Synthesia: a catalogue entry, or a clone with its own reach
Two routes, each documented with a range. The catalogue lists every voice with a language name, a code, a gender, a name and an id. Cloning carries a separate list, described as the same one used for standalone cloning. As of 2026-09-22.
| What the documentation settles | What it leaves to a take |
|---|---|
| Each voice is listed with a formal and native language name, a code, a gender, a name and an id | Which entries suit a dramatic read rather than a presentation |
| Voice cloning carries a language list of its own, running from Afrikaans to Zulu | How faithfully a cloned voice performs across that range |
| Lip sync and facial expressions are generated from the spoken content | How the face behaves with a cloned voice it was not built around |
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 browsable inventory, which is rare in this column
Everywhere else in this register a catalogue is asserted or hidden behind an endpoint. Here it is published per voice with enough structure to be filtered: a language code, a gender and a stable id. A production can shortlist before it signs anything, which is the difference between choosing a voice and discovering one.
Structure also makes the inventory auditable over time. An id that disappears is visible; a voice quietly replaced behind a claim of broad support is not.
2Two routes with two ranges is a distinction worth keeping
The catalogue and the cloning list are not the same list, and the cloning one is described in the sweeping terms the catalogue avoids. A production reading only one will misjudge its reach, in whichever direction it happened to read.
The register keeps them separate for that reason. Two published ranges collapsed into a single number is the error this column exists to prevent, and it is an easy error to make because both sentences sit near each other on the vendor's pages.
3The others that hand a production a catalogue
Four more entries answer with something to choose from. This is the only one whose inventory is published in enough structure to be filtered before any commitment.
- 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.
- SceneMixer — a preset library, or the user's own recordings.
- LanguagesEach 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 codes
- Voice sourceVoice 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 reach
- Lip-syncLip sync and facial expressions are generated from the spoken contentdriven by the script
4Sources
Read from the voices reference and avatar documentation at docs.synthesia.io on 2026-09-22. The same column across every entry is on voice source; everything this vendor publishes about speech is on Synthesia. What counts as documented is on how read.