
Same model, different agent: what a harness is
What an AI agent's harness is, where the idea comes from, what we were already doing before LLMs, and why agents now need more control around the model.
Research
Since 2017 we've been researching applied AI for voice, conversation and multimodal agents, with companies, universities and public institutions.
Our own text-to-speech models, brand voices, Spanish accents and co-official languages. It started with a CDTI NEOTEC project and continues in Fonos.
Synthetic voices to train and evaluate fake audio detection systems, with the RTVE-UGR Chair.
Voices that represent more people, like Free the Voices, the first LGBTIQ+ synthetic voice bank, created with LLYC.
Assistant and agent personality, conversational quality and user-centered evaluation methods.
Voice and AI to help information reach more people, like RTVE's election coverage in small towns.
Agents that take on tasks across voice, text and images, while people make the calls that matter. It builds on our voice-and-screen experiences, awarded at the 2019 Alexa Skills Challenge: Multimodal.
A research chair run by RTVE, Spain's public broadcaster, and the University of Granada. Synthetic voices to research fake audio detection. Scientific paper published in 2024.
Synthetic voices for local election and weather news, in Spanish and Catalan.
Research on our own Spanish speech synthesis models, the origin of Fonos.
Collaborations with Universidad Rey Juan Carlos, Universidad de Granada, Universidad de Castilla-La Mancha and Universitat de Lleida.
We research and collaborate with
Articles on voice, conversation and AI.

What an AI agent's harness is, where the idea comes from, what we were already doing before LLMs, and why agents now need more control around the model.

Multimodal agents that combine voice, text, images and screens: which channel to use when, what we know about multimodal design, and the new challenges it brings.

How to design the personality of an AI assistant or agent: role, tone, limits, voice and consistency between what it says and how it sounds. A practical guide.
We join R&D projects, research chairs and funding calls as a technology partner. If you have a research line in speech, language or conversation, let's talk.