AVAY

How to Find Which Meeting Something Was Said In

21 August 2026

You don't search for the word you typed — you search for the word you remember, and those are rarely the same thing. Keyword search over meeting transcripts fails because it matches strings, not meaning; semantic search matches meaning, so it can find the moment someone said "forty cents a seat" even though you searched "pricing." What makes the result usable isn't the match itself — it's the date, the speaker, and enough surrounding speech to tell you whether it's actually the meeting you're thinking of.

A diagram showing spoken words becoming a timestamped transcript, then an indexed meaning, then a ranked passage returned with its date and speaker. live transcri… embedding mod… semantic sear… surfaced with… 1 Spoken words said once, in passing 2 Transcript timestamped text per spea… 3 Meaning index chunks mapped by concept 4 Query match ranks passages by relevan… 5 Result shown passage, date, speaker to…
How a spoken line becomes a searchable result

Forty meetings and one fuzzy memory

A weekly vendor call runs for nine months and you've sat through thirty-nine of them. Somewhere in there, pricing came up. You remember the shape of the conversation — someone pushed back, a number got said out loud — but not which Tuesday it was, and not the words used to say it. That's the actual search problem: not "where is this," but "where is this thing I can describe but can't quote."

Why keyword search misses it

Keyword search tokenizes a transcript and matches literal strings. Type "pricing" and it looks for the token "pricing" — not "the number we talked about," not "what we'd charge them," not "the floor." People rarely use the word you'd use to describe the topic later; they use whatever phrase was natural in the moment, and that phrase is usually more specific and less searchable than the category you'd file it under.

The worse part is the silence. A keyword search that finds nothing looks identical whether the topic was never discussed or was discussed in different words. There's no signal telling you it's a language problem, not an absence.

What semantic search changes

Semantic search converts chunks of transcript into vectors that represent meaning, then converts your query the same way and ranks passages by how close the vectors sit — not by shared letters. Say "pricing" and it can surface a passage where nobody said that word, because "forty cents a seat," a currency figure, and a vendor name sitting next to a renewal date cluster near the same meaning. AVAY runs this over every past meeting a person has attended, so a query typed mid-call can pull a line said months earlier without anyone having tagged or filed it.

What a good result actually looks like

A good result is not a transcript dump. It's a passage — a handful of lines before and after the match, the speaker's name, the meeting title, and the date — enough to decide in three seconds whether this is the one, without opening the full recording.

Where it still misses

Semantic search ranks by closeness in meaning, and closeness isn't always correctness. A passage about the wrong vendor's pricing can rank near the one you want if the topic and phrasing are similar enough. Negation is a known weak spot too — "we are not doing forty cents" and "we're doing forty cents" can land close together in meaning space even though they say opposite things.

It also only works on what got transcribed. A meeting where the recording was saved locally and never uploaded, or a side conversation that happened off-call, leaves nothing to search. The result list is only as complete as the meetings that actually ran through a transcript.

Keyword searchSemantic search
Matches onthe exact word or phrase you typethe meaning of what you describe
Best caseyou remember the exact term someone usedyou remember the topic, not the wording
Worst caseword was never said, returns nothing, looks emptynear-miss on the same topic surfaces the wrong meeting
Effort across 40 recordingsguess terms and scrub each transcript by handone query, ranked candidates across all of them
Keyword search versus semantic search over 40 recurring meetings
  1. 1 Describe, don't quote Type what you remember about the topic, not the exact phrase you think was said.
  2. 2 Scan candidates, not transcripts Look at the ranked passages first — the surrounding lines tell you more than the match itself.
  3. 3 Check date and speaker Match the passage's date and who's talking against what you remember of the conversation.
  4. 4 Jump in to confirm Open the recording at that timestamp only once you're fairly sure it's the right meeting.
How to actually search once you have semantic search

Common questions

What if the exact word I'm searching for was never actually said?

That's the case semantic search is built for. It matches the meaning of your query against the meaning of what was said, so a search for "pricing" can surface a line where someone only said a dollar figure and a vendor's name, with no mention of the word pricing at all.

Can I search across every meeting, or only one recurring series?

A search like this should cover every past meeting a person has attended, not just one recurring call. AVAY's search runs across all of it, so a query typed during today's call can pull up something said in an unrelated meeting six months ago.

Does this work on meetings that were never transcribed?

No. Semantic search runs over transcript text, so a meeting with no transcript — because it wasn't recorded, or the recording sits only on someone's laptop and was never processed — has nothing for the search to reach.

How do I tell apart two meetings that both mention the same topic?

The ranking gets you close; the surrounding context is what actually decides it. Check the date against what you remember, the speaker against who you think said it, and the sentence before and after the match — that's usually enough to know within a few seconds.

Does it understand negation, like 'we're not doing that price'?

Not reliably. A sentence and its negation can land close together in meaning, since they're about the same topic in similar words, so it's worth reading the actual line rather than trusting the match blind for anything that hinges on a yes or no.

The short version

The word you remember is rarely the word that was said — search for the idea instead, and check the date and the sentence around the match before you trust it.

Read next

Try it on your next call

AVAY is a video meeting platform that transcribes the call itself — no bot joins, because there is nothing to join. Start one at avay.ai, read how each part works in the documentation, or see what it costs.