SceneMixer: a preset library, or your own recordings
Two routes are named: a preset voice library, or the user's own recordings. The unusual part is where the sentence lives. It is in a checklist about likeness and publishing risk, which also rules a third route out. As of 2026-09-12.
| What the documentation settles | What it leaves to a take |
|---|---|
| Users are told to use a preset voice library or their own recordings | How many voices the library holds, and which languages they cover |
| Cloning an identifiable voice is treated as a likeness issue, with digital-replica statutes named | Where the line falls between a reference recording and a clone |
| Voice routes are described; persistence between shots is not | How a chosen voice stays with a character across episodes |
Inclusion rule. Only statements found on the vendor page named in the caption, and only ones bearing on this one field. Nothing here is filled in from generated output. Order. In the order the statements arrive on the vendor's page.
1A rule stated as a rule, rather than a feature
Most entries in this column are selling a capability. This sentence is restricting one, and the restriction is where the two permitted routes get named. It confirms a library exists and that supplied recordings are accepted, without describing either.
That is a real difference in reading. A feature page will over-claim and a compliance checklist will under-claim, so the information here is probably conservative and definitely incomplete: no count, no languages, and no statement about how a selection is made.
2Ruling a method out is documentation too
Treating the cloning of an identifiable voice as a likeness question, with United States digital-replica statutes named, is the only place in this register where a vendor says what a production must not do with a voice. Several other entries document cloning as a feature and address permission nowhere.
It leaves a boundary question open in return. A reference recording of a performer and a clone of an identifiable voice are not always easy to tell apart, and the checklist names the risk without drawing the line.
3The others that hand a production a catalogue
Four more entries answer with a library or a list. None of the others states what is not permitted, which is the half this one adds.
- D-ID — a voice id, or a recording by url.
- Hedra — a track, or a voice id from the endpoint.
- PixVerse — a sample, or a built-in voice.
- Synthesia — a catalogue voice, or a cloned one.
- Voice sourceThe guide tells users to use a preset voice library or their own recordingstwo routes named
- What the vendor rules outCloning an identifiable voice is described as a likeness issue, with US digital-replica statutes named
- Per-character bindingNot documented by the vendor (as of 2026-09-12)no public description
4Sources
Read from the languages guide at scenemixer.com on 2026-09-12. The same column across every entry is on voice source; everything this vendor publishes about speech is on SceneMixer. What counts as documented is on how read.