Loading
Extremely low-resource
8.2m
speakers, low confidence estimate
5
AI readiness, weighted toward speech
3
dialects tracked as separate collection targets
North-east Nigeria and the Lake Chad basin, where NGO and humanitarian demand is real and durable even where commercial demand is not.
Capability coverage
Under ten hours, benchmark-only presence. Collection required before anything ships.
The facts
Dialects
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
None at scale. Everything for this language has to be collected, which is why it sits where it does in the tiers rather than in a roadmap.
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.
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.