Skip to main content

​
Overview

The bridge call is where incidents actually get solved, and the first place that context is lost. Meeting Scribe joins the bridge automatically and preserves the call as a live, searchable, speaker-labeled record attached to the incident. Late responders catch up from the live transcript instead of interrupting the call. Transcripts flow straight into AI Summaries and retrospectives. Supported platforms: Zoom, Google Meet, Microsoft Teams, Webex, and GoToMeeting.

​
What You Get

During the call, the scribe joins as Rootly Scribe in the participant list, announces itself, then provides:
  • Live transcription, streamed back to Rootly in real time with speaker identification
  • Audio recording, and video where the platform supports it
  • Slack notifications in the incident channel when recording starts and when the transcript is ready
  • Live context for catchup, so /rootly catchup already knows what the bridge discussed
After the call, the incident’s Scribe tab holds the full speaker-labeled transcript, a Rootly AI meeting summary of the key points and decisions, and the optional video recording. Before storage, Rootly redacts 26 categories of sensitive personal data from every transcript in a language with PII redaction, from credentials to government IDs. Names, dates, and locations stay in the transcript. See Privacy and Security for the Scribe-specific handling boundaries.
The incident Scribe tab with the Rootly AI meeting summary and the speaker-labeled transcript

​
Setup

Set up Meeting Scribe from AI & Agents → Scribe. Connect a meeting platform there, then let the scribe join its calls.
1

Open the Scribe page

Go to AI & Agents, then select Scribe. With no platform connected, the Platforms section reads Connect a meeting tool.
2

Connect a platform

Select Select a tool, then choose Zoom, Google Meet, Microsoft Teams, or Webex. Rootly takes you straight to the platform’s sign-in, then back to the Scribe page. Connecting from the integrations catalog works too.
3

Let Scribe join the calls

After you connect Zoom or Google Meet, Let Scribe join calls? opens. Select Turn on Scribe for . This also turns on call creation for incidents, so the scribe has a call to join. Select Not now to change nothing. A platform that still reads Scribe isn’t joining calls yet has a Set up button that opens the same dialog.
Microsoft Teams and Webex have a Join automatically toggle instead of the dialog. A platform you manage with your own meeting workflows reads Recording for is managed in your own workflows. Turn on Scribe joins the call in the create-meeting action of those workflows.
Prefer the Rootly-generated meeting URL. When an incident starts, Rootly creates the meeting room and pins the link in the incident’s Slack channel; the scribe is created automatically for that meeting. You can also attach a different meeting URL to the incident and the scribe will target it, but the Rootly-generated link works with zero extra steps.

​
Platform Requirements

Follow Zoom → Installation if you connect from the integrations catalog. On the Scribe page, turn on Record without host approval (recommended). The scribe then joins with a Zoom join token that skips the waiting room, and starts recording without waiting for the host to approve. If the row reads Reconnect Zoom to approve the permissions this needs, disconnect and reconnect Zoom.Zoom-specific issues live at Zoom Meeting Scribe Troubleshooting.

​
Limits and Scribe Behavior

​
Recording Sessions

Sessions appear chronologically in the Scribe tab, each with its own transcript, summary, and optional video. Session numbers are per platform, so a Zoom bridge and a Google Meet bridge on the same incident each count from 1. Every session carries the same set of controls, available from the Scribe tab and from Slack:
A recording session card in the Scribe tab showing Session 1 in progress, with the overflow menu open on Pause, Stop, and Remove

Session actions live behind the ... menu on the session card

​
Re-inviting the Scribe

The scribe does not rejoin on its own once it has left, so putting it back on the call is always a deliberate action. Every route below is held to the same permission: update on the incident, the same one that lets you edit the incident itself.

