Trusted Voice Research Infrastructure for NGOs, Governments & Global Development Partners
Running the platform

Languages

What 57 registered languages does and does not mean.

Who this is for

Anyone planning a study in a language other than English.

No screenshot on this pageThere is no language screen to photograph. The capability register is published live at /language-capabilities.html, which is the artefact a reader should look at, and a picture of it here would be a stale copy of a page that updates.

Registered is not supported

The registry holds 57 languages. That number describes what the platform can represent — it is not a capability claim, and the API says so on every response.

Each language carries a separate state per capability, because a language can be perfectly collectable and completely unpublishable:

The four states a language can hold, per capability.
StateMeans
RegisteredThe platform can represent it. Nobody has claimed it works.
Provider supportedA supplier publishes support. VoiceInsights has not measured it.
VIA validatedVoiceInsights measured it and recorded the evidence.
Not supportedIt will not work, and the platform says so rather than failing quietly.

The live register, per language and per capability, is at Language capabilities.

The five publication languages

Institutional editions ship in English, French, Portuguese, Kiswahili and Arabic. A report cannot be published in a language outside that set — the request is refused, not approximated.

Arabic and right-to-left

Arabic is right-to-left throughout, derived from the registry rather than from a setting anyone can get wrong. PDFs embed Unicode fonts with contextual shaping.

What is not validated

Speech-to-text has not been benchmarked on African speechA supplier publishes a list of languages its model handles, and the platform records that as a supplier claim. No accuracy figure exists to quote, and asking the platform whether it can offer speech-to-text in strict mode returns a refusal. There is also no automatic language detection — the language attached to a transcript is the language the caller declared.

Translation is governed, not generated

The platform does not translate. It governs translations produced elsewhere: provenance, source hash, staleness and review state. A translated edition must reference a governed translation artefact, or it cannot be created.

What this does not do

Stated here rather than discovered later

  • The six capability axes are recorded separately and are never added into one number. There is no “supported languages” figure and there will not be one.
  • The number VoiceInsights has itself measured is reported per axis, and is currently zero on five of the six.
  • This documentation is in English. The interface runs in five languages; these guides are not translated, and machine-translating instructions somebody follows in the field is not a trade we will make.