BantuNomics Sign in
B
BantuNomics
Body & Health · BTS-BH100
Partnership
Bantu Body & Health · BTS-BH100 · standardized clinical-language infrastructure

Body parts and health symptoms,
standardized across 21 Bantu languages.

BantuNomics maps body parts, symptom families, patient-report phrases, noun-class grammar, plural forms, concord patterns, and native audio into one governed substrate. It gives health AI the clinical language layer it cannot scrape: what hurts, where it hurts, how a patient says it, and how the sentence must agree in the language.

The whole family — click one, or watch it rotate
~235M Speakers
21 Languages
15 Countries
1,106 Real ways patients say things
Language Country Speakers Body terms Phrases
🇰🇪
Swahili (Kenya)
Kiswahili · G42
Kenya · Tanzania 100M 80 174
🇺🇬
Swahili (Uganda)
Kiswahili · G42
Uganda 100M 80 174
🇷🇼
Kinyarwanda
Ikinyarwanda · JD61
Rwanda · DR Congo · Uganda 15M 80 173
🇲🇼
Chewa / Chichewa
Chichewa · N31
Malawi · Zambia · Mozambique 14M 80 175
🇱🇸
Sesotho
Sesotho · S33
Lesotho · South Africa 13.7M 85 175
🇧🇮
Kirundi
Ikirundi · JD62
Burundi · Rwanda 12M 81 172
🇿🇦
isiZulu
isiZulu · S42
South Africa 12M 91 175
🇺🇬
Luganda
Oluganda · JE15
Uganda 10M 80 175
🇿🇼
Shona
chiShona · S10
Zimbabwe · Mozambique 9M 80 175
🇧🇼
Setswana
Setswana · S31
Botswana · South Africa 8.2M 80 175
🇿🇦
isiXhosa
isiXhosa · S41
South Africa 8.2M 85 175
🇰🇪
Gikuyu
Gĩkũyũ · E51
Kenya 8.1M 87 175
🇿🇦
Tsonga (Xitsonga)
Xitsonga · S53
South Africa · Mozambique · Zimbabwe 7M 80 175
🇿🇦
Sepedi (Northern Sotho)
Sesotho sa Leboa · S32
South Africa 4.7M 80 175
🇿🇲
Bemba
IciBemba · M42
Zambia · DR Congo 4.1M 100 185
🇺🇬
Runyankore
Runyankore · JE13
Uganda 3.4M 80 174
🇸🇿
Siswati (siSwati)
siSwati · S43
Eswatini · South Africa 2.4M 108 185
🇿🇼
Northern Ndebele (isiNdebele)
isiNdebele · S408
Zimbabwe 1.6M 80 175
🇿🇲
Luvale
Luvale · K14
Zambia · Angola 1M 80 175
🇿🇲
Chilunda (Lunda)
Chilunda · K14
Zambia · Angola · DR Congo 500K 80 175
🇿🇲
Kaonde (Kikaonde)
Kikaonde · L41
Zambia 240K 80 175
👆 Click any part on the body above — its exact word, plural and grammar appear here, with the real native variants patients use.

Views cycle on their own — front, back, internal, brain; the language rotates, or pick one above. Click a part to inspect it.

02 — The blindness you can't see

Fluent isn't safe.

Bantu languages aren't built like English. Meaning is carried by syllables, noun classes, and verb grammar that flat training text quietly throws away. So a model can sound fluent and still be unable to do the basic clinical things — and, worse, it doesn't know it can't. It answers confidently. In a consultation, confidently wrong is dangerous.

Failure 1

It names the wrong body part.

Ask for "calf" and a model hands back the word for a baby cow. One spelling, many meanings — and no way to tell which one a clinician means.

Failure 2

It can't form the sentence.

"The joints ache" needs noun-class agreement the model never learned. It produces grammatical nonsense a patient won't understand — or trust.

Failure 3

It can't hear the patient.

Real patients switch between Bantu and English mid-sentence. There is almost no data teaching a model to follow it — so it mishears the symptom.

1 / 12 attested clinical phrases the best frontier model produced in our first cross-frontier run
0 what most models produced — while fabricating confidently

We ran the same clinical prompts across frontier models. One translated “fainting” as the word for “to die.” In a consultation, a clinician cannot tell fabricated from correct.