​
Ask @Rootly

The quickest route, and the one that works from wherever the conversation already is. Mention @Rootly in the incident channel and ask it to re-add the meeting scribe.
A responder asks @Rootly to hop back into the bridge, and Rootly AI replies that the meeting bot was re-added to the Google Meet call as session 6 and is joining shortly
Rootly AI works out which bridge you mean, confirms the platform, and names the new session number in its reply. That number tells you the rejoin landed and how much of that platform’s 10-session budget the incident has used. When the incident carries links for more than one platform and the choice is genuinely ambiguous, it asks which one you want rather than guessing.
This route needs Rootly AI in Slack enabled for your workspace, and it runs in the incident channel only. It can only do what you can do, so it is capped at your own Rootly permissions like every other Rootly AI action.

​
Other routes

1

Open the incident's Scribe tab

Each connected platform gets its own card with its own session list.
2

Press the invite button

It reads Invite Scribe before the first session for that platform and Start New Session after. Greyed out and reading Cannot Start Session means something is blocking the re-invite, covered in When re-invite is blocked.
3

Confirm

Rootly confirms that a new session will be created and that previous transcripts are preserved. The new session appears in the list and the scribe joins shortly after.
The incident Scribe tab with a Google Meet card, an Invite Scribe button in the top right, and a Join Meeting link

The Scribe tab before the first session on a Google Meet bridge

​
Retrying a session that captured nothing

Everything above starts a new session, numbered one higher than the last, with earlier transcripts left untouched. That is what re-invite means almost everywhere. There is a second, narrower behavior for a session that ended without recording anything, such as one that timed out in a waiting room or was refused recording permission. Retrying reuses that session instead of adding another, so a dead row does not sit in the session list forever. Find that session’s card in the Scribe tab and press its own Invite Scribe button. Sessions that did record show no such button. Over the API, the same thing is POST /v1/meeting_recordings/{id}/reinvite_bot, which is rejected if the session holds recording data, so it cannot overwrite a transcript.
Linux

​
When re-invite is blocked

An invite that never reached the recording service at all does not count against the 10-session cap, so a failed attempt does not cost you a session.

​
Multilingual Support

The scribe detects the dominant spoken language on every call and transcribes in it. The transcript is in the detected language, and the Rootly AI meeting summary is in English.
Very short calls, and calls that switch between languages, give the scribe less to go on, so the detected language may be less reliable.
Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Norwegian Nynorsk, Occitan, Panjabi, Pashto, Persian, Polish, Portuguese, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Swiss German, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, and Yoruba.

​
Languages With PII Redaction

Rootly redacts sensitive personal data from transcripts in these languages: Afrikaans, Arabic, Belarusian, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Georgian, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Khmer, Korean, Latvian, Lithuanian, Luxembourgish, Malay, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Turkish, Ukrainian, and Vietnamese. Transcripts in any other language are stored without PII redaction.

​
Scribe Settings

Controls for the whole organization decide whether the scribe runs at all, whether transcripts name speakers, and how long Rootly keeps them. They live in one place, AI & Agents → Scribe. A Platforms section on the same page sets up each meeting platform. Owners and admins can change these settings. Other users who can open AI & Agents see the page read-only, with the note Only owners and admins can change these settings. Rootly records every change, with the old and new value, in the audit log under Scribe Settings.

​
Enable Scribe

Enable Scribe, in the General section, is the off switch for the scribe across your organization. It’s on by default. Turn it off and the scribe doesn’t join or record any meeting, whatever the integration and workflow settings say. While it’s off:
  • Incident call workflows still create the meeting, but skip the scribe. The workflow run records Rootly transcript bot skipped: Scribe is turned off for this organization.
  • Every invite and re-invite route is blocked: the Scribe tab, Slack, @Rootly, and the API. Session-complete messages in Slack arrive without a Start New Session button, and the API returns Scribe is disabled for this organization.
  • The incident’s Scribe tab shows a Transcribe your meetings with Rootly Scribe banner.
Turning the scribe off doesn’t delete anything. Existing recordings and transcripts stay on their incidents. The scribe detects the spoken language automatically. See Multilingual Support.

