Read.ai to Jira
Read.ai records the meeting and ties every line to a speaker. Jira wants a typed issue in the right project, with acceptance criteria and an estimate. Spectr turns the first into the second: it reads the summary and transcript, pulls out a structured spec, drafts a story for each requirement and bug, and creates the approved ones as issues your team can pick up.
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 Jira, and the requirements, scope log and project memory update from the same call.
Both sides use OAuth, so there are no keys to copy. You approve Spectr on Read.ai's consent screen and on Atlassian's, choosing the Jira Cloud site there, and Spectr refreshes both tokens itself whenever it uses them.
Spectr asks for no particular Read.ai plan. Jira has to be a Cloud site; Server and Data Center installs cannot connect.
Read.ai's transcript records who said what, and every line reaches Spectr with its speaker, so the model knows whether the client or your own team asked for each thing. On the Jira side, each story gets a real issue type from your project, priority matched to your own scheme, and sub-tasks under a parent issue where the spec marks a parent task.
The import list can be filtered by the project's keywords, matched against each Read.ai meeting's title and summary, so a month of recordings shrinks to the calls that are about this project.
Under Story defaults you can set an issue type, used when a story's mapped type does not exist in the project, and a status that new issues move to when the workflow allows it. The status list follows the workflow of the type you chose.
Spectr stores Jira's permanent numeric id next to the issue key. Move an issue to another project or rename it, and the link to the story survives; the new key shows up on the next status refresh.
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 Jira, click Connect, and pick the site on Atlassian's consent screen.
Pick the Jira project new issues should land in - and optionally a default issue type and starting status.
Import a meeting from Read.ai. Spectr gathers project context, extracts a structured spec, and drafts a story for each requirement and bug.
Approve the drafts and publish. Each issue gets the type its story maps to, moves to your starting status where the workflow allows it, and stays linked even if it is moved later.
Anything else? Email hello@crowdlinker.com and a person will answer.
Read.ai's integration turns one action item into one Jira issue, a click at a time, on its Pro plan and up. Spectr reads the whole meeting, drafts stories for its requirements and bugs with acceptance criteria and an estimate, and publishes the ones you approve together. Many teams use Read.ai's for quick follow-ups and Spectr for the backlog.
Yes. A project can have all three sources connected, and imports from any of them feed the same pipeline and the same backlog.
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 Jira issues, with sub-task nesting, and read their status back
