Transcript Standards

How we render the record.

An Anticipated Transcript is legal work product, so we hold it to written standards — built by immigration attorneys, applied to every hearing, and visible on the page rather than buried in fine print. Here is exactly what we do, what we mark, and what we never do.

1. Verification is the standard

We don't ask you to trust the transcript — we make it checkable. Every line carries a timestamp that links to that exact moment of the hearing audio. Reading and verifying are one click apart, which is a stronger guarantee than any accuracy percentage anyone could quote you.

2. Judgment calls are marked, never hidden

Courtroom audio is imperfect: people mumble, talk over each other, and trail off. When a reading involves a genuine judgment call — a word corrected from context, an ambiguous speaker, reconstructed speech — that line carries an inferred mark:

The recording at that moment is ambiguous; context makes the reading near-certain — so we render it, and we tell you we made the call. Click the timestamp and judge it yourself. Routine fixes with only one right answer (formatting, obvious vocabulary) are not marked; only judgment is.

3. Citations and forms render in standard legal form

Spoken citations become written citations. "Two-twelve A six A little i" renders as section 212(a)(6)(A)(i); "the 589" renders as the I-589. Your transcript should read like the record you'd cite, not like a phonetic puzzle.

4. The interpreter convention

We follow official-transcript practice for interpreted testimony:

• Non-English speech is not transcribed — no placeholder lines, no clutter.
• The interpreter's English rendition of a witness's answer is attributed to the witness, styled "Respondent (through interpreter)" — because that rendition is the testimony of record.
• The interpreter appears under her own name only when speaking for herself on the record: stating her name, confirming her oath, or asking for a repetition.

The full multi-channel recording is always preserved — the transcript renders the record; it never replaces it.

5. What was said beats what reads smoothly

Speech recognition tends to tidy human speech — dropping an "uh," smoothing a false start. We treat the audio as ground truth and preserve the speaker's actual words wherever the recording supports them. And where automated transcription has quietly normalized something, the click-to-hear link is your remedy: the audio is always one click away, which is precisely why we build the transcript around it.

6. What we never do

• We never certify. The Anticipated Transcript is a working transcript — clearly labeled, never passed off as an official transcript.
• We never invent. Unintelligible is rendered as unintelligible, not guessed into fluency without a mark.
• We never claim an accuracy number we can't prove. Our accuracy claim is verifiability.
• We never let anyone else's AI learn from your data. The commercial AI services in our pipeline are contractually committed not to train on your material. We improve our own system only with your explicit consent, and only on anonymized material.

Open the live demo  Get your first hearing free