Read.ai to Linear

Turn Read.ai meetings into Linear issues

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 with acceptance criteria, priority and an estimate. Nothing is created in Linear until you approve it.

How it connects

Read.ai: OAuth. You authorise Spectr from Read.ai's consent screen; Spectr refreshes the connection itself and never asks for a password. Linear: OAuth. You authorise Spectr from Linear's consent screen and choose the team. Tokens rotate on every refresh and Spectr handles that itself.

Before you start

No plan requirement. Connections are configured per project, and every credential is encrypted at rest.

A backlog that stays honest after publish

Publishing is the easy half. Spectr reads each Linear issue's state back on a schedule, 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.

What Spectr reads from Read.ai

Meeting summary: Read.ai's own summary is imported as the leading section, so the most condensed account of the call is what the model reads first.
Speaker-labelled transcript: The full transcript with speaker turns preserved, so a requirement can be traced back to who raised it.

What Spectr writes to Linear

Issues, only after approval: Nothing reaches Linear until a person approves it in review. You can edit a story inline first - title, description, acceptance criteria, priority, estimate, labels - and publish the corrected version.
Priority, labels, estimates and assignee: Mapped onto Linear's own fields. Later edits in Spectr sync across, so a story corrected after publish does not leave a stale issue behind.
Parent and sub-issue nesting: A spec-sheet task that generates several stories publishes as a parent issue with the rest nested beneath it, rather than as a flat list that loses the grouping.

A person approves everything before it is published

Spectr generates specs and stories, then stops. Every story goes to a review page where you approve it, edit it inline, or reject it - individually or in bulk. Only approved stories reach an issue tracker. There is no auto-publish setting to switch on, because a backlog nobody read is not a saving.

Setting it up

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 writes a story per item.
Review the generated stories - approve, edit inline, or reject - then publish the approved ones to Linear.