February 14, 2026
Adapting the Mimi Neural Codec for Kikuyu Speech
How we fine-tuned Kyutai's Mimi codec on 750+ hours of Kikuyu audio with a custom pitch-preservation loss — achieving 0.0710 val loss and 1.1 Hz pitch error.
researchvoice-aimimi
Blog
Research updates, technical deep dives, and insights on building AI for African languages.
January 29, 2026
Building Kikuyu TranslateGemma: From 2.29 to 19.61 BLEU
How we fine-tuned Google's TranslateGemma-12B for English-Kikuyu translation, achieving 19.61 BLEU through iterative experimentation and deployed it on Modal.
researchtranslationgemma
January 08, 2026
Building Kikuyu AI: Interview with C-elo's Research Team
How do you build a chatbot that speaks Kikuyu? Our research team discusses the technical challenges and our roadmap for voice AI.
interviewteamresearch
December 22, 2025
Speech-to-Speech AI for African Languages
Our architecture for real-time voice chatbots using the Mimi neural codec, preserving tonal fidelity in Kikuyu.
voice-airesearch
December 10, 2025
The 750-Hour Kikuyu Dataset: African Next Voices
How we're leveraging the African Next Voices initiative's audio corpus to train robust Speech-to-Speech models for Kikuyu.
datasetaudio
December 13, 2025
Announcing C-elo Labs: AI for African Languages
We're launching C-elo Labs to build production AI for African languages — starting with Kikuyu translation, voice chat, and text-to-speech.
announcementcompany