Mistral Voxtral-4B-TTS-2603: text-to-speech model released
Mistral released Voxtral-4B-TTS-2603, a 4B parameter text-to-speech model on Hugging Face under CC-BY-NC-4.0. It is fine-tuned from Ministral-3-3B-Base-2512, served via vLLM, and supports 10 languages.
PUBLISHED2025-11-17
OBSERVED2026-08-11
AGE9mo
SOURCES1
- 4B parameter text-to-speech model, vLLM library
- CC-BY-NC-4.0 license (non-commercial)
- Fine-tuned from mistralai/Ministral-3-3B-Base-2512
- 10 languages: en, fr, es, pt, it, nl, de, ar, hi
- Referenced arxiv paper: 2603.25551
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.