Fireflies.ai to Jira

Turn Fireflies.ai meetings into Jira issues

Fireflies gives you a recap, a set of chaptered bullets and a paragraph of action items. Jira needs something different: a properly typed issue, in the right project, with acceptance criteria someone can work from and an estimate you can plan around. Spectr is the bit in between. It reads the meeting, pulls out a structured spec, drafts a story per item, and publishes only what you approve.

How it connects

Fireflies.ai: API key. You generate a key in Fireflies under Integrations and paste it into the project you want to connect. Jira: 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.

Before you start

No paid Fireflies plan is required - the API is available on their free tier. What the key can see is what Spectr can import: a key made by a team admin covers that team's meetings, a personal key covers only your own.

The action items Fireflies buries in prose still reach Jira

Fireflies captures action items, and can push them into Jira itself - but what its API hands a third party is one block of text grouped by assignee rather than a list, so anything reading it the obvious way loses the structure and then the items. Spectr parses the assignee and the point in the recording back out of that block before anything is extracted, so each one is a real item the spec has to account for. From there it sorts each item into a Story, Bug or Task using your project's own issue types, matches priority to your scheme, converts the description into Jira wiki markup so headings look like headings, and nests several stories from one requirement as real Jira sub-tasks.

What Spectr reads from Fireflies.ai

Recap and chaptered bullets: Fireflies renders the same meeting eight different ways. Spectr stores two of them - the prose recap and the chaptered bullets that keep names, numbers and timestamps - and reads them ahead of the transcript. The other six are shorter restatements of those two, and sending them would spend prompt budget saying the same thing three times.
Action items, recovered from prose: Fireflies captures action items but hands them over as one free-text block grouped by assignee, not as a list. Spectr parses the assignee and the point in the recording back out of it, so Fireflies action items land in the same high-precision section Fathom's structured ones do rather than being buried in summary text.
Full transcript: The complete speaker-labelled transcript, up to a 200,000-character budget for a single meeting - large enough that the whole of almost any meeting is sent rather than cut off. A meeting Fireflies never summarised is still imported on its transcript alone.

What Spectr writes to Jira

Issues, only after approval: Nothing reaches Jira until a person approves it in Spectr's review step. Descriptions and acceptance criteria are converted from markdown to Jira wiki markup on the way in, so headings and lists render as headings and lists instead of raw syntax.
Type, priority, labels and estimates: Feature maps to Story, bug to Bug, chore and spike to Task - resolved against the project's real issue types. Priority maps by name against your instance's own priority scheme. Labels are slugified because Jira rejects spaces in them. Estimates use your site's story-points field when it exists.
Parent and sub-task nesting: When a spec-sheet task generates several stories, Spectr creates one parent issue and nests the rest as real Jira sub-tasks. If the project has no sub-task type, it publishes flat rather than failing.

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.
In Fireflies, create an API key from the Fireflies API page under Integrations.
Choose Fireflies, paste the key, and let Spectr validate it.
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 Fireflies.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 Jira.

Frequently asked questions

Do the Jira issues get created automatically after a meeting?

No. Spectr generates the stories, then waits. You review them - approve, edit inline, or reject - and only approved stories are published to Jira.

Does this need a paid Fireflies plan?

No. Fireflies exposes its API on the free tier, so a free account can connect. The one thing to get right is whose key you use: a key only ever returns the meetings its own owner can see.

Does Jira status come back into Spectr?

Yes. Spectr reads each published issue's status category on a schedule and rolls it up onto the story, which is also what feeds the budget projection.

Use case