Sentioscope

Speech and voice controls, as each vendor documents them

Languages: which ones are named for dialogue

Languages records which languages a vendor names for spoken dialogue, not which languages its interface runs in. Two entries publish names. Three publish a total with nothing named. Three claim breadth without naming anything. The remaining nine say nothing at all. As of 2026-09-12.

From a count, to a named list, to a market that can shipA count says the capability exists somewhere inside the model. A list says whether next quarter's market is in it. Neither says how the delivery sounds to somebody who speaks that language at home.A countFive languages, withno names attached.The capability existssomewhere in it.Names itA named listLanguages set perproject, so a marketis in scope or out ofit.Still untestedA listenerRegister, accent andidiom, which nodocumentation pagesettles.
Fig. 1 The field carries the wording rather than a number, because the step between a count and a list is the step a schedule depends on.
Controls documented, model by modelFilled where the model documents that control, hollow where nothing is published about it.Controls documented, model by modelWhat is published for dialogueWhat is publishedfor dialogueThe published wording behind the cellThe publishedwording behind th…D-IDD-ID — What is published for dialogue: A language field, no listD-ID — The published wording behind the cell: An optional language sits beside the chosen voiceHedraHedra — What is published for dialogue: A claim with no namesHedra — The published wording behind the cell: Full multi-language supportHeyGenHeyGen — What is published for dialogue: A count, attached to translationHeyGen — The published wording behind the cell: Thirty or more languages, with cloning and lip-syncKling AIKling AI — What is published for dialogue: A count, no namesKling AI — The published wording behind the cell: Native audio in five languages, on VIDEO 3.0LTX StudioLTX Studio — What is published for dialogue: Not documented by the vendorLTX Studio — The published wording behind the cell: Nothing published about spoken languagesLuma RayLuma Ray — What is published for dialogue: Not documented by the vendorLuma Ray — The published wording behind the cell: Nothing published about spoken languagesMiniMaxMiniMax — What is published for dialogue: Not documented by the vendorMiniMax — The published wording behind the cell: Speech is documented without a language listPixVersePixVerse — What is published for dialogue: Multiple, none of them namedPixVerse — The published wording behind the cell: Multiple languages and audio types, including singingRunwayRunway — What is published for dialogue: Not documented by the vendorRunway — The published wording behind the cell: A multilingual model option, with no language namedSceneMixerSceneMixer — What is published for dialogue: A named list, set per projectSceneMixer — The published wording behind the cell: Fifteen dialogue languages, with Cantonese added for dialogue onlySora 2Sora 2 — What is published for dialogue: Not documented by the vendorSora 2 — The published wording behind the cell: Dialogue guidance that never mentions a languagesync-3sync-3 — What is published for dialogue: A count, ninety-five or moresync-3 — The published wording behind the cell: The same coverage as the models before itSynthesiaSynthesia — What is published for dialogue: A catalogue with codesSynthesia — The published wording behind the cell: A formal name, a native name and a code, per voiceVeoVeo — What is published for dialogue: Not documented by the vendorVeo — The published wording behind the cell: Audio is documented; the language it speaks is notViduVidu — What is published for dialogue: Not documented by the vendorVidu — The published wording behind the cell: Three audio tracks documented, no language namedWan 3.0Wan 3.0 — What is published for dialogue: Not documented by the vendorWan 3.0 — The published wording behind the cell: Audio is documented; the language it speaks is notWan2.2-S2VWan2.2-S2V — What is published for dialogue: Not documented by the vendorWan2.2-S2V — The published wording behind the cell: Audio-driven, so the language is whatever was recorded
Fig. 2 Filled where the model documents that control, hollow where nothing is published about it.
Models documenting each controlHow many models document each control. A hollow column is a statement about documentation, not capability.Models documenting each controlWhat is published for dialogue8 of 17The published wording behind the ce…The published wording behind the cell16 of 17
Fig. 3 How many models document each control. A hollow column is a statement about documentation, not capability.
What each vendor names, or counts, as a language for spoken dialogue. Recorded 2026-09-12.
ModelWhat is published for dialogueThe published wording behind the cell
D-IDA language field, no listAn optional language sits beside the chosen voice
HedraA claim with no namesFull multi-language support
HeyGenA count, attached to translationThirty or more languages, with cloning and lip-sync
Kling AIA count, no namesNative audio in five languages, on VIDEO 3.0
LTX StudioNot documented by the vendorNothing published about spoken languages
Luma RayNot documented by the vendorNothing published about spoken languages
MiniMaxNot documented by the vendorSpeech is documented without a language list
PixVerseMultiple, none of them namedMultiple languages and audio types, including singing
RunwayNot documented by the vendorA multilingual model option, with no language named
SceneMixerA named list, set per projectFifteen dialogue languages, with Cantonese added for dialogue only
Sora 2Not documented by the vendorDialogue guidance that never mentions a language
sync-3A count, ninety-five or moreThe same coverage as the models before it
SynthesiaA catalogue with codesA formal name, a native name and a code, per voice
VeoNot documented by the vendorAudio is documented; the language it speaks is not
ViduNot documented by the vendorThree audio tracks documented, no language named
Wan 3.0Not documented by the vendorAudio is documented; the language it speaks is not
Wan2.2-S2VNot documented by the vendorAudio-driven, so the language is whatever was recorded