This isn't a long-tail edge case. It's hundreds of millions of speakers — ~235M across these 21 languages alone — and the exact place your health AI most needs to be right.

One anchor · measured · BH-AI v1

A living platform, growing on three axes.

See the coverage matrix →
Reach
21 languages

All aligned to the same English anchor — every one is Anchored. New languages join comparable from day one.

Scope
328 units

143 concepts + 185 phrases. A living standard — it widens by version.

Depth
8 voicing

Languages with native audio underway — deepening Anchored → Filled → Voiced → Verified.

03 — And you can't scrape your way out

There is no dataset for this.

Clinical Bantu, natively attested and grammatically correct, isn't sitting on the web waiting to be crawled. To build it yourself you would need all of this — and years:

📐

A linguistic standard

one shared structure so 21 languages line up — not 21 incompatible word lists.

🌍

Native speakers, 20 countries

found, paid, and verified — for terms, grammar, and voice. Relationship work, not a crawl.

🛡️

Consent infrastructure

informed, revocable, de-identified — the gate your own safety review will demand.

🎙️

A recording program

native voice, including the code-switch your models have never heard.

We already did. Here's what your model gets ↓

One clinical take · six functions

One consented recording does the work of six datasets.

A patient names a symptom in their language, then crosses to the English clinical term — in one take. We capture the switch, the meaning, and the structure.

01Clinical-term ground truth
02Code-switch clinical ASR
03Bantu-accented English
04FSI alignment target
05Clinical pronunciation / TTS
06Turnkey ASR benchmark
Hear one take do the work →
What's actually in the box

Not a glossary. A structured clinical corpus.

Every concept is addressable by a stable ID and carries layers — terms, phrases, verbs, grammar, attested evidence, voice. You license queryable infrastructure, not a flat file.

6,956
Aligned translations
English ↔ family, ID-keyed
286
Clinical concepts
frozen, shared anchor
283
Body terms
per language
185
Clinical phrases
patient-report + clinical
81
Health verbs
193 applied frames
581
Attested lexemes
with source + evidence
148
Grammar examples
concord, made explicit
9,050
Native audio takes
two modes · live, growing nightly

The clinical map

286 concepts spanning 7 domains — anatomy to symptoms to care.
External Anatomy
112
75/112 curated
Internal Anatomy & Systems
38
23/38 curated
Functions & Processes
19
10/19 curated
Symptoms & Signs
33
6/33 curated
Conditions & Injuries
26
7/26 curated
Clinical Workflow & Care
49
1/49 curated
Patient & Demographics
9
0/9 curated

The full clinical domain is mapped. Anatomy is deep today; the symptom, condition and care layers are scaffolded and fill with each partnership cycle — which is exactly what a subscription funds.

The same idea, the whole family at once

Pick a body part. Watch your model's blind spot fill in.

One clinical concept, resolved across every language at the same time — the family-scale alignment your model needs and can't get anywhere else.

languages · native variants

Every word carries a stable ID — so you can license and query this like infrastructure, not a spreadsheet. See all 286 concepts →

05 — Not just words

It doesn't just match a word. It builds the sentence.

A word list can't reason. This carries the verbs and grammar a model needs to produce a correct clinical sentence — and the attested evidence to check itself against.

🔤283

Every part, correctly named

so it stops guessing the body

💬185

The sentences patients say

real clinical phrasing, not paraphrase

⚙️81

The verbs to build with

generate, don't echo

🧩148

The grammar that makes it correct

concord, not nonsense

🧠399

Verbs used in context

how a clinician actually says it

📚581

Dictionary-grounded evidence

attested, not invented

Watch it build the sentence

Your model doesn't retrieve these. It generates them.

Each below is a real clinical sentence built from the health-verb grammar — same machinery, any symptom, in every language. The morphology equation is the recipe.

Ache S2 + S3 + S5 + S8[-a] [S4 blocked]
Ifilundwa filekalipa.
“Pain in the joints”
Bleed S2 + S3 + S5 + S8[-a] [S4 blocked]
Umona ulesuma
“Blood is coming from the nose.”
Swell
Amakasa ayafimbile.
“Swollen feet”
Cough
Pali icikolala pamukoshi
“There is phlegm in the throat.”

