Lingala
ISO 639-3 · lin
RegionDR Congo · Republic of Congo
Speakers70M+
★ First language in publication
bli://thelanguagesweservev0.1
/ The languages we serve
Five hundred languages. One family.
The Bantu language family is one of the largest in the world, spread from Cameroon to South Africa over millennia of migration. We start with the most-spoken and most under-served, and work outward.
- Family 01
- Bantu
- Phylum 02
- Niger-Congo
- Languages 03
- 500+
- Speakers 04
- 350M+
/ 01 · Distribution
Spoken from the Atlantic to the Indian Ocean.
Bantu languages emerged in present-day Cameroon and Nigeria around 3,000–4,000 years ago. The great Bantu expansion carried them south and east, where they evolved into more than 500 distinct languages spoken today across Central, East and Southern Africa.
Despite their reach, only Swahili enjoys meaningful representation in modern NLP datasets. The rest — Lingala, Kikongo, Tshiluba, Shona, Sesotho and hundreds more — are functionally absent.
Bantu language regions · approximateLingala
/ 02 · Languages in scope
Where we are, and where we're going.
Roadmap is rolling. New languages get prioritized as community contributors and partners come on board.
In progress
Swahili
ISO 639-3 · swa
RegionEast Africa · Lingua franca
Speakers200M+
★ Most spoken Bantu language
Kikongo
ISO 639-3 · kon
RegionDR Congo · Angola · Congo
Speakers8M+
Tshiluba
ISO 639-3 · lua
RegionDR Congo (Kasai)
Speakers6M+
Kinyarwanda
ISO 639-3 · kin
RegionRwanda · DR Congo
Speakers12M+
Shona
ISO 639-3 · sna
RegionZimbabwe · Mozambique
Speakers10M+
Zulu
ISO 639-3 · zul
RegionSouth Africa
Speakers12M+
Luganda
ISO 639-3 · lug
RegionUganda
Speakers10M+
Sesotho
ISO 639-3 · sot
RegionLesotho · South Africa
Speakers6M+
Phonology
Seven-vowel system (i, e, ɛ, a, ɔ, o, u). Tonal: high vs. low tones distinguish meaning. Limited consonant clusters.
Morphology
Agglutinative. Noun-class system characteristic of Bantu languages, with paired singular/plural prefixes and class-agreement on verbs and adjectives.
Orthography
Latin alphabet, with several conventions in use. Tonal marking is inconsistent in everyday writing — a known challenge for ASR and TTS systems.
NLP challenges
Sparse high-quality corpora, code-switching with French, dialectal variation between Kinshasa and upriver Lingala, and limited speech data.