Transcribe a recording, then check it before you quote it

Use it when you have a recording of an interview, lecture, voice memo or call, and you want to quote it, search it or summarise it.

Not when anyone in the recording did not agree to it, or the recording is medical, legal or about someone's job. Keep those out of AI tools unless your organisation has approved one for that use.

You need the recording, the consent of the people in it, a transcription tool you already have, headphones, and a text file for the check sheet below. Remove what the tool does not need before you upload anything: What not to paste. The steps, times and thresholds are our suggestion.

Why the check matters

• In one study of OpenAI's Whisper as it ran in 2023, about 1% of transcriptions contained whole phrases or sentences that were never spoken, and 38% of those invented passages included explicit harms such as violence, false associations or false authority (Koenecke et al., 2024, benchmark, peer-reviewed, FAccT 2024). The study used 13,140 audio segments from 437 speakers.
• The inventions were more common for speakers with aphasia, a language disorder often caused by a stroke (1.7% of segments against 1.2% for the control group), and audio with a larger share of silence was more likely to get invented text. The authors found the rate fell after a late-2023 update but that the model still "regularly and reproducibly hallucinates".
• OpenAI's own Whisper model card (its published fact sheet on the model) says its output may include "texts that are not actually spoken in the audio input", that it is prone to repeating text, that accuracy is uneven across languages, accents and speaker groups, and it recommends "against use in high-risk domains like decision-making contexts" (model card, vendor).

A word error is easy to spot. An invented sentence reads smoothly. That is why the check below is about listening, not reading.

Steps

Tools you may already have

Read on each vendor's page on 2026-10-11:

• Zoom cloud recordings can produce an audio transcript on Pro, Business, Education or Enterprise accounts, saved as a VTT file (a plain-text subtitle format) with a timestamp on each section. Zoom's tips: keep background noise low, place the microphone near active speakers, and prefer an external microphone (Zoom).
• Microsoft Teams transcripts show speaker names and timestamps, all participants are notified when transcription starts, and organisers can download a .docx or .vtt file. Microsoft says to "make sure the meeting spoken language reflects the language everyone is speaking" (Microsoft).
• Pixel Recorder on Google Pixel phones transcribes recordings, and you can edit the text. Google says re-transcribing "may process audio files on Google servers" (Google).
• Voice Memos on iPhone can show a transcription of a recording (Apple).
• Whisper is open source (its code is public and free to use) under the MIT License and installs from a terminal (the window where you type commands) with pip install -U openai-whisper plus ffmpeg (GitHub). It installs on your own computer. The model sizes range from tiny (about 1 GB of video memory, the memory on a graphics card) to large (about 10 GB).

Check sheet

Copy this into a text file next to the recording and fill it as you go:

Recording: <RECORDING_NAME>    Date recorded: <RECORDING_DATE>
Consent: <WHO_AGREED_AND_HOW>
Tool and language setting: <TOOL_AND_LANGUAGE>

SPOT-CHECK (3 random 1-minute stretches)
Start time | Word errors | Wrong speaker | Invented phrase (Y/N)
<START_1>  |             |               |
<START_2>  |             |               |
<START_3>  |             |               |
Total word errors:      Any invented phrase: Y / N

LISTENED IN FULL
Timestamp | What (quote / number / name / date / silence / crosstalk) | Checked or corrected | Note
<TIMESTAMP> | <WHAT> | <STATUS> | <NOTE>

Ready to summarise only after every quote above says checked or corrected.

Replace the following:

• <RECORDING_NAME>: the file name, such as interview-03.m4a.
• <RECORDING_DATE>: the day it was recorded.
• <WHO_AGREED_AND_HOW>: names and how they agreed, such as both, aloud at 00:00.
• <TOOL_AND_LANGUAGE>: the tool and the language you set, such as Zoom, English.
• <START_1> to <START_3>: three start times you picked at random, such as 07:00.
• <TIMESTAMP>, <WHAT>, <STATUS>, <NOTE>: one row per passage you listened to in full.

How to tell it worked

• Every quote you publish or send has a timestamp and the word "checked" in the sheet.
• Every number, name and date you use matches the audio, not only the text.
• The sheet shows a spot-check result, so you know how much to trust the lines you did not hear.
• It has failed if you quoted a line you only read. Go back and listen to it.

Sources

1. Koenecke et al., 2024. "Careless Whisper: Speech-to-Text Hallucination Harms". 13,140 audio segments from 437 speakers, FAccT 2024. Peer-reviewed benchmark. Link. Summary: Cornell Chronicle.
2. OpenAI. Whisper model card and repository. Vendor. Model card, repository.
3. Zoom. Audio transcripts for cloud recordings. Vendor help page. Link.
4. Microsoft. Live transcription in Teams meetings. Vendor help page. Link.
5. Google. Pixel Recorder transcription. Vendor help page. Link.
6. Apple. View a Voice Memos transcription on iPhone. Vendor help page. Link.
7. Otter.ai. Privacy policy, effective 16 June 2026. Vendor policy, read 2026-10-19. Link

Changes

1. v1.010 Oct 2026first version