Voxtral
Mistral Voxtral TTS: Open-Weight Voice AI You Can Run Locally
Mistral's March 2026 Voxtral TTS is a 4B open-weight text-to-speech model: voice cloning from 3 seconds, 9 languages, CC BY-NC 4.0. Voxtral 3 has no downloadable weights. How to run the March model, and the open alternatives.
Talk to Your Local LLM: Voice Chat Setup
Under 1 second response time with Whisper + Kokoro TTS + your local model. Full setup guide for Open WebUI voice chat and standalone options. Needs 2-4GB VRAM.
A weekly email with every new guide and measured benchmark.
Subscribe — free, no spam