​
Platforms

The Platforms section lists Zoom, Google Meet, Microsoft Teams, and Webex. With none connected, it shows Connect a meeting tool and a Select a tool menu. Once one is connected, connected platforms come first and the others collapse under Other tools. Each connected row shows the controls below. A row can also read:
  • Not connected, with a Connect button.
  • Not available, when the platform isn’t configured for your environment.
  • Call creation for is off because your team uses its own meeting workflows, with an Open workflows link. Turn on Scribe joins the call in those workflows, or turn on call creation on the integration page. Rootly doesn’t turn call creation on for you, because that would create duplicate calls.
  • You don’t have permission to change this platform’s settings, when you can edit Scribe settings but not that integration.
Teams and Webex settings are saved in the platform’s linked workflow. If Terraform manages that workflow, Terraform can overwrite the Join automatically setting. The Zoom and Google Meet integration pages show a read-only Scribe card with a Manage in Scribe link.

​
Anonymous Speakers

Some teams want the record of what was said without a record of who said it. With Anonymous speakers on, in the Privacy section, Rootly stores speakers as Responder A, Responder B, Responder C instead of their names. Rootly swaps in the labels before it saves the transcript, so speaker names never reach the Scribe tab, the API, Liquid variables, Slack posts, or Rootly AI.
Anonymous speakers changes speaker labels only. The scribe doesn’t remove names that people say aloud, so they can appear in transcripts.
No Privacy section on your Scribe settings page means anonymous speakers isn’t enabled for your organization. Contact your Rootly account team.

​
Transcript Retention

By default, Rootly keeps transcripts until someone deletes them from the Scribe tab. Transcript retention, in the Data section, deletes them for you a set number of days after the meeting ends: Off, 7 days, 30 days, 60 days, or 90 days. The clock starts when the meeting ends, or when the recording is created if the meeting never ends. Retention applies to existing recordings as well as new ones, so turning it on can delete transcripts you already have.
Retention deletes transcripts permanently. Rootly can’t recover a transcript, summary, or video recording once retention has deleted it.
Turning retention on, or choosing a shorter period, opens a Delete older transcripts? confirmation. It shows how many existing transcripts will be past the new period when deletion starts, and the date it starts. Select Confirm to save, or Cancel to keep the current setting. Deletion starts 24 hours after you confirm. To undo a mistake, set retention back before then. A longer period, or turning retention off, saves straight away with no confirmation, and only affects transcripts that still exist.

​
What Retention Deletes

Retention deletes the transcript, the meeting summary, the video recording, and Recall.ai’s copy of the media. The recording session itself stays, with its platform, start and end times, and duration. In the Scribe tab, the session reads Transcript deleted by retention policy on followed by the date. In the API, the session comes back with:
  • transcript_deleted_at set to when retention deleted it
  • An empty transcript array when you request include=transcript
  • A null transcript_summary and video_url
Until then, transcript_expires_at shows when the transcript, summary, and video become due for deletion. It’s null when retention is off and once the transcript is gone.

​
What Retention Can’t Delete

Retention covers the copies the scribe stores. It can’t reach copies made outside the scribe:
  • Workflow outputs
  • Timeline events rendered from Liquid variables
  • Slack threads
  • Large language model (LLM) traces
Rootly also keeps AI outputs built from transcripts, such as AI incident summaries and retrospective content.

​
Recording Retention

Recording retention, in the Data section, sets how long Recall.ai, Rootly’s recording provider, keeps its copy of the audio and video after the call: Default, Delete after transcript, 1 day, 7 days, 30 days, or 90 days. It doesn’t change the transcript or a recording already stored in Rootly.
  • A period longer than your transcript retention is capped at the transcript retention period.
  • With anonymous speakers on, the setting reads Delete after transcript, and you can’t change it.
No Data section on your Scribe settings page means retention isn’t enabled for your organization. Contact your Rootly account team.

