Meeting sources
Read.ai records, transcribes and summarises your meetings. Connect it and any of those meetings becomes a spec sheet: requirements, bugs, decisions and action items, each one pointing back to the meeting it came from, with a draft story for every requirement and bug waiting for your review. Read.ai meetings sit next to Fathom and Granola imports in the same project, so using two note-takers does not leave you with two backlogs.
How Read.ai fits in
A call is imported from Read.ai. Spectr picks out a requirement, a bug, an action item and an out-of-scope ask, and drafts a story and a bug with acceptance criteria. A person approves both, they are published to the team's tracker (Jira, Linear, or Shortcut), and the requirements, scope log and project memory update from the same call.
OAuth. You authorise Spectr from Read.ai's consent screen; Spectr refreshes the connection itself and never asks for a password.
A Read.ai account that can approve the OAuth request. Spectr does not require a particular Read.ai plan.
From the project in Spectr, open Integrations.
Choose Read.ai and click Connect. You are redirected to Read.ai to authorise access.
Approve the request. Spectr stores an encrypted token and refreshes it automatically.
Click Import meeting and pick from your recent Read.ai meetings, optionally filtered by the project's keywords against each title and summary.
Process, review, and publish the stories you approve.
Anything else? Email hello@crowdlinker.com and a person will answer.
Yes. Meeting sources are not exclusive - a project can have all three connected and import from whichever recorded the call.
No. Read.ai access tokens are short-lived, so Spectr refreshes them automatically whenever it uses the connection. You only reconnect if you revoke access on Read.ai's side.
Spectr imports the text of a meeting from Read.ai: the summary and the speaker-labelled transcript. It never imports audio or video. The text is stored encrypted on AWS in the US and used only inside the project you imported it into, and Spectr does not train any AI model on it. Deleting a meeting in Spectr archives it; to have it removed completely, email hello@crowdlinker.com.
Use case
Import a call, get a draft backlog, approve what is right
Import a Fathom call and get structured specs and stories from its notes, action items, and transcript
Native Granola import - no Zapier, no scripts - straight through to Jira, Linear or Shortcut
Import a Fireflies meeting and get structured specs and stories from its recap, action items, and transcript
Publish stories as Linear issues and keep their status and labels in sync
Publish stories into a Shortcut team and read their workflow state back
Jira