Sentioscope

Speech and voice controls, as each vendor documents them

A second-language version: dub the cut or perform it again

Three entries document reaching another language by dubbing: new speech over the same picture, with mouths re-synced. One documents the other route, a second project with the same cast whose dialogue is performed in the new language as each shot is generated. As of 2026-10-13.

Three routes into a second languageDubbing lays new speech over the finished cut and redraws the mouths. Performing again makes a second project with the same cast and generates the scenes with dialogue in the new language. Subtitling keeps one picture and one soundtrack and asks the audience to read.Dub the cutNew speech over thesame picture, mouthsre-synced.OrPerform againSame cast, secondproject, dialogue inthe new language.OrSubtitleOne picture, onesoundtrack,translated text onscreen.
Fig. 1 Only one entry documents performing again; only one guide mentions subtitles as an option.
How each entry documents getting from one language to another, and what it states about range. Recorded 2026-10-13.
ModelRoute to another languageRange stated
HeyGenVideo translation with voice cloning and lip-syncThirty or more languages
SceneMixerA second project with the same cast, performed in the new languageFifteen named, plus Cantonese for dialogue
sync-3Dubbing, matching mouths to the new audio95 or more languages
SynthesiaA dubbing project with locales addedA voice catalogue with language codes

Inclusion rule. Entries whose documentation describes producing a version of a video in another language. Subtitling alone does not earn a row. Order. Alphabetical by model name.

1Dubbing keeps the performance and replaces the voice

The three dubbing routes start from a finished cut. The pacing, framing and acting stay as approved; speech in the new language is laid over and the mouths are redrawn to it. That is fast and keeps every language version visually identical, and it inherits the original timing, so a language that runs longer than the source has to be compressed to fit.

2Performing again keeps the cast and replaces the performance

The fourth route treats the new language as a new production of the same story. The dialogue language is fixed when the script is read, so a second version is a second project; each character is brought across so the faces match, and the scenes are generated again with the dialogue performed in the new language.

The result is lip movement made for the words rather than adjusted to them, and a second set of clips to review. Its guide also notes that a voice chosen for one language can be swapped for another from the library if it does not suit the new one.

3Subtitles are the third route

One entry's guide names subtitles over the existing episodes as the cheaper option when viewers only need to follow the story. None of the dubbing entries discusses that alternative, which is unsurprising and worth remembering when pricing a first release into a market whose response is unknown.

  • Languages
    Video translation is documented for thirty or more languages, with voice cloning and lip-synccounted on the translation endpointHeyGen, API quick start / recorded 2026-09-22
  • A route into another language
    A version in another language is a second project with each character brought across so the faces match; the dialogue language cannot change after the script is readSceneMixer, second-language guide / recorded 2026-10-13
  • The third route
    Subtitles over the existing episodes are named as the cheaper route when viewers only need to follow the storySceneMixer, second-language guide / recorded 2026-10-13
  • 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
  • Languages
    sync-3 supports 95 or more languages, described as the same coverage as the models before itpublished as a countSync, sync-3 model documentation / recorded 2026-09-22
  • A route into another language
    The model page describes sync-3 as designed for global dubbing at native qualitysync, sync-3 model page / recorded 2026-10-13
  • A route into another language
    The API reference lists creating a dubbing project from an uploaded video asset and adding locales to itSynthesia, API reference / recorded 2026-10-13
  • Languages
    Each 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 codesSynthesia, list of supported voices / recorded 2026-09-22

4Sources

Every line is read from the vendor documentation linked on the speech controls page, checked 2026-10-13. What counts as documented is on how read. Nearby: Keeping a voice, Lip-sync, Voice sources.