​
Privacy and Security

The short version:

​
Processing and storage flow

  1. Recall.ai joins the meeting and captures the audio and, where supported, video. With anonymous speakers on, it captures audio only.
  2. Recall.ai sends the audio to AssemblyAI with transcript PII redaction enabled. Rootly requests redaction for 26 categories of sensitive personal data before accepting the transcript for storage.
  3. Rootly stores the speaker-labeled transcript with the incident, redacted if it’s in a language with PII redaction. With anonymous speakers on, the labels are Responder A, B, C instead of names. If video recording is enabled, Rootly also attaches a copy of the recording to the Scribe session. Rootly sends the stored transcript through its managed model path to produce the meeting summary.
  4. AssemblyAI and OpenAI don’t retain the data after processing. Recall.ai media follows a separate Rootly-managed retention setting; some teams are configured to delete that provider copy after transcript processing, and Rootly always deletes it then for anonymized recordings. Deleting the provider copy doesn’t remove the transcript or an attached recording already stored in Rootly.
  5. With transcript retention set, Rootly deletes the transcript, summary, and video recording 7, 30, 60, or 90 days after the meeting ends. With retention off, the default, Rootly keeps them until you delete them from the Scribe tab.
Rootly requests redaction for account numbers, banking information, blood types, credit-card verification values, credit-card expiration dates, credit-card numbers, dates of birth, driver’s licenses, drugs, email addresses, gender and sexuality, healthcare numbers, injuries, IP addresses, medical conditions, medical processes, nationalities, passport numbers, passwords, ages, phone numbers, political affiliations, religions, US Social Security numbers, usernames, and vehicle IDs.Names, dates, locations, organizations, occupations, URLs, money amounts, events, languages, and general number sequences stay in the transcript so responders and Rootly AI can read service, vendor, region, and timing details.Rootly AI prompts built from the transcript still pass through outgoing prompt scrubbing, which removes email addresses, phone numbers, credit-card numbers, US Social Security numbers, IP and MAC addresses, and passwords embedded in URLs.
When Rootly AI uses an attached transcript as investigation or conversational context, the separate agent retention and processing boundaries apply. See Data Privacy for Rootly AI.

​
Troubleshooting

For platform-specific issues, start with the dedicated pages:

Zoom Troubleshooting

Record without host approval, waiting rooms, host controls, and Zoom-specific failure modes.

Google Meet Troubleshooting

Service account setup, admin console settings, and admission failures.
Check in order: Enable Scribe is on in Scribe settings; the meeting URL is attached to the incident (the pinned Rootly-generated link works out of the box; a manually added URL must be attached to the incident); the platform’s row on the AI & Agents → Scribe page reads connected, not Scribe isn’t joining calls yet or Call creation for is off; and the scribe is being admitted. Zoom without Record without host approval needs a human to admit it, and Google Meet Host management can hold it in the waiting room even with a service account.
One of the two timeouts fired. Either no one admitted the scribe within 10 minutes, or it got in and no responders joined within 5. Re-invite the scribe by whichever route is closest to hand, and turn on Zoom Record without host approval to prevent the first case.
Post-meeting processing takes a few minutes. Check the Scribe tab and refresh. Past 10 minutes with nothing, confirm the scribe actually recorded: there should be a Recording started event in the incident timeline.
The incident is probably carrying a personal meeting room or a manually generated link. The scribe is scoped to the meeting attached to the incident. Start a fresh meeting from the incident’s Slack channel, then re-invite the scribe.
Your team exceeded its monthly recording cap. Ask your Rootly admin to review usage or raise the limit.

Data Privacy for Rootly AI

How Rootly AI can use an attached transcript, including retention and processing boundaries.

AI Summaries

Where transcripts turn into summaries and catchups.

AI in Retrospectives

Bridge transcripts as retrospective source material.