Multimodality

Language, voice & vision

Multimodality is a model's ability to handle several content types (text, image, audio, video) within one exchange: describing a photo, analysing a scanned document, commenting on a chart. Recent foundation models are natively multimodal, opening uses impossible with text alone.

In practice at Gensai

Gensai combines modalities per project: voice and text for voice agents, image and text for document analysis.

Same theme

Natural language NLP (Natural Language Processing)Speech recognition (STT)Speech synthesis (TTS)Computer vision AI avatar Voice cloning OCR and IDP (intelligent document processing)

Definition written with AI assistance, checked by Sébastien Lecocq, co-founder of Gensai.

Going beyond the definition?

From concept to project: Gensai builds custom, sovereign, GDPR-compliant AI solutions.

Related services: Voice AI, Chatbots and answer engines

hello@gensai.ai

Tel. : +33 1 62 04 59 32

55 boulevard de Strasbourg, 75010 Paris

Book a 30-minute call