Hardware
Releasing vui an open source voice mode 300M TTS model Runs on a single consumer gpu / apple sillicon Context aware speech 6 minutes of cont…
Jeremy Howard announced the release of Vui, an open-source voice mode text-to-speech (TTS) model with 300 million parameters that can run on consumer GPUs and Apple Silicon. The model features context
Jeremy Howard announced the release of Vui, an open-source voice mode text-to-speech (TTS) model with 300 million parameters that can run on consumer GPUs and Apple Silicon. The model features context-aware speech generation and supports approximately 6 minutes of continuous audio processing. This release aims to democratize advanced voice synthesis by making it accessible to developers without requiring enterprise-level hardware.
Source: Jeremy Howard (X) | 2026-06-03