Sentioscope

Speech and voice controls, as each vendor documents them

Sora 2 and Wan 3.0: two ways to write a spoken line

Two native-audio entries that tell a writer where the words go. One asks for a dialogue block underneath the prose description with speakers labelled. The other puts the line in the prompt itself, after the word saying. As of 2026-09-22.

A labelled block, against a clause after sayingA shot list written for one syntax has to be converted for the other, and that conversion is done by hand at generation time under deadline, which is exactly where a line gets mangled.Sora 2Wan 3.0Where the line goesA dialogue block under the proseIn the prompt, after the word sayingTwo speakersLabels, with turns alternatedNot addressedSilenceNot addressedHas to be asked for, and costs the samePublished numbers16 or 20 s, to a total of 120Clip window, bytes, and a price statementKeep the line in plain language beside whichever syntax is current
Fig. 1 A production that stores only the rendered prompt has stored the model's format rather than its own script.
Controls documented, model by modelFilled where the model documents that control, hollow where nothing is published about it.Controls documented, model by modelSora 2Wan 3.0Where they partAudio sourceAudio source — Sora 2: With the pictureAudio source — Wan 3.0: With the picture, unless switched offAudio source — Where they part: Different answersVoice sourceVoice source — Sora 2: Nothing documented as an inputVoice source — Wan 3.0: Reference audio, 15 seconds in totalVoice source — Where they part: Different answersPer-character bindingPer-character binding — Sora 2: On the promptPer-character binding — Wan 3.0: On the callPer-character binding — Where they part: Different answersLanguagesLanguages — Sora 2: Not documented by the vendorLanguages — Wan 3.0: Not documented by the vendorLanguages — Where they part: Same answerLip-syncLip-sync — Sora 2: Named only where it failsLip-sync — Wan 3.0: Not documented by the vendorLip-sync — Where they part: Only Sora 2 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 controlSora 23 of 5Wan 3.03 of 5Where they part5 of 5
Fig. 3 How many models document each control. A hollow column is a statement about documentation, not capability.
Sora 2 and Wan 3.0 on the five fields this register keeps, with the gap on each. Recorded 2026-09-22.
FieldSora 2Wan 3.0Where they part
Audio sourceWith the pictureWith the picture, unless switched offDifferent answers
Voice sourceNothing documented as an inputReference audio, 15 seconds in totalDifferent answers
Per-character bindingOn the promptOn the callDifferent answers
LanguagesNot documented by the vendorNot documented by the vendorSame answer
Lip-syncNamed only where it failsNot documented by the vendorOnly Sora 2 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.

1Dialogue syntax is the part of a shot list that travels worst

A labelled block and an inline clause are not interchangeable, and a shot list written for one has to be converted for the other. That conversion is exactly where a line gets mangled, because it is done by hand at generation time under deadline.

The habit that survives a model change is keeping the line in plain language alongside whichever syntax is current. A production that stores only the rendered prompt has stored the model's format rather than its own script.

2Both publish numbers, and they bound different things

One publishes clip lengths of sixteen or twenty seconds extendable to a hundred and twenty, plus how much speech fits four and eight seconds. The other publishes a default, a pricing statement, reference audio limits and a byte ceiling.

Between them a writer can size a scene on one and cost a voice on the other, and neither page carries both halves. Reading them together is how the arithmetic gets finished.

3One addresses two speakers, the other addresses silence

One asks for turns alternated so each line lands on the right face, which is the commonest shot in drama. The other documents the phrasing for asking a shot to be quiet, since audio is on by default and silence costs the same.

Both are unusual sentences, and neither vendor publishes the other one. A production needing both has to take one from each page and treat the combination as its own convention.

4Each of them on its own

The column this pair was chosen for is audio source, 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.

  • How a spoken line is written into a prompt
    Dialogue belongs in a dialogue block below the prose description, with exchanges limited to a handful of sentencesOpenAI, Sora 2 prompting guide / recorded 2026-09-22
  • Shot length a line has to fit
    Generations run 16 or 20 seconds, and an extension adds up to 20 seconds at a time to a total of 120OpenAI, video generation guide / recorded 2026-09-22
  • Two characters in frame
    For multi-character scenes the guide asks for speakers labelled consistently and turns alternated, so each line lands on the right characteraddressed rather than skippedOpenAI, Sora 2 prompting guide / recorded 2026-09-22
  • How a spoken line is written into a prompt
    The worked example puts the spoken line in the prompt itself, after the word sayingAlibaba Cloud, Wan 3.0 API reference / recorded 2026-09-22
  • What choosing silence costs
    Enabling or disabling audio does not affect pricingAlibaba Cloud, Wan 3.0 API reference / 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: Runway and Luma Ray, LTX Studio and Vidu.