Served

Afrikaans

17m

speakers, high confidence estimate

100

AI readiness, weighted toward speech

dialects tracked as separate collection targets

The best-served language on the continent, and the control case: where a language is genuinely covered, the only place left to compete is price and domain.

Capability coverage

TextProduction

Speech corporaProduction

TranslationProduction

Speech to textProduction

Text to speechProduction

200+ hours of transcribed speech, commercial voices, big-tech support. Compete on domain, not capability.

The facts

ISO code: afr
Family: Indo-European · West Germanic
Writing system: Latin
Tone: Not tonal
Countries: South Africa, Namibia
Regions: Western Cape, Gauteng, Namibia

Dialects

Cape Afrikaans
Standard Afrikaans

Dialect is self-declared at contribution and then validated against gold-standard clips. Which dialects people turn up to record in is a better demand signal than any desk ranking.

Open corpora that cover it

Common Voice
FLEURS
NCHLT

Voices

No voice yet. Studio recording is the scarcest asset in this whole field — the largest open African corpus holds 11,000 hours and about twenty of them are studio-grade — so voices follow demand rather than leading it.

Help build AI for this language

Same family

Transfer learning follows family, not geography

A Yoruba model helps Igbo less than the shared border suggests, and a Hausa model transfers usefully across Chadic languages in three other countries. These share Indo-European with Afrikaans.

Nigerian English

NigeriaServed

Where the enterprise volume actually sits. Frontier ASR runs 24.7–35% WER on the accent generally — and 40–70% on African named entities, which is the number that decides whether a bank can deploy.

eng-NG
Non-tonal
2 dialects

76 AI readiness

110m

Build with Afrikaans

Take an API key and make the call from your own code, or start in the playground and see what the model actually does with your text.

Get an API key Open the playground