Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
Introducing Usage and Cost Tracking on Omnara Managed Agents transcript
Omnara · @OmnaraAI
Published September 23, 20261:409 views
Transcript analysisComputed from the caption text
Words
381
Runtime
1:40
Speaking pace
229wpm
Reading time
2min
229 words per minute, above the 201 75th percentile of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
Nana now tracks usage and cost for your agents. This is the organization view here. And up top you can see that we've got all of our totals. So that's cost, input tokens, output tokens, and how many model calls your agents have made. And underneath that, you could see that broken down by each model you're using. You can also filter this by date and by project. So if you want to see a certain month, you can or specific projects to see which one's spending what. And this is all available in the API as well. Each project has its own version of this page, too. and so does each profile. A profile
115 words, the words spoken in the first 30 seconds at 229 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 29 |
| Average words per sentence | 13.1 |
| Longest sentence | 36 words |
| Questions asked | 0 |
| Sentences containing a number | 0 |
Most used terms
- agent11
- agents6
- cost5
- usage5
- profile4
- model3
- projects3
- sub3
- sub agents3
- tokens3
- api2
- available2
Filler phrases
1 in total: basically 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
Audit this video's script
Run the check on the words above: where attention is likely to drop, with a rewrite for each weak line. The free check shows the scores and the one issue costing the most.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
No Script X-ray for this video: YouTube shows a Most replayed graph only once a video has enough views.
Transcript
Nana now tracks usage and cost for your agents. This is the organization view here. And up top you can see that we've got all of our totals. So that's cost, input tokens, output tokens, and how many model calls your agents have made. And underneath that, you could see that broken down by each model you're using. You can also filter this by date and by project. So if you want to see a certain month, you can or specific projects to see which one's spending what.
And this is all available in the API as well. Each project has its own version of this page, too. and so does each profile. A profile is basically the definition of an agent. And so every time something launches from it, that's a new agent. So if you've connected a profile to Slack, every thread starts a new instance. If you have a curron schedule, every run starts a new one. And this tab will add all of those up here, the agents tab.
So you can see what one bot that scheduled the job cost you overall. For example, let's go ahead and open up a single agent. You can see its usage right here in the sidebar. And if the agent handed off work to sub agents, which it did here, those are also counted as their own agent. So I can click into them and see how much usage they had. If I go back to the parent agent though, under usage here, I can make sure to include sub agents.
So I can see what the total cost of the agent including its sub agents were. You can also see pricing before you spend anything. So if we go to make a new agent, when you're picking the model for the agent, you can see the price per million tokens both for input and output show up right next to it. You'll see the same thing on the models page as well. And all of this is available in the API too. So there's an endpoint for the org, for projects, for each agent profile, and then for each agent itself.
And they all support the same filters for dates and for projects. That's usage and cost inara.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Working on a video like this one?
Free tools for your own script: paste a draft and see where it stands before you record it.
Script Audit
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Hook Analyzer
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Policy Pre-Flight
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Channel Skill Generator
Read this channel's public videos and transcripts, and download a writing brief for it.