Early accessdesign partners

Quality assurance hears two percent of the calls. Audiqa hears all of them.

Audiqa is a review layer for contact centres. It scores every call in a campaign against the rubric you already use, builds an evidence file for the ones that need a supervisor, and waits for a human before any coaching goes out.

CALL 4-1187 · 07:42 · Collections, campaign “Mora temprana”

04:51 · 05:03 · 05:10
00:0007:42

Apertura

PASS

Verificación de identidad

PASS

Disclosures

FAIL

Resolución primera llamada

WARN

Tono

PASS

Frases de cumplimiento

FAIL

3 pass · 1 warn · 2 fail → Requires supervisor review

“el descuento lo autoriza mi supervisor”

source: transcript

audio clip, 11 s

source: recording

rule QA-DISC-03 not cited

source: rubric

Sample data. Not a verdict.
01The sampling problem

calls a day on a sixty-seat collections floor

%

percent programme: the share of calls it hears

calls heard out of four thousand

go out unheard, scored by nothing

A sixty-seat collections floor takes around four thousand calls a day. A two percent programme hears eighty of them. The other three thousand nine hundred and twenty go out unheard, scored by nothing, and the failures that matter are not evenly distributed through the day: they cluster at the end of a shift, on the longest calls, and on the agents with the least seniority.

The sample is defended on cost, and the cost is real. Listening is the most expensive hour in a quality department. What changed is that listening is no longer the only way to find the call.

Audiqa does not remove the supervisor. It removes the search.

What a sample missesHow it looks
A disclosure omitted at 11:40call 3,900 of the day, never drawn
A discount promised that does not exist40 s of a 9-minute call
A hang-up at 38 secondsthe 200th call of that agent’s shift
Sample data.
02How it works

Three stages. The last one is yours.

1

Ingest.

Point Audiqa at the audio you already store, or drop it to S3. Per campaign you set a consent flag and a retention window. Nothing is scored before both exist.

2

Score.

Every call runs against the campaign rubric. The transcript is a by-product; the output is a score per dimension with the span that caused it.

3

Escalate.

Calls under threshold produce an evidence file and land in the supervisor’s queue. Coaching stays a human decision.

Full pipeline
03The rubric

Six dimensions. Yours to edit.

The default rubric is the one collections and telco floors in Argentina already run on paper. Every dimension is a rule with an id, and every fail cites one.

DimensionWhat is checkedCounts as a fail
Aperturagreeting, agent identification, recording noticeno notice
Verificación de identidadname, document, address check before disclosuredisclosure before verification
Disclosuresrequired legal phrasing per campaignomitted or paraphrased
Resolución primera llamadawhether the stated reason was closedrepeat contact within 72 h
Tonointerruption, pace, closingtalking over the customer twice
Frases de cumplimientoforbidden promises, mandatory wordinga promise outside the authorised list
Rubric detail
04Why now

The cost of listening fell through the floor.

Three years ago scoring every call cost more in compute than the agent cost in salary. Speech recognition was billed per minute by vendors who priced for the enterprise, and a classifier good enough to cite a rule did not exist at a price a mid-size floor could carry.

Both halves moved. Recognition on open models runs at a fraction of a cent per minute on commodity GPUs, and scoring a rubric dimension is a classification problem with a short context. The work did not become easier. It became affordable.

05The evidence file

What a supervisor opens.

An evidence file is not a verdict. It is the smallest set of things a person needs to decide in under a minute.

Evidence file
01The dimension and the rule id
02A timestamped excerpt, never the whole call
03The audio span, eleven seconds either side
04The transcript with the flagged span marked
05Agent, campaign and shift
06The agent’s prior calls on the same rule, last 30 days
Sample data. Not a verdict.
06Control

Autonomy inside limits you set.

01

Thresholds are per campaign, not global.

02

Coaching is a proposal until a supervisor approves it.

03

Permissions are per role: read audio, write score, write file.

04

Retention defaults to 90 days and is configurable down to 7.

05

Audio is never used to train a third-party model without opt-in.

Security and data handling

07Integrations

Where the audio already is.

Read-only in every case. Audiqa never writes back into the telephony platform.

SourceMode
Asterisk / FreePBXread, SFTP
3CXread, API
Twilioread, recording webhook
Aircallread, API
Genesysexport, S3 drop
Anything elseS3 drop or CSV plus audio
08Who it is for

Floors where the sample has already failed an audit.

For

Collections, telecom, prepagas, utilities. Forty seats and up. Teams that already store audio and already run a written rubric.

Not for

Under ten seats, pure outbound sales (different rubric), teams with no stored audio.

09Pricing

By audio hours, monthly.

Three bands, a monthly minimum, invoiced in USD. No per-seat charge, because seats are not what costs us money.

10Limits

What Audiqa does not do.

01

It does not score calls where the consent flag is off.

02

It does not handle overlapping speech well: two people talking at once is the known weak point.

03

It does not coach. It proposes, a person decides.

04

It does not run on your hardware yet.

All limits
11FAQ

Questions we get.

No. The transcript is a by-product of scoring and is kept only as long as the retention window.

No. It replaces the search for the call. The judgement stays.

The recognition model is tuned for it, and each campaign carries its own glossary of product names, plan names and legal phrasing.

Ninety days by default, configurable down to seven, deleted on request inside the window.

Not today. Cloud only, Toronto region.

12Roadmap

Where this goes.

Today

Rubric scoring and evidence files.

Next

A coaching assistant that drafts the conversation from the file.

Later

Trend detection per seat, shift and campaign, before the audit finds it.

We expand one stage at a time and only after the previous one holds.

13Team

Two people.

MR

Malena Rossi

Product

Ten years running quality on collections floors, the last four as head of QA on a three-hundred-seat BPO.

IS

Iván Sequeira

Machine learning

Speech recognition and classification.

Audiqa SAS, Lavalle 1520, piso 6, CABA. Founded 2026.

Team
14Ready when you are

We are taking a small number of design partners.

Tell us what you are trying to catch and what your floor looks like. We reply from a person, not a queue, and we will say no if the fit is wrong.