About Notes Turaco Contact RC 9251155

Turaco

A text-to-speech system for Nigerian languages, starting with Hausa.

Why voice

Millions of Nigerians are locked out of digital education, health information, and commerce because those systems only speak English. Voice removes the literacy barrier and the language barrier at once.

Where it stands

Language
Hausa
Corpus
WAXAL
Licence
CC BY 4.0 and CC BY-SA 4.0
Duration
10.45 h across eight speakers
Under thirty seconds
4.38 h
Speech type
Read: phonetically balanced scripts, studio, voice actors
Stage
Data verification
Next
Conversational data collection

Hausa is first. The Hausa text-to-speech portion of WAXAL is 10.45 hours across eight speakers, of which 4.38 hours sits in clips under thirty seconds.

What exists in the open data is read speech: phonetically balanced scripts, recorded in studios, by voice actors reading. What it lacks is how people actually speak: the hesitations, the register shifts, the code-switching between Hausa and English mid-sentence, the difference between explaining something to a child and explaining it to a stranger.

10.45 hours, of which 4.38 usable without segmentation. Enough to establish a baseline. Not enough to train a production voice. Closing that gap is what the collection work is for.

A system trained only on read speech reads. It doesn’t talk.

WAXAL. Collected by Makerere University, the University of Ghana, Digital Umuganda, Addis Ababa University, AIMS Senegal, Media Trust and Loud and Clear. Funded by Google and the Gates Foundation. Partner institutions retain ownership of the data they collected. Released under CC BY 4.0 and CC BY-SA 4.0.

What we’re solving next

Conversational nuance.

Collecting and processing high-quality Hausa audio that captures everyday speech rather than scripted speech. This is the work that decides whether Turaco is usable or merely demonstrable.

Turn-taking.

A system that speaks but cannot stop speaking is not a conversation. Detecting when a person begins talking, yielding, and resuming coherently is a separate problem from synthesis, and we’re treating it as one.

Language order.

Hausa first. Nigerian Pidgin next.

The family

Turaco is the family. Species denote tier.

  • Turaco Violet — open. Named for the Violet Turaco, a West African species common in Nigeria.
  • Turaco Great Blue: frontier tier. More expressive voices, conversational turn-taking, lower latency, custom voices.

What’s open, what isn’t

Terms

Models are open. Inference is available. The conversational data we collect stays with us. It is the work we are doing, and it is what funds the next language. What we publish is what we learn: research, findings, methods, and the openings we can’t take ourselves.

Models
open
Inference
available
Conversational data
stays with us
Published
research, findings, methods

Open

Contact

This work needs native speakers, recording capacity, compute, and people who know these languages better than any dataset does. If that’s you, or if you’re working on the same problem from another direction, we’d like to hear from you.