Skills Quality assurance

Voice QA: grading calls you cannot read

Voice QA looks like text QA with an extra step. It is not. You are grading a transcript, not a call, and the transcription pipeline introduces errors that become grading errors — errors that are not randomly distributed.

Quality assuranceScorecards and calibrationPlaybookAny helpdeskRead-only
Installnpx rulebase-skills install cx-voice-qa

When to use it

Reach for this when someone says any of these — they are the phrases the skill itself triggers on:

  • QA our calls
  • score phone conversations

How it works

The method, in the order the skill runs it. The full procedure — tables, worked examples and the edge cases — is in the skill itself.

  1. The problem that makes voice QA different

    Automatic speech recognition and speaker diarisation fail systematically, not randomly. Word error rate is consistently worse for: Accented and non-native speech, Regional dialects and code-switching, Poor audio, Overlapping speech and interruptions, Domain vocabulary, product names, alphanumerics.

  2. Step 1: validate the pipeline before writing any criteria

    Build a gold set of 30–50 calls with human transcription, deliberately spanning your real conditions: accents, languages, mobile and landline, quiet and noisy, short and long, and at least a few with heavy crosstalk.

  3. Step 2: choose criteria the transcript can actually support

    Anything that can end in an auto-fail must be confirmed against the audio by a human. A "missing" disclosure is at least as likely to be an ASR miss as a real one, and the consequence of getting it wrong is disciplinary or regulatory.

  4. Step 3: adapt the scorecard rather than reusing it

    An email or chat scorecard does not transfer. Follow the general design procedure in cx-qa-scorecard-design and then change these.

  5. Step 4: expect AI grading to be worse on voice, and quantify it

    If you grade transcripts with a model, the errors compound: transcription error feeds grading error. Follow the AI-grading practice from cx-qa-scorecard-design — evidence quotes, blinding to outcomes, per-criterion agreement — with three voice-specific additions: Report agreement per audio condition, not just per criterion. Model, Never auto-fail on transcript evidence alone.

  6. Step 5: handle the data properly, because voice is worse

    Call recordings carry obligations that text does not.

  7. Step 6: report the measurement quality alongside the scores

    Every voice QA report should carry: WER overall and by segment, so the reader knows the precision of the, The share of calls excluded for poor transcript quality, Which criteria are transcript-graded vs human-confirmed, Agreement by audio condition, if AI-graded.

  8. Troubleshooting

    Some agents consistently score lower — check WER by agent before concluding anything about performance. Accent-correlated WER produces exactly this pattern.

Related skills

Free and open source, and vendor-neutral — it reads the conversations from whichever helpdesk you already run. Browse all 149 skills · connect your helpdesk over MCP · source on GitHub

Review every conversation. Act on what it finds.

AI for customer operations, built for financial services. Specialist agents chase every issue to resolution and every stalled customer to activation.

Rulebase dashboard