Inclusion rule. Models whose documentation names or counts the languages of the spoken performance. Interface languages, subtitle exports and prompt languages are not this field and do not earn a row. Order. Alphabetical by model name.

1A count is not something a schedule can be planned against

Five languages and a named list of fifteen are not the same kind of statement, even though both look like coverage in a feature table. A count tells a production that the capability exists somewhere inside it. A list tells a production whether the market it is shipping to next quarter is in or out, which is the question being asked.

The field keeps the difference visible by recording the wording rather than a number. Where a vendor counts, the cell says it counts, and the gap between a count and a list is left where the vendor put it instead of being filled in by inference.

2Interface languages and dialogue languages are separate lists

Product pages tend to carry a language list that belongs to the menus, the documentation or the prompt parser, and that list is longer than the one the actors speak. Reading the two as one is the most common way this field is misread, and it converts into a market decision that the documentation never supported.

So only a language named for the spoken performance is recorded here. Where a vendor publishes a list without saying which of the two it describes, the cell records the ambiguity rather than resolving it in the vendor's favour.

3Named is still not the same as usable in that market

One entry states that the line is performed in the chosen language while the shot renders, with no dubbing pass afterwards and therefore nothing to synchronise. That is the strongest claim in the column, and it is a claim about mechanism rather than about how the delivery sounds to someone who speaks the language at home.

Register, accent and idiom are outside what any page can settle, and no vendor read for these notes documents them. A named language moves a market from impossible to testable; whether it moves it to shippable is decided by a listener rather than by this field.

4One entry at a time on this column

A cell gets a page of its own where the vendor says something specific in it, or where its silence is unusual among the entries answering the same way. The remaining cells are left in the table above, because a page repeating one short phrase would be worse than a row carrying it.

Entries that publish names rather than a total:

Entries that publish a total with no names beside it:

  • HeyGen — a count, attached to translation.
  • Kling AI — a count, no names.
  • sync-3 — a count, ninety-five or more.

Entries that claim more than one language without naming any:

  • D-ID — a language field, no list.
  • Hedra — a claim with no names.
  • PixVerse — multiple, none of them named.

Entries that never say which language a performance is delivered in:

  • Runway — not documented by the vendor.
  • Sora 2 — not documented by the vendor.
  • Wan 3.0 — not documented by the vendor.
  • Wan2.2-S2V — not documented by the vendor.
  • 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
  • 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
  • Audio source
    Native audio on VIDEO 3.0 in five languagesgenerated with the pictureKling AI, model 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
  • 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
  • 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
  • Languages
    Multiple languages and audio types are supported, including speech, singing, and advertisementsmultiple, none of them namedPixVerse, speech and lip sync guide / recorded 2026-09-22
  • Languages
    Described as text, image and audio to video with full multi-language support, and a maximum duration of ten minutesa claim carrying no listHedra, Character 3 model page / recorded 2026-09-22
  • 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

5Sources

Each cell is read from the vendor page it links to, checked 2026-09-12. The fields sit side by side on the speech table, and what counts as documented is set out on how read. The other fields: Lip-sync, Audio source. All of them: the field notes.