Sentioscope

Speech and voice controls, as each vendor documents them

SceneMixer: fifteen named, and Cantonese makes sixteen

Dialogue is set per project to any of fifteen named languages, and Cantonese is listed as a sixteenth for dialogue alone. Naming them turns a capability claim into something a commissioning conversation can act on. As of 2026-09-12.

Sixteen names against a total, and why the shape mattersFifteen dialogue languages are named and set per project, with Cantonese a sixteenth for dialogue only. A list can be checked against a distribution plan in a minute; a total cannot be checked at all.A named listA totalQuestion it answersIs the next market in itIs the capability broadHow long to checkAbout a minute, against a planCannot be checkedNear missesVisible, like a dialogue-only entryInvisibleWhen it goes staleVisibly, one name at a timeSilently, as the number is reusedGrading a list above a total ignores which number is bigger
Fig. 1 A dialogue-only sixteenth entry is the ragged edge that usually marks an inventory taken from an implementation rather than from marketing copy.
SceneMixer on languages, statement by statement. Read from the vendor's languages guide on 2026-09-12.
What the documentation settlesWhat it leaves to a take
Dialogue is set per project to any of fifteen languages, with Cantonese a sixteenth for dialogue onlyWhether register and idiom hold up in each of the sixteen
The model performs the line in the chosen language while it renders the shotHow a native listener rates that performance
There is no separate dubbing step and no lip-sync patch afterwardsWhat changing a market costs once a season is generated

Inclusion rule. Only statements found on the vendor page named in the caption, and only ones bearing on this one field. Nothing here is filled in from generated output. Order. In the order the statements arrive on the vendor's page.

1A list answers the question that is actually asked

Commissioning conversations do not ask how many languages a tool speaks. They ask whether it speaks the one the next market needs. A count cannot answer that and a list can, which is why this column grades a list above a total whichever number is larger.

Sixteen named is also small enough to audit. A reader can check the list against a distribution plan in a minute, and can tell the difference between a market that is in and a market that is nearly in, which a total hides completely.

2Cantonese as a dialogue-only entry is the telling detail

Separating a language that is available for dialogue from the languages available everywhere else is a distinction most vendors do not make at all. It implies the production documents and the spoken performance are drawn from different inventories, which is exactly the confusion this column exists to prevent.

It is also a small argument that the list is real. Inventories that are marketing copy tend to be tidy; ones with a ragged edge like this usually come from an implementation.

3The other entry that publishes names

One more entry answers this column with names rather than a number, and it does so in a very different form: a per-voice catalogue with language codes rather than a per-project setting.

  • Languages
    Dialogue is set per project to any of 15 languages, with Cantonese a 16th for dialogue onlya named list of 15SceneMixer, languages guide / recorded 2026-09-12
  • Audio source
    The video model is described as performing the line in the chosen language while it renders the shotgenerated with the pictureSceneMixer, languages guide / recorded 2026-09-12
  • Lip-sync
    The vendor states there is no separate dubbing step and no lip-sync patch afterwardsstated as unnecessary rather than as a featureSceneMixer, languages guide / recorded 2026-09-12

4Sources

Read from the languages guide at scenemixer.com on 2026-09-12. The same column across every entry is on languages; everything this vendor publishes about speech is on SceneMixer. What counts as documented is on how read.