Synthesia: a catalogue with a code on every voice
Each voice is published with its formal and native language name, a language code, a gender, a name and a voice id. That is the most machine-readable answer in this column, and cloning carries a language list of its own on top of it. 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 of those voices suits a dramatic read rather than a presentation |
| Voice cloning carries its own language list, running from Afrikaans to Zulu | Whether a cloned voice performs equally across that range |
| Lip sync and facial expressions are generated from the spoken content | How the face behaves in a language the avatar 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 code makes a language list something software can check
Publishing a language code beside each voice is a different order of answer from naming a language in prose. A code can be matched against a distribution plan automatically, which means a catalogue of this shape can be audited rather than read.
It also removes the ambiguity that ruins most language claims. A name can mean a market, a script or a dialect depending on who wrote it; a code picks one. That is why this cell sits at the top of the grades this column keeps even though no total appears anywhere.
2Two lists, and they are not the same list
The catalogue covers voices the platform supplies. Cloning has a separate range, described as the same list used for standalone cloning and running from Afrikaans to Zulu. A production reading only one of the two will over- or under-estimate its reach depending on which route it intends to use.
Keeping them apart in the record is deliberate. Where a vendor publishes two ranges, merging them into a single number would be the exact error this register is built to avoid.
3The other entry that publishes names
One more entry answers this column with names. It does so per project rather than per voice, which suits a series with one language and suits a catalogue search much less.
- SceneMixer — a named list, set per project.
- 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
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 languages; everything this vendor publishes about speech is on Synthesia. What counts as documented is on how read.