Voice synthesis
Krio Voice
A speech-first model family for natural text-to-speech and conversational voice experiences in Krio and related African languages.
Models
Krio language models for speech, translation, and voice.
NovaxAI builds a family of Krio language models and speech models that can speak, listen, translate, and assist in the languages that communities already live with every day — starting with Sierra Leonean Krio and extending to other African languages.
Which Krio model should you use?
Pick the model that matches your task.
- Krio Voice
- Reading Krio text aloud in apps, IVR systems, and accessibility tools
- Krio ASR
- Transcribing Krio voice notes, phone calls, and field recordings
- Krio Translate
- Converting written Krio to English and back
- Phos
- Transcribing and translating Krio speech in a single step
Why this matters
The future of AI should not be limited to a handful of globally dominant languages. We are building systems that are practical for education, healthcare, public services, customer support, accessibility, and local knowledge work across Africa.
Speech recognition
Krio ASR
An automatic speech recognition system built for real-world African language speech, from call-center audio to field recordings.
Translation
Krio Translate
A multilingual translation model designed to connect Krio with English and other African languages with practical accuracy.
Multilingual AI
Phos
A research-driven language model experience that brings together multilingual understanding, generation, and agentic workflows.