Sentioscope

Speech and voice controls, as each vendor documents them

Which column almost every entry fills

One column is almost always answered and the rest thin out. Where the sound comes from is filled by fourteen entries. Languages are a minority answer, a persistence mechanism is filled by ten and a mouth driver by nine, and the voice source is blank for seven. From 5 source pages, read 2026-09-22 to 2026-10-13; no maker pays to be listed.

Documentation thins exactly as the questions get usefulWhere the sound comes from is a single binary fact, easy to state. Every column after it asks a vendor to describe a workflow, and the fill rate falls in the same order across products that share nothing else.Audio sourceFourteenentries. Onefact, binary,hard to getwrong.Then thinnerBindingTen entries.Requiresdescribingsomethingoutlasting acall.Then thinnerVoice sourceNine entries.Requiresdescribing whatmay be handedover.Then thinnestLanguagesSeven entries,and only two ofthem publishnames.
Fig. 1 Counting filled cells would flatter whoever writes most, which is why this register keeps the wording instead.
How many entries fill each column, and what the blanks in it mean. Recorded 2026-09-12.
FieldWhat is documentedDetail
Audio sourceFourteen entriesThe two blanks are a picture page and a voices page
Voice sourceNine entriesBlank where a voice arrives without being chosen
Per-character bindingTen entriesBlank where nothing is said to outlast a call
LanguagesSeven entriesAnd only two of the seven publish names
Lip-syncNine entriesFour of those name the feature and no driver

Inclusion rule. Every column this register keeps is listed, with the number of entries whose documentation fills it. A column is not added unless enough vendors publish something comparable. Order. Fixed field order, the order the questions arrive in.

1The easiest question is the one everybody answers

Whether sound comes out of a model is a single binary fact, easy to state and hard to get wrong, so almost every document manages it. The columns that stay empty are the ones requiring a vendor to describe a workflow rather than a capability.

That pattern is the most consistent finding in this register. Documentation gets thinner exactly as the questions get more useful, and it thins in the same order across products that otherwise share nothing.

2The two blanks in the filled column are instructive

One is a video reference that never mentions sound; the other is a voices reference that never mentions a shot. Between them they cover both halves of this subject and neither covers the join, which is where every question here lives.

Neither is a weak product. The blanks describe what each document was written for, and a production is the party left to establish the rest by test.

3A filled cell still says less than it appears to

Counting filled cells would flatter the vendors who write most, so this register keeps the wording instead. Nine entries fill the mouth column and five of those name anything as the driver; four name the feature and stop.

Grades inside a column matter more than the tally across it. A list beats a total, a driver beats a capability, and a stored voice beats a clip supplied on every call, regardless of how many cells are filled on either row.

  • Audio source
    Not documented by the vendor (as of 2026-09-22)no mention of sound in the video referenceLuma, video generation reference / recorded 2026-09-22
  • Lip-sync
    Not documented by the vendor (as of 2026-09-22)not addressed where voices are definedRunway, custom voices reference / recorded 2026-09-22
  • Per-character binding
    A voice matched to a character from the built-in preset library is used as reference audio on every shot that character speaks ina matched preset kept on the characterSceneMixer, character voices guide / recorded 2026-10-13
  • Languages
    Not documented by the vendor (as of 2026-09-22)neither a list nor a countOpenAI, video generation guide / recorded 2026-09-22
  • Languages
    Not documented by the vendor (as of 2026-09-22)nothing published about the spoken performanceWan-AI, Wan2.2-S2V-14B model card / recorded 2026-09-22

4Sources

Every line is read from the vendor documentation linked on the speech controls page, checked 2026-09-12. What counts as documented is on how read. Nearby: Speech without the bed, Regenerating a shot, Consent in the docs.