription for cloud recordings
Live (Auto-Generated) Transcription
Live transcription uses automatic speech recognition (ASR) to caption meetings/webinars in real time. (This feature is unavailable in Breakout Rooms and Zoom on Linux OS.)
Helpful for: Hosts interested in enhancing the general accessibility of their meeting in real time for the benefit of participants, such as:
- Hearing individuals who benefit from audio prompts.
- Individuals who speak English as an additional language.
- Situations to compensate for low audio quality and enhance understanding.
Refer to Getting Started With Live (Auto-Generated) Transcription in Zoom for steps on enabling and using live transcription in Zoom.
Note: Currently, live transcription only supports English, and the accuracy of the feature depends on many factors, such as background noise, volume and clarity of the speaker’s voice, and the speaker’s lexicon/dialect. External microphones (separate from your laptop) can greatly improve audio quality, and speakers are encouraged to use one.
Communication Access Realtime Transcription (CART)
Communication Access Realtime Transcription (CART) involves human transcription in real time while someone is speaking or a video is playing. Most deaf and hard-of-hearing individuals require the level of accuracy that CART provides.
Zoom supports professional CART providers through the built-in “Live Transcript” feature, allowing a meeting participant to share captions through the platform. When this feature is enabled for a meeting/webinar, captions can be typed directly into Zoom or added to Zoom via an integration with a third-party software or service.
CART providers are trained to:
- Turn live audio into accurate captions in real time.
- Incorporate specialized terminology and proper names.
- Infer the right words and spelling from context.
- Compensate for noise and a range of voices.
Helpful for: Hosts who know they have participants in need of real-time transcription and/or are required to provide ADA-compliant accommodations for deaf and hard-of-hearing individuals.
Refer to Getting Started With Third-Party (CART) Captioning in Zoom for additional information on CART providers at the University of Michigan and steps on enabling and using CART transcription services in Zoom.
Audio Transcription for Cloud Recordings
Audio transcription for cloud recordings enables captions to be added to the meeting/webinar recording after it has concluded. If you require accurate transcriptions, we recommend using this option within Zoom to review and edit recordings and their transcripts before making them available to your audience.
Helpful for: Hosts who have used some form of real-time captioning and/or whose content is to be made available to individuals after the meeting/webinar has ended, such as:
- Deaf and hard-of-hearing individuals.
- Hearing individuals who benefit from audio prompts.
- Individuals who speak English as an additional language.
- Situations where transcription must be 100% accurate. (This will require editing.)
If audio transcription for cloud recordings is not already enabled, learn how to enable it on your U-M Zoom account.
Refer to Zoom Support to learn more about managing, editing, and sharing audio transcripts, as well as steps on displaying transcripts as closed captions on cloud recordings.
Related: MiVideo, U-M’s cloud-based media streaming service, also allows file owners to order, edit, and delete captions for audio and video files, including Zoom recordings. If long-term retention (i.e., more than 150 days) of cloud recordings and their audio transcripts is needed, this is a great resource.