Sentioscope

Speech and voice controls, as each vendor documents them

Hearing a voice before a season depends on it

Casting is a listening decision and almost nothing here documents anything to listen to. The substitute is a deliberate test: one short generation per character, heard and kept, before any episode is written around it. As of 2026-09-12.

Four short generations that answer what no page doesA held note exposes artefacts a short line hides. A proper noun is the reliable failure case. An exchange in the target language tests register. The same line twice shows how much a rebuild drifts.A held noteExposesartefacts thata short spokenline conceals.ThenA proper nounNames breakreads moreoften thansentences do.ThenThe languageAn exchange inthe targetlanguage;register isundocumented.ThenThe same lineGeneratedtwice, to showhow far arebuilt voicemoves.
Fig. 1 Four generations per speaking character is trivial against a series, and the findings have to be retrievable or they get re-discovered under deadline.
Controls documented, model by modelFilled where the model documents that control, hollow where nothing is published about it.Controls documented, model by modelWhyWhat it preventsA held note or a long vowelA held note or a long vowel — Why: Exposes artefacts a short line hidesA held note or a long vowel — What it prevents: A voice that fails only on emotionA line with a proper nounA line with a proper noun — Why: Names are the reliable failure caseA line with a proper noun — What it prevents: Renaming a character in episode nineA short exchange in the target langua…A short exchange in the target languageA short exchange in the target language — Why: Register and idiom are undocumentedA short exchange in the target language — What it prevents: Discovering a market is unusableThe same line twiceThe same line twice — Why: Shows how much a rebuild driftsThe same line twice — What it prevents: A cast that changes voice mid-season
Fig. 2 Filled where the model documents that control, hollow where nothing is published about it.
What a pre-season voice test should produce, and why each part matters. Recorded 2026-09-12.
What to produceWhyWhat it prevents
A held note or a long vowelExposes artefacts a short line hidesA voice that fails only on emotion
A line with a proper nounNames are the reliable failure caseRenaming a character in episode nine
A short exchange in the target languageRegister and idiom are undocumentedDiscovering a market is unusable
The same line twiceShows how much a rebuild driftsA cast that changes voice mid-season

Inclusion rule. Elements of a pre-production voice test, chosen to exercise the behaviours no vendor documents. Order. Alphabetical by element.

1A paid test is cheaper than a season

Four short generations per speaking character is a trivial cost against a series, and it answers questions that no page in this register answers: how the voice handles names, how it behaves in the target language, and how much it moves between calls.

Keeping the results beside the shot list matters as much as running them. A finding nobody can retrieve is a finding that gets re-discovered by whoever is on shift when a shot comes back wrong.

2The same line twice is the most informative test

Generating one line, then generating it again from the same inputs, shows how much a voice drifts on a rebuild. Where a voice is stored and reused, the answer should be nothing; where it is re-established from a clip, it rarely is.

That single comparison decides how much archival discipline a production needs. It is also the test most obviously missing from every vendor page, because it measures consistency rather than quality.

3Proper nouns break reads more often than sentences do

Initialisms, invented words, brand names and names from another language are the reliable failures. There is no way to know how one will be read except by generating it, and a character name is the worst possible thing to discover late.

Testing the proper nouns of a production before writing a season around them is a twenty-minute job. Renaming a lead in episode nine is not.

4Where the published detail is logged

What is described above is how the techniques work in general. Which models document which of them, in whose words, is kept in the speech controls table with a date on every field.

A mechanism note rather than a documented field. Nothing here is attributed to a model, and nothing here is a claim about one. The sourced material is on the speech controls table. Related: Singing and read copy, First tests.