Read.ai to Shortcut

Turn Read.ai meetings into Shortcut stories

Read.ai records and summarises. Shortcut tracks. Spectr connects to both and produces what neither can on its own: a structured spec from the meeting, plus a Shortcut story with acceptance criteria and an estimate for every requirement, bug and decision in it. You review the set before any of it is created.

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. Shortcut: API token. You create a token in Shortcut and paste it into the project, then pick the team and the workflow state new stories should land in.

Before you start

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

Search the meeting, then scope it

Read.ai's import list is searchable on title and summary, so finding the right call in a month of recordings means typing the feature name instead of scrolling by date. From there Spectr gives each item the right Shortcut story type and estimate, creates it in the workflow state you picked, and reads its state back afterwards so what is done in Shortcut shows as done in Spectr.

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 Shortcut

Stories, only after approval: Nothing reaches Shortcut until a person approves it in Spectr's review step.
Estimates, tags and assignee: Mapped onto Shortcut's own fields, with story type resolved from Spectr's feature, bug, chore and spike classification.

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.
In Shortcut, create an API token from your account settings.
Choose Shortcut, paste the token, then pick the team and the workflow state new stories start 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 Shortcut.