Pitch and pace, second by second
8:24 · 4 pausesYour pitch movement, words per minute and every pause on one timeline. Hover any peak to see the moment.
7-day free trial · cancel anytime
Upload or record any talk. In about three minutes you get an evaluator's report on your fillers, pacing, vocal variety and structure, with the three changes that will matter most.
What we measure
Four things you can act on. Each one scored, timestamped and explained in plain language, never a wall of numbers.

Every um, uh, like and you know, counted and timestamped to the second.
23in 8:24
Words per minute across the talk, and where your deliberate pauses landed.
148words / min
Pitch and energy. Are you landing emphasis, or holding one note?
2.4octaves
Your opening, your signposts, and whether the close really closes.
5/5tight close
How it works
An MP3, WAV or M4A of any talk up to twenty minutes, or record straight from your browser.
5 seconds
Transcription, an acoustic pass and an AI evaluator run side by side, not one after another.
About 3 minutes
Scores across eight categories, a pitch-and-pace timeline, rewrites and your top three actions.
A 90-second read
Beyond the score
Your pitch movement, words per minute and every pause on one timeline. Hover any peak to see the moment.
Phrasing edits pinned to the second they happened, with a line on why the new version lands.
What you said · 0:34
“I think this is kind of an important point, you know, that we should sort of pay attention to.”
Try instead
“This is the point. Pay attention to it.”
Why it works. You're at the climax of the open. Every hedge tells the room you don't quite believe it either.
See everything a real upload returns.
Scorecard, top three actions, every rewrite, the live chart and the numbers. Two full sample reports, no sign-up.
Questions
Anything else? Use the feedback button in the corner. A real person reads every message.
No. Audio is kept only while your report is being generated, then deleted. We keep the report itself so you can come back to it from your dashboard; you can delete it at any time.
English transcription is the most accurate today. We can analyze most major European languages, but the rubric prompts are tuned for English speech-coaching conventions for now.
Up to twenty minutes per upload, or 100 MB of audio, whichever you hit first. Most talks under fifteen minutes return a report in about three minutes.
A single adaptive-thinking Claude Sonnet call handles synthesis; Deepgram does transcription; Parselmouth and librosa handle the acoustic pass.
Every plan starts with a 7-day free trial. We ask for a card up front, but you're only charged after the trial and you can cancel any time before then. After that it's a simple monthly or yearly subscription for unlimited analyses.
Yes. You sign in so your reports stay together across devices and your subscription follows you. Start the free trial, upload a recording, and your report is saved to your dashboard.
Unlimited reports, free for seven days. Then €5.83 a month, billed yearly, or €12.99 monthly. Cancel any time before the trial ends and you won't be charged.