➡️ This presentation is part of IRCAM Forum Workshops Paris / Enghien-les-Bains March 2026
We will then present PardiSpeech, an updated version of the zero-shot TTS system introduced at the Forum 2025,
now nearing the final stage of development and expected to be ready in autumn 2026.
The presentation will include demonstrations of:
-
a new graphical, web-based, user interface for performing zero-shot synthesis from “arbitrary” English and French voices;
-
the training of initial states from voice examples;
-
a small set of voice control parameters offered by the new model.