193 applied verb frames · 561 attested lexemes · 11 training-ready views — a generative engine, not a lookup table.

Real patients, not one textbook form
1,106

different real ways to say the same clinical thing — kept, not collapsed. Your model learns how people actually speak across the family, each source-attributed to a named speaker.

🇿🇲 Chilunda
Collins Chisoya + Harrison Kalichi
247 variants
🇿🇼 Northern Ndebele (isiNdebele)
Shammah
229 variants
🇧🇼 Setswana
Tshepho
210 variants
🇷🇼 Kinyarwanda
Pacifique + Uwayisenga
209 variants
🇺🇬 Luganda
Catherine
207 variants
Real people, named and credited
8

native speakers building and verifying these languages so far — fairly paid, consent-first. This is sourced, not scraped.

CatherineCollins ChisoyaHarrison KalichiMusa DubePacifiqueShammahTshephoUwayisenga
06 — The part no one else has

And we're teaching it to hear the patient.

Native speakers record every concept and phrase twice — once in Bantu, once as a real patient speaks it: Bantu, then switching to English mid-sentence — with the exact switch point captured. It's the code-switch data your voice models have never had. Consent-first; in active collection, scaling with partnership.

  • ✓ Native voice at 48 kHz · two modes per item
  • ✓ The switch point captured — clean for ASR, TTS, translation
  • ✓ Consent-first · de-identified · grows with the partnership
A real patient utterance, captured cleanly
🔴 Bantu — "Gotsi"switches ➜English — "back of head"

The Bantu and English halves are separately usable — exactly what a voice model needs to learn the switch.

Status: active, consent-first collection — we don't oversell it as finished.
07 — Safe to ship

It clears your safety review before you ask.

This is language infrastructure — not patient data, not PHI.

Body-part words, symptom phrasing and clinical language — never medical records or identifiable patient information. It sits outside HIPAA / medical-records regimes. It's the substrate your health AI is built on, not health data itself — so it won't drag a regulatory review.

🤝

Informed consent

Every contributor consents — including voice — and can revoke. Deletion-on-request is honored.

🛡️

De-identified by contract

Speaker identity, raw audio paths and internal IDs never leave the server.

⚖️

Fairly sourced

Native contributors fairly compensated; voluntary, with grievance and withdrawal channels.

🔒

This is the public view. There's a lot more inside.

A Pilot opens the data room across every domain: per-record provenance, the full per-language matrix, native audio samples (Bantu-only + code-switch), live coverage, and exports — to evaluate on your own infrastructure. A Full Annual Subscription license is the entire program, uncapped.

08 — Partner

Be the lab whose health AI is actually safe in Bantu.

One substrate, three reasons it matters to you. Evaluate it on your own infrastructure — data access only, no black box — then license it family-wide.

If safety is the bar

Anthropic

A verified, consented clinical lexicon your model won't hallucinate — the grounding that makes Bantu health assistance safe to ship.

If scale & voice is the bar

OpenAI

Family-wide breadth plus the code-switch audio your voice models need for real African clinical speech.

If clinical reasoning is the bar

Google · DeepMind

Concept→phrase→verb structure and a body-figure grounding surface for multilingual clinical models and Africa health programs.

See your own model fail it — then fix it.

Scoped, de-identified data access — no black box. A Pilot opens every domain, sampled, including this one; the Full Annual Subscription license is the entire program.

Start your free evaluation →

Language infrastructure — not patient data / not PHI. Native-speaker audio program in active, consent-first collection.

Access

Start where you are.

Prove it free, validate it on your own data, or license the whole program.

01 · Free
Evaluation

Score your model against the foundational layer — the Alphabet Test and the L26 Lite suite, with saved results. Self-serve, no cost.

Start evaluating →
Most labs start here
02 · 75 days
Validation Pilot

Three languages you choose — and everything we hold for them. Measured on your own held-out data.

Scope a pilot →
03 · Program
Full Annual Subscription

Every product, every language, the full consented corpus — and everything curated while you're subscribed.

Start a Full Annual Subscription →