What Is Verbatim Transcription?

To make the differences concrete, here is the same 12-second audio clip rendered in all three styles:

Original audio: A speaker pauses, restarts, and answers a question.

Strict verbatim

Interviewer: So, um, can you tell me about, uh,
the project?

Subject: Yeah, yeah, sure. So I, I started — well,
we started, um — [coughs] excuse me — we started
the project back in, um, January? Yeah, January.
And it's been, you know, it's been a journey.
[laughs] Yeah.

Intelligent verbatim

Interviewer: Can you tell me about the project?

Subject: Sure. We started the project back in
January. It's been a journey.

Clean read

Interviewer: Tell me about the project.

Subject: We launched the project in January, and
it has been an interesting journey since then.

All three are accurate to what was said — they just preserve different amounts of how it was said. Choose the style based on what you'll do with the transcript.

Strict verbatim is required (or strongly preferred) in these contexts:

• Court reporting and legal proceedings. Depositions, trial transcripts, and other legal records must capture exactly what was said. Filler words, hesitations, and tone of voice may matter to a case. Strict verbatim is the legal standard.
• Qualitative research (PhDs, sociology, ethnography). When studying how people think and speak, the filler words, hesitations, and self-corrections are data. Researchers analysing speech patterns need every utterance.
• Medical transcription. Specifically, mental health and behavioural assessments where the manner of speech is part of the diagnosis.
• Linguistics and conversation analysis. Studying turn-taking, interruptions, repair sequences, and other conversational structures.
• Insurance investigations. Where exactly how a claimant phrased something can matter.
• Focus group research. Where the dynamics of how people respond — including filler and hesitation — are part of the analysis.
• Forensic linguistics. Authorship attribution, threat analysis, and stylometric work all depend on capturing every speech feature.

If you're writing a transcript for any of these purposes, request strict verbatim explicitly when ordering from a service or when configuring an AI transcription tool. Most AI tools default to intelligent verbatim and clean filler words automatically — you have to opt out.

Intelligent verbatim is the right choice for most general business and content use cases:

• Journalism interviews. Reporters need accurate quotes that preserve the speaker's voice without making them look inarticulate by including every "um."
• Podcast show notes. Capture what was said in readable form without forcing readers to wade through hesitations.
• Customer feedback analysis. Understand what customers said in research interviews without getting distracted by speech artifacts.
• Sales call review. Reps want to study what they said and how prospects responded — readability matters more than capturing every "right" and "yeah."
• Conference talks and keynotes. Distributing a written version of a talk for accessibility or content reuse.
• Internal meeting notes. Capturing decisions and discussion without the noise of speech disfluencies.
• Educational content. Lectures and tutorials transcribed for student reference.

This is the default style produced by most AI transcription services in 2026. TranscribeVideo.ai, Otter, Rev's auto-transcription, and Whisper all output intelligent verbatim by default.

Clean read transcription is appropriate when the final output will be read as prose, not as a record of speech:

• Repurposing audio into blog posts. Convert a podcast episode into a written article — clean read removes spoken-language patterns that don't read well.
• Book content from interviews. Authors who interview subjects often want clean-read transcripts they can edit further into prose.
• Marketing case studies. Customer interview content turned into branded marketing material reads more polished in clean read style.
• Email newsletter content from podcasts. The conversational style of audio doesn't translate to skimmable email writing.
• Academic papers citing interviews. When the meaning matters more than the exact phrasing, clean read makes citations more readable.

Clean read is rarely the output of an AI transcription tool directly — it usually requires a second pass through an editor (human or AI) that paraphrases and restructures. Tools like Descript and Otter offer "clean up" features that approximate clean read.

By default, modern AI transcription tools clean up speech disfluencies. To get strict verbatim, you have to request it explicitly:

Whisper (OpenAI)

Pass the prompt parameter explicitly: --initial_prompt "Include all filler words like um, uh, and false starts. Do not clean up speech." in the CLI, or include this instruction in the prompt parameter when calling the API. Whisper's default output already preserves more disfluencies than other models, but the prompt forces full strict verbatim.

Otter.ai

In Otter, the default cleans up filler words. There is no native "verbatim mode" — you'd need to use the raw transcript before Otter's smart-summary processing, which is exposed via the API but not via the standard UI export.

Rev.com

Rev's human transcription service offers an explicit verbatim option as a paid add-on. AI Rev (auto-transcription) does not currently have a verbatim toggle.

Trint

Offers a "show fillers" toggle in the editor. Turn it on after upload to see filler words; turn it off to get the cleaned version.

The honest tradeoff

AI transcription is significantly less accurate at strict verbatim than at intelligent verbatim. The models were trained on cleaned-up text, so reproducing exact disfluencies requires breaking the model's natural inclination. For high-stakes strict verbatim work (legal, research), human transcription is still the standard. AI is reliable for intelligent verbatim and adequate for clean read.

Beyond the words, verbatim transcripts have formatting conventions:

• Speaker IDs in caps with colon. JOHN: or INTERVIEWER:. Some research conventions use [P1], [P2] for participants or pseudonyms.
• Bracketed non-speech sounds. [laughter], [cough], [pause - 3 sec], [phone ringing], [overlapping speech].
• Filler words written out. "um," "uh," "ah," "er," "mm-hmm," "uh-huh." Convention varies on apostrophes.
• False starts marked with em-dash. "I was going to — well, actually, let me start over."
• Pauses marked. Short pauses with ellipsis or (...). Long pauses with a duration: [pause - 5 sec].
• Inaudible markings. [inaudible] or [inaudible 00:23:14] when a section can't be transcribed.
• Overlapping speech. [crosstalk] or square brackets around the overlapping sections to show simultaneity.
• Timestamps. Inserted at speaker changes or at fixed intervals (every 30 seconds, every 2 minutes) for navigation. Format: [00:14:25].

For research transcripts especially, follow the conventions used by your field's standards. Sociolinguistics has different conventions from clinical interviewing.

Is verbatim transcription required by law?

For court reporting and certified legal transcripts: yes, strict verbatim is required. For accessibility-compliant captioning: no — captions are typically intelligent verbatim plus sound effect descriptions, which is what makes them captions rather than subtitles. For research subject to IRB approval: it depends on the methodology, but most qualitative research IRBs require strict verbatim of recorded interviews.

How accurate is AI verbatim transcription?

For intelligent verbatim, modern AI achieves 95%+ word accuracy on clear single-speaker audio. For strict verbatim — preserving every filler and disfluency — accuracy drops because models tend to clean as they go. Whisper is the most reliable AI for strict verbatim; even so, expect 80-90% accuracy compared to human transcription.

How long does verbatim transcription take?

Human strict verbatim: roughly 4-6 hours per hour of audio for an experienced transcriptionist. Human intelligent verbatim: 3-4 hours per hour of audio. AI: minutes per hour of audio, regardless of style. The choice between human and AI usually comes down to whether the use case can tolerate AI-level accuracy or requires the higher human standard.

Can I convert AI intelligent verbatim back to strict verbatim?

Not reliably. AI cleaning is lossy — once "um" and "uh" are removed, they can't be reconstructed without re-running the transcription on the original audio with explicit instructions to preserve them. If you anticipate needing strict verbatim, configure for it from the start.