Product · VIDTREO Intelligence

New

Every recording, turned into answers you can verify.

Describe what you need to know in plain words. Intelligence builds the lens, analyzes every video and audio, returns structured data and links each answer to the moment that proves it.

Start free — $1 credit See how it works

01 · Lenses

A lens is what you want to know, written once.

It holds the objective, the questions and the rules. Run it on one recording or on every new one, and each result comes back in the same shape.

+ Objective: What the analysis is for, in one sentence.
+ Summary sections: The headings every summary must cover.
+ Data points: Text, numbers, yes/no, choices and lists your system can read.
+ Scorecard: Criteria with a maximum score, for rubrics like interviews or QA.
+ Trust rules: What the analysis must never assume or invent.
+ On-screen checks: Yes/no questions about what appears in the video.

Lens

Sales discovery call

Objective: Find out if the prospect is ready to buy and what is blocking them.
Summary sections: Pain pointsNext steps
Data points: Budget confirmed yes/no
Decision maker text
Objections list
Scorecard: Discovery questions · /5
On-screen check: Is a pricing slide on screen?
Trust rule: Never assume a budget that wasn't said out loud.

02 · Lens Designer

Describe it. The Designer writes the lens.

No prompt engineering. Drop in a recording or just say what you're looking for: the Designer asks a few quick questions and drafts the lens with you.

01

Start from a recording or a sentence

Upload a video or audio, pick one you already have, or describe what to detect.
02

It reads before it suggests

The Designer writes down what was said and who said it, then proposes two or three lenses based on what is really in the recording.
03

Answer with a tap

Short rounds of questions with a recommended option, never a blank form.
04

Publish and analyze

See the cost before you run it. Every later change is saved as a new draft with a note.

03 · What comes back

Structured results, with the receipts.

Each analysis returns an Intelligence Package: a headline, a summary by section, chapters, data points, a scorecard and the evidence behind every one of them.

Transcript and speakers

What was said, split by speaker.
Visual review

Frames checked against the lens's on-screen questions.
Who is speaking

Names matched from introductions and video-call labels.
Lens analysis

Your objective, data points and scorecard, applied.
Evidence checks

Every citation validated against the recording.

The evidence reel plays every cited moment back to back
Speaker lanes show who talks when
Chapters, transcript and evidence side by side

Discovery call · Acme

Sales discovery call · v3

Headline

Ready to buy in Q3 if the security review passes.

Data points

Budget confirmed Yes ▶ 04:12
Decision maker Dana, VP of Operations ▶ 01:47
Objections Security review · Onboarding time ▶ 09:30
Competitors evaluated Not enough evidence

Discovery questions

4/5

Evidence · 04:12

“We set aside budget for this in Q3.”

04 · Ask

Ask your recordings anything.

Chat with one recording or across everything you've analyzed. Answers come only from what was said and shown, with the exact moments, and when the answer isn't there, it says so.

Ask a single recording from its player
Ask across every analyzed video and audio
Answers in the language you ask in

Ask your recordings

Which calls this month pushed back on the annual commitment?

Two of them. Acme asked to start with a quarterly plan, and Northwind wants a pilot before signing.

▶ Acme · 12:05▶ Northwind · 03:41

Did Acme agree on a next step?

Yes: a security review call with their IT lead next Tuesday.

▶ Acme · 31:20

05 · Trust

Built to be checked, not just believed.

Intelligence is designed for decisions people have to defend. Every answer shows its work.

Every claim is cited: Points, data points and scores must cite a moment of the transcript or a frame, and each citation is checked against the recording.
It abstains instead of guessing: When the recording doesn't support an answer, the result says so instead of making one up.
Contradictions are flagged: If the recording says two different things, the data point is marked as contradictory.
No emotion reading, no face recognition: The visual review never infers emotions or personality and never identifies people by their face.
Your reviewers make it better: Mark any claim right or wrong. Every review joins the lens's gold set, and accuracy is tracked for each version.

06 · Automate

Runs on every new recording.

Publish a lens, turn it on for an environment and every video or audio uploaded there is analyzed on its own. The result arrives in your system as JSON.

+ Versions you can trust: Drafts, published versions, change notes and comparisons between any two versions.
+ Per environment: Turn each lens on where it belongs, with automatic analysis on or off.
+ A webhook with the full result: intelligence.lens_analysis.completed carries the run, the recording and the complete structured result.

Webhook payload (trimmed)

{
  "event": "intelligence.lens_analysis.completed",
  "data": {
    "run": {
      "lensName": "Sales discovery call",
      "headline": "Ready to buy in Q3 if the security review passes.",
      "score": "4/5"
    },
    "result": {
      "findings": [
        {
          "field": "Budget confirmed",
          "value": true,
          "status": "supported",
          "evidence": [{ "kind": "segment", "start": 252.4, "end": 259.1 }]
        }
      ]
    }
  }
}

07 · Pricing

Pay per analyzed minute.

Analyses are paid from the same prepaid credits as your recordings. No seats, no monthly fee.

Video

$0.035

per minute, per analysis

Audio

$0.025

per minute, per analysis

Estimate your monthly cost

Recordings analyzed per month100

Average length20 min

Recording type

Lenses per recording

Also recorded with VIDTREO RecorderHD video at $0.010/min or audio at $0.005/min, with storage and transcription included.

$70.00per month

Analysis: $70.00
per recording: $0.700

Each analysis is rounded up to the next minute. Analyses that fail are never charged.
Your $1 free credit covers about 28 minutes analyzed like this.

→ See full pricing

Intelligence FAQ

Which languages does Intelligence understand?

Spanish and English, including recordings that mix both. Results can be written in Spanish, in English or in the main language of the recording.

Does it work with audio recordings?

Yes. Audio gets the transcript, the speakers and the full lens analysis. The visual review only runs on video, when the lens has on-screen checks.

Do I need to write prompts?

No. The Lens Designer builds the lens from a description or a sample recording, and you can still edit every part of it by hand.

How do results reach my system?

Turn on automatic analysis for an environment and subscribe to the intelligence.lens_analysis.completed webhook. Every result arrives as structured JSON, together with the recording it belongs to.

Can it analyze recordings that weren't made with the Recorder?

Yes. Any video or audio in your VIDTREO library can be analyzed, whether it was recorded with the Recorder or uploaded.

How much does an analysis cost?

$0.035 per minute for video and $0.025 per minute for audio, for each analysis. A 10-minute video costs $0.35 per lens. Failed analyses are free.

Does it read emotions or recognize faces?

No. It works from what was said and what is shown on screen. It never infers emotions or personality and never identifies people by their face.

Ready to record?

Start with $1 free credit. No credit card required.

Start recording free Read the docs