Start where we stand
We begin with Gĩkũyũ because we speak it. We can hear when the model gets a tone wrong, judge a transcript like a native, and build with the community it serves — not at a distance from it.
Aria — twandĩke.
Our languages deserve to be heard — and written.
Afrika Labs is building open speech-to-text for African languages, starting with Gĩkũyũ. Speak naturally, and watch your words become text.
"Aria — twandĩke" is Gĩkũyũ for "Speak — let us write."
Mũgambo · Voice
Speak Gĩkũyũ. We're learning to listen.
Press the microphone, say something in Gĩkũyũ, and hear it back. Transcription switches on the moment our first model finishes training.
Your recording
Audio stays in your browser. Nothing is uploaded until a transcription endpoint is connected — and we'll always say so here first.
Rũthiomi · Language
Speech technology skipped our languages. We're going back for them.
Voice assistants, dictation, subtitles — they exist because someone trained a model. For most African languages, no one has. That is the gap Afrika Labs exists to close, one language at a time.
8M+
people speak Gĩkũyũ today
2,000+
languages are spoken across Africa
217h
of transcribed Gĩkũyũ speech in our first training corpus
Built in the open
We publish our progress, our benchmarks, and our mistakes. Speech technology for African languages should not be a black box owned elsewhere — it should be something the continent can inspect, improve, and own.
A method, not just a model
Every step — gathering voices, training, evaluating with native speakers — becomes a repeatable pipeline. Gĩkũyũ is the proof. Kiswahili, Dholuo, Amharic, and hundreds more are the point.
Rũgendo · The journey
One language proves it. Every language needs it.
-
Now — 2026
Gĩkũyũ v0
Fine-tune our first speech-to-text model on 217 hours of transcribed Gĩkũyũ, benchmark it with native speakers, and switch on live transcription in the demo above.
-
Next
Community voices
Open voice contribution on this site so any Gĩkũyũ speaker can teach the model — more speakers, more dialects, more everyday speech.
-
Then
Kiswahili, Dholuo, and beyond
Run the proven pipeline on the next languages, working with the communities that speak them.
-
The horizon
A speech platform for Africa
An open API and tools — dictation, subtitles, accessibility — so builders everywhere can put African voices into their products.
Aria na ithũĩ · Talk to us
This will take many voices. Add yours.
Whether you speak Gĩkũyũ, build machine learning systems, or want to bring this to your own language — we want to hear from you.