Notes from the lab. How we build AI that speaks Swahili.
Why we are building Waridi
Waridi is an AI research lab training frontier models for human–computer interaction, built around how Africans actually speak. We are starting with voice, and with Swahili.
Read the articleThe problem with "press one"
Phone menus were built to save businesses money, and callers pay the price. A look at how IVR fails people, and what a voice agent should do instead.
Designing voices that sound Tanzanian
How we approach casting, recording and shaping Waridi Sauti voices so they sound like someone from Tanzania, not a generic accent stitched together from everywhere.
Code-switching is not an edge case
Tanzanians mix Swahili and English mid-sentence every day. Here is why Waridi Sikia and Waridi Sauti treat that mixing as normal speech, and how we build for it.
How we collect speech data with consent
Every recording we train on comes from a speaker who understood the request, agreed to it in their own language, and was paid fairly and on time.
Latency budgets for real-time voice agents
A voice agent has roughly a breath's worth of time to answer. Here is how we split that time across listening, thinking, speaking and the phone network.
What good Swahili speech sounds like
Stress, clean vowels, noun-class agreement and the way Tanzanians read numbers, prices and times. The details that decide whether Swahili text-to-speech sounds natural.
Dubbing for African audiences
Good dubbing is more than translated subtitles read aloud. How Waridi Dub approaches timing, lip-sync, cultural adaptation and consented voices for African screens.
Building a Swahili ASR benchmark
Before we can claim Waridi Sikia works, we need a test that reflects real Swahili speech: phone lines, noisy streets, regional accents and constant code-switching.
Voice cloning and consent
A cloned voice can open doors for creators and businesses, or be used to deceive. Here is how we are designing Waridi's cloning so only the voice owner decides.
Why we're starting with Swahili (and Tanzania)
More than 200 million speakers, a working language of the African Union and a bridge across East Africa. Here is why Swahili comes first, and Tanzanian Swahili first of all.
From Dar to Nairobi: dialect coverage
Swahili sounds different in Dar es Salaam, Zanzibar, Mombasa, Mwanza and Nairobi. Here is how we plan to cover that variation instead of flattening it.
A developer tour of the Waridi API
Speech synthesis, recognition, streaming, agents, cloning and dubbing, all from one API. A hands-on walk through the endpoints with curl, Python and Node.