Issue trackers
When user stories are written from memory after the meeting, some come out wrong and some never get written. Spectr drafts them from the meeting itself. Connect a Jira Cloud site, pick the project they land in, and every story you approve becomes a real Jira issue with its description, acceptance criteria, type, priority, labels, estimate and assignee already set. A status refresh then reads each issue's status back, so what Spectr thinks has shipped matches what actually has.
How Jira fits in
A call is imported from a note-taker (Fathom, Granola, Read.ai, or Fireflies.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 Jira, and the requirements, scope log and project memory update from the same call.
OAuth 2.0 (3LO). You pick the Jira site on Atlassian's own consent screen. Spectr requests read and write access to Jira work plus read access to users, and refreshes the token itself.
A Jira Cloud site - Server and Data Center are not supported. New issues go to the one Jira project you pick for each Spectr project.
In Spectr, open the project and go to Integrations.
Choose Jira and click Connect. Atlassian asks which site to authorise.
Pick the Jira project new issues should land in.
Optionally set Story defaults - a default issue type and the status new issues should start in.
Generate stories from a meeting, review them, and publish. Each story in Spectr then links to the Jira issue it became.
Anything else? Email hello@crowdlinker.com and a person will answer.
Summary, a description carrying the acceptance criteria, issue type, priority, labels, assignee, and the estimate in your story-points field when the site has one.
No. The integration is Jira Cloud only, over Atlassian's OAuth 2.0 (3LO) flow.
Jira rejects labels containing spaces, so "Auth Flow" is published as "Auth-Flow". Spectr deliberately does not sync labels back from Jira, because un-slugifying them would guess at your data and sometimes guess wrong.
Spectr stores Jira's stable numeric id alongside the human key, so a rename or a project move does not break the link. The key and browse URL are backfilled on the next status refresh.
Use case
Draft stories with real acceptance criteria, then approve, edit or reject each one
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
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
Read.ai
Fireflies.ai