DataBubble·

Model Detail

Voxtral-4B-TTS-2603

▲ 2.8%

Provider: MistralCategory: audioPipeline: text-to-speechParameters: 4B

Downloads

Likes

718

Day

+2.8%

Week

+122.6%

Month

+0.0%

Download History

Research Paper

arXiv: 2603.25551→

Voxtral Realtime

arXiv:2602.11298v3 Announce Type: replace Abstract: We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows, Voxtral Realti

arxiv6d ago

Voxtral TTS

arXiv:2603.25551v2 Announce Type: replace Abstract: We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of semantic sp

Related Models

Mistral-7B-Instruct-v0.3

Mistral · 2.3M downloads

Voxtral-Mini-4B-Realtime-2602

Mistral · 869K downloads

speaker-diarization-3.1

pyannote · 10.8M downloads

Kokoro-82M

hexgrad · 9.8M downloads