Read.ai to Linear
Read.ai gives you the meeting. Linear is where the work lives. Spectr connects both and does the writing: it reads the summary and transcript, separates out requirements, bugs and decisions, and drafts a Linear-ready story for each requirement and bug with acceptance criteria, priority and an estimate.
How it works
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 Linear, and the requirements, scope log and project memory update from the same call.
Two OAuth approvals and nothing to paste: one on Read.ai, one on Linear, after which you pick the team in Spectr. Spectr refreshes both tokens itself whenever it uses them.
No upgrade needed on Read.ai or Linear. Settle which single Linear team owns this project's work, because that is where every approved issue goes.
Publishing is the easy half. Whenever you refresh story status, Spectr reads each Linear issue's state back, counts a cancelled issue as cancelled rather than folding it into done, and syncs label and assignee changes back onto the story. That same data feeds the budget forecast, so a story marked done in Linear moves a number a client will eventually see. Which is only safe if the sync is accurate rather than optimistic.
Read.ai's summary is read first, then a transcript that keeps each speaker's turns. On a call with a client, a designer and two engineers, that is how the model knows who asked for what.
If half the team records with Read.ai and the rest with Fathom or Fireflies, every import lands in the same Spectr project and feeds the same Linear team.
Stories of a task the spec marks as a parent are created in Linear as sub-issues of one parent issue, so the reason they exist travels with them instead of being split across unrelated issues.
In Spectr, open the project you want to connect and go to Integrations.
Choose Read.ai, click Connect, and approve access on Read.ai. Spectr refreshes the token from then on.
Choose Linear, click Connect, and authorise on Linear.
Select the Linear team new issues should be created in.
Import a meeting from Read.ai. Spectr gathers project context, extracts a structured spec, and drafts a story for each requirement and bug.
Approve and publish the drafts. From then on Spectr reads each Linear issue's state back, so done, cancelled and in progress all show on the story.
Anything else? Email hello@crowdlinker.com and a person will answer.
No. Read.ai's built-in task integration is Jira, and Zapier has no Read.ai-to-Linear template. Spectr connects to both Read.ai and Linear over OAuth.
Yes, and it tracks each destination separately - the story is only done when every tracker it was published to reports it done.
Use case
Import a call, get a draft backlog, approve what is right
Connect Read.ai over OAuth and mix its meetings freely with Fathom and Granola in one project
Publish stories as Linear issues and keep their status and labels in sync
