Strong measurement evidence

Your set

Thursday late show

8.1 minutes of your set, measured laugh by laugh.

4.8laughs per minute

How we counted

How solid is this number?

39 laughs ÷ 8.1 min = 4.8 · 2 maybe-laughs kept out

Heard in the room20clear crowd audio

Transcript-backed22a laugh in the transcript

Pauses (not counted)5kept for review

Of your set8.1mof 9.0m recorded

Strong measurement evidence. Most of these laughs were heard clearly in the room. Use the trend to compare sets you recorded the same way.

Laughs392 more to check below

Average laugh2.7show long they held, on average

Biggest laugh7.2syour longest of the night

Typical roar58/100Mid · relative to this set

Clip these

Your 3 biggest laughs

The strongest moments of the set — the ones worth cutting into a clip

3:36

7.2slaugh

Near this set's peak

Heard in the room

“That is not a family group chat. That is a hostage negotiation with birthday GIFs.”

crowd-audio burstspeech pausetranscript laugh marker

8:17

6.1slaugh

Near this set's peak

Heard in the room

“My smartwatch congratulated me for standing up. At my age, honestly, fair.”

crowd-audio burstspeech pausetranscript laugh marker

1:36

5.8slaugh

Near this set's peak

Heard in the room

“I said, if the algorithm knows me that well, it should at least pay half the rent.”

crowd-audio burstspeech pausetranscript laugh marker

Moment by moment

Your set, reaction-tiered.

1:36Bankerstrongest response

…if the algorithm knows me that well, it should at least pay half the rent · 15-word setup

5.8s detected

2:13Workhorseshort response

…airport people clap when the plane lands like the pilot just parallel parked · 13-word setup

2.6s detected

2:38Hitterclear response

…I told the barista my name and she still spelled it like a ransom note · 15-word setup

3.7s detected

3:36Bankerstrongest response

…that is not a family group chat, that is a hostage negotiation with birthday GIFs · 15-word setup

7.2s detected

5:00Reviewlong response gap

…the bit about my gym membership ran 46 seconds without a detected response · 13-word setup

46s response gap

6:28Hitterclear response

…my landlord calls it 'cozy' — cozy is a word for small that pays no rent either · 17-word setup

4.9s detected

8:17Bankerstrongest response

…my smartwatch congratulated me for standing up — at my age, honestly, fair · 13-word setup

6.1s detected

Before this set’s strongest detected responses, the machine transcript averaged ~14 words. Verify the boundaries before treating that as a writing pattern.

Tiers are automated and set-relative. They classify detected response duration—not writing quality, audience intent, or whether a joke is proven across rooms.

Laughs you might’ve gotten

Did we miss any?

A second listen · kept out of your numbers

Moments the main count may have missed.

A second, local audio model thought it heard laughter here. These are leads, not confirmed laughs — so they stay out of your LPM, grades, and trends until you check them.

Check 13:081.9s · not counted
Check 27:272.3s · not counted

Listen before you trust it: applause, music, and room noise can sound like laughter to a machine. This panel only stores timing, never extra joke text, and can’t change the numbers above.

Laughs you might’ve stepped on

Did you talk over a laugh?

Where a laugh overlapped your next line

3moments to check

You got the laugh — did you give it room?

At these timestamps a laugh ran into your next words. Sometimes that’s stepping on it early — but a tag, crowd work, a close mic, or loose transcript timing can look the same. Listen before you rework the bit.

5.9s overlap8% of your laughsA nudge not a grade

012:513.1s laugh72% overlapCheck your recording
025:122.4s laugh65% overlapCheck your recording
037:102.0s laugh55% overlapCheck your recording

We keep this careful: a moment only shows up when the audio, your speech timing, and a laugh marker all line up. It stores timing only — never extra joke text — and never touches your LPM.

Unlocked this set

Achievements

+75Laugh Score

Hat TrickThree or more Bankers in a single set.

On the RiseYou beat your previous set's LPM.

Personal BestA new all-time LPM high.

See your whole trophy case

Your set, start to finish

Laugh timeline

Taller = longer laugh

5 pauses kept for review — not counted as laughs.1:16 · 3:22 · 5:00 · 6:51 · 8:26

Set #6 · your trajectory

Are you getting funnier?

This set4.8LPM

vs last set▲ 0.64.2 → 4.8

Your best4.8LPM · same detector

Career Bankers14your biggest laughs, all-time

Fair-comparison note: mic placement, room, and crowd size all move the number. Compare sets you recorded the same way — and we only line up sets measured by the same detector.

🔒 Analyst

6 sets tracked — and counting.

Analyst charts every set over time, follows your recurring bits night to night, and shows you which ones are growing and which to rest. Turn one set into a trajectory.

See your Analyst trajectory

Transcript · check before you quote it

Auto-transcription mishears punchlines, names, and crowd noise. It’s here to help you navigate — it’s not a word-for-word record.

…so I download the meditation app, right, and it opens with a notification: 'You haven't meditated in 14 days.' That is not mindfulness, that is my mother with a subscription model. And I said, if the algorithm knows me that well, it should at least pay half the rent. [laughter] My landlord calls the place cozy. Cozy is a word for small that pays no rent either. [laughter] I fly home for the holidays, the whole plane claps when we land, like the pilot just parallel parked a bus…

What to do with this

Turn it into your next set.

Laughs per minute (LPM)

Your laughs divided by the minutes we analyzed. It’s most useful as your own trend across sets you recorded the same way — not as a universal score.

Your tiers → what to work on

Banker, Hitter, and Workhorse rank how long each laugh held. Review flags a long stretch with no laugh. None of them grade the writing — that’s your call.

Length, roar & setup

Length is how long a laugh held. Roar is scaled within this set, so your loudest is always 100. Setup counts come from the transcript, so eyeball them.

How sure we are

Heard in the room is the strongest. Transcript-backed is machine-read. Recovered laughs (from pauses you talked over) are counted but least certain — verify them. Plain pauses stay out of the count.

Did we miss any? → check the tape

A second listen can flag laughs the main pass missed. Those stay uncounted until you confirm them.

Talked over a laugh? → give it room

Shows up only when the audio, your speech timing, and a laugh marker all agree. It points you to the tape — it doesn’t decide whether a tag or riff was intentional.

Do next: clip your top three, listen back to one flagged moment, and record your next set the same way so the comparison’s honest. Watch the pattern in Analyst.

Straight with you

We count laughs — and we won’t fake them.

A laugh counts when the room backs it up: clear crowd audio, or a transcript marker. Turn on pause recovery and we’ll also count laughs you talked over when a second laughter detector hears them — those are labeled “recovered” because they’re less certain (the detector can mistake applause or noise for laughter, so verify them). Plain pauses and unconfirmed leads stay review-only. It’s automated measurement — not a verdict on the room, and not a grade on your writing.

Private processor · detector 2.0.0 · transcript model whisper.cpp-small.en

Analyze your set →