Sentioscope

Speech and voice controls, as each vendor documents them

HeyGen and Synthesia: a count, or a code per voice

One documents thirty or more languages for video translation, with cloning and lip-sync in the same sentence. The other publishes a formal name, a native name and a code on each voice. A workflow claim against a catalogue. As of 2026-09-22.

Reaching markets by translating, or by choosingA count attached to translation describes one master, one performance and a localisation stage at the end. A catalogue with codes describes choosing a voice for a market before anything is made.One masterGenerated andapproved once, in itsoriginal language.TranslateThirty or moreMarkets reachedafterwards, withcloning and lip-syncnamed.Or insteadChoose firstA voice picked permarket from acatalogue with codes.
Fig. 1 Translating concentrates the work and the risk in one master; choosing per market spreads both.
Controls documented, model by modelFilled where the model documents that control, hollow where nothing is published about it.Controls documented, model by modelHeyGenSynthesiaWhere they partAudio sourceAudio source — HeyGen: From a speech endpoint, then renderedAudio source — Synthesia: From the script, or uploadedAudio source — Where they part: Different answersVoice sourceVoice source — HeyGen: A recording to clone fromVoice source — Synthesia: A catalogue voice, or a cloned oneVoice source — Where they part: Different answersPer-character bindingPer-character binding — HeyGen: On a stored clonePer-character binding — Synthesia: Not documented by the vendorPer-character binding — Where they part: Only HeyGen answersLanguagesLanguages — HeyGen: A count, attached to translationLanguages — Synthesia: A catalogue with codesLanguages — Where they part: Different answersLip-syncLip-sync — HeyGen: Named, alongside translationLip-sync — Synthesia: The spoken content, framed closeLip-sync — Where they part: Different answers
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 controlHeyGen4 of 5Synthesia4 of 5Where they part5 of 5
Fig. 3 How many models document each control. A hollow column is a statement about documentation, not capability.
HeyGen and Synthesia on the five fields this register keeps, with the gap on each. Recorded 2026-09-22.
FieldHeyGenSynthesiaWhere they part
Audio sourceFrom a speech endpoint, then renderedFrom the script, or uploadedDifferent answers
Voice sourceA recording to clone fromA catalogue voice, or a cloned oneDifferent answers
Per-character bindingOn a stored cloneNot documented by the vendorOnly HeyGen answers
LanguagesA count, attached to translationA catalogue with codesDifferent answers
Lip-syncNamed, alongside translationThe spoken content, framed closeDifferent answers

Inclusion rule. Two entries are given a page together when at least one column puts them at opposite grades of answer. Pairs that agree on every column, or that are both blank throughout, do not get a page. Order. Fixed field order, identical on every side-by-side page.

1Where a language figure sits tells you what it is for

A count attached to translation describes reaching markets by translating a finished master: one performance, one set of frames, and a localisation stage at the end. A catalogue with codes describes choosing a voice for a market before anything is made.

Those are different production plans with different risks. Translating concentrates the work and the risk in one master; choosing per market spreads both, and keeps a bad episode from reaching thirty places at once.

2One threshold, one condition, and both worth copying

One publishes twenty minutes or more of audio for a professional clone, which turns cloning into a booked session rather than a feature. The other publishes a framing condition, saying lip sync performs better with the avatar closer to camera.

Both are sentences that change a plan rather than a preference, and both are rare. Most entries in this register publish neither a threshold on their inputs nor a weak case for their outputs.

3Cloning across thirty languages raises a question neither answers

Naming voice cloning next to a language count implies a performer's voice travelling into markets they never discussed. The mechanics are documented on both platforms and the permission is on neither.

This register records the mechanism because that is what a page can settle. Who may lawfully be cloned, and in how many languages, is decided by a release form that no API quick start contains.

4Each of them on its own

The column this pair was chosen for is languages, and each entry has a page of its own on it. The full row for either, all five columns with the wording behind each cell, is on its model note.

  • 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
  • Voice source
    A voice clone is instant from one recording or professional from twenty minutes or more, and is then passed as a voice idtwo enrolment routes with a thresholdHeyGen, API quick start / 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
  • Voice source
    Voice 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 reachSynthesia, create an avatar / recorded 2026-09-22
  • A framing condition attached to lip-sync
    Lip sync performs best when the avatar is framed closer in the scene rather than positioned far from the cameraSynthesia, create an avatar / recorded 2026-09-22

5Sources

Every cell above is read from the documentation each vendor publishes, on the dates carried by the two model notes. The whole register on one column is on the field note; entries grouped by the shape of their answer are on the routes. Other pairs: D-ID and Hedra, Kling AI and Synthesia.