
Festival
The foundational open-source framework for multi-lingual text-to-speech and linguistic research.
Discover the strongest tools and workflows for synthesize speech from text.

The foundational open-source framework for multi-lingual text-to-speech and linguistic research.

The industry-standard multi-engine translation aggregator for real-time web localization.

NVIDIA-powered toolkit for high-performance distributed mixed-precision sequence-to-sequence modeling.

A fast, local neural text to speech system.

Real-time neural text-to-speech architecture for massive-scale multi-speaker synthesis.

The community-powered hub for hyper-realistic voice synthesis and deepfake lip-syncing.

The professional AI vocal platform for music production and artist-first voice synthesis.

Create with the most expressive generative voice AI and protect with advanced deepfake detection, all from one trusted platform.