Entries that publish language names, not a total
Two entries name the languages. One sets a list of fifteen per project with Cantonese a sixteenth; the other publishes a code on every voice. Both let a reader check a distribution plan instead of trusting a total. As of 2026-09-22.
| Model | What is published | And where the sound is made |
|---|---|---|
| SceneMixer | A named list, set per project | With the picture, in the language set for the project |
| Synthesia | A catalogue with codes | From the script, or uploaded |
Inclusion rule. Entries whose documentation names the languages of the spoken performance. A count without names, however large, is on a separate route page, and an unnamed claim of breadth is on another. Order. Alphabetical by model name.
1Commissioning asks about one language, not about how many
The question that decides a season is whether a tool speaks the language the next market needs. A total cannot answer it and a list can, which is why this register grades a list above a count regardless of which number is larger.
Both lists here are short enough to audit in a minute. That is the practical test: a reader can tell the difference between a market that is in, a market that is out, and a market that is nearly in, which a number hides completely.
2Two lists, two shapes, two uses
One is a per-project setting, which suits a series committed to a single language and makes the choice early and durable. The other is a per-voice catalogue with codes, which suits picking a voice for a specific market and can be filtered by software.
Neither shape is better. A production making one long thing in one language and a production making many short things in many languages want opposite arrangements, and the two entries here happen to serve those two cases.
3Named is still not the same as usable in that market
A named language moves a market from impossible to testable. Whether the delivery convinces somebody who speaks it at home is decided by a listener, and no vendor read for this register documents register, accent or idiom at all.
So a list is where the work starts rather than where it finishes. The useful next step is one short exchange per market, heard by somebody who lives there, and kept beside the shot list as a finding rather than a specification.
4The entries on this route, one page each
Each of these links to that entry on the field this route groups by. The wording behind every cell, and the date it was read, sits on the page it links to.
- SceneMixer — a named list, set per project.
- Synthesia — a catalogue with codes.
- LanguagesDialogue is set per project to any of 15 languages, with Cantonese a 16th for dialogue onlya named list of 15
- LanguagesEach voice is listed with its formal and native language name, a language code, a gender, a name and a voice idpublished as a catalogue with codes
- Voice sourceVoice cloning carries a language list of its own, running from Afrikaans to Zulu and described as the same list used for standalone cloninga cloned voice with its own reach
- Audio sourceThe video model is described as performing the line in the chosen language while it renders the shotgenerated with the picture
5Sources
Membership of this route is decided by the wording in the field it groups by, read from the documentation each vendor publishes. The column itself is on the field note, all five columns are on the speech table, and what counts as documented is on how read. Other routes: Languages counted, Breadth claimed.