Sentioscope

Speech and voice controls, as each vendor documents them

Entries handed a recording and asked to fit a picture

Three entries are driven by audio a production supplies. Nothing is generated until a recording exists, which lengthens the front of a schedule and hands a director something to approve before any rendering is paid for. As of 2026-09-22.

A schedule that runs backwards, and what that buysNothing is generated until a recording exists, so casting, a session and a delivered file sit in front of the first frame. In exchange a director approves the performance before any rendering is billed.Cast and recordA performer anda session, bothbefore anythingis rendered.A fileApproveThe performanceis signed offwhile changesare stillcheap.An approved takeGenerateThe picture isfitted to theaudio, and thedriver isalways named.Picture onlyReviseVisual fixesleave theapprovedperformanceuntouched.
Fig. 1 A line change here is a room, a performer and a diary rather than another call.
Audio-driven entries, beside what each vendor says the mouth follows. Recorded 2026-09-22.
ModelWhat the model is givenAnd what the mouth is said to follow
HedraSupplied; audio is requiredThe supplied audio
sync-3Supplied, or read from textThe audio it is given
Wan2.2-S2VSupplied; the model is audio-drivenThe audio input

Inclusion rule. Entries whose documentation describes audio as an input that drives the generation. Entries that synthesise speech from a script in a separate step are on their own route page, because the recording session is the part that differs. Order. Alphabetical by model name.

1Every entry here names its driver, and that is not a coincidence

When the waveform is an input, saying the mouth follows it costs the vendor nothing: it is a description of the interface rather than a promise about a model's internals. All three of these publish a driver statement, and only two entries elsewhere in the register manage one.

That makes this group the easiest to plan around and the hardest to shortcut. The alignment question is settled on the page; the recording question is entirely a production's own, and no parameter will help with it.

2Approval moves to the front, and so does the cost of a change

A director signs off a performance before a frame is billed, which is the strongest argument for this arrangement. The counterpart is that a line change is a re-record, and a re-record is a room, a performer and a diary rather than a call.

One of these says the audio normally determines the video length, which pushes even the pacing decision into the session. A performer who pauses for effect is buying frames, and that is much cheaper to adjust with a microphone in front of them.

3Two of the three are stages rather than generators

Products on this page operate on material: a still, a reference image, or existing footage. They sit late in a pipeline and assume something else made the picture or the portrait, which is a scheduling fact rather than a limitation.

It also explains why voice inventories are thin here. A team reaching this stage usually already has its audio, from a session or from whichever speech service it standardised on, so a catalogue would go unused.

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.

  • Hedra — supplied; audio is required.
  • sync-3 — supplied, or read from text.
  • Wan2.2-S2V — supplied; the model is audio-driven.
  • Audio source
    Avatar videos are driven by audio, and the character in the image will lip-sync and move to the audio providedhanded to the model rather than made by itHedra, avatar video guide / recorded 2026-09-22
  • Shot length set by the take
    The audio normally determines the video length, and omitting the duration follows the source audioHedra, avatar video guide / recorded 2026-09-22
  • Audio source
    The accepted pairs are video with audio, video with text, image with audio and image with textsupplied or read from textSync, sync-3 model documentation / recorded 2026-09-22
  • Length per call on the free tier
    A free account runs one generation a month with a fifteen-second ceiling, with paid limits following the planSync, sync-3 model documentation / recorded 2026-09-22
  • Audio source
    The card describes audio-driven cinematic video generation from an audio input with a reference image and an optional text prompthanded to the model rather than made by itWan-AI, Wan2.2-S2V-14B model card / recorded 2026-09-22
  • A second control alongside the audio
    A pose video argument lets the result follow a pose sequence while staying synchronised to the audioWan-AI, Wan2.2-S2V-14B model card / recorded 2026-09-22

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: Speech from a script, Nothing published.