Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2603.25551

Voxtral TTS

Mistral-AI·:·Alexander H. Liu·Alexis Tacnet·Andy Ehrenberg·Andy Lo·Chen-Yo Sun·Guillaume Lample·Henry Lagarde·Jean-Malo Delignon·Jaeyoung Kim·John Harvill·Khyathi Raghavi Chandu·Lorenzo Signoretti·Margaret Jennings·Patrick von Platen·Pavankumar Reddy Muddireddy·Rohin Arora·Sanchit Gandhi·Samuel Humeau·Soham Ghosh·Srijan Mishra·Van Phung·Abdelaziz Bounhar·Abhinav Rastogi·Adrien Sadé·Alan Jeffares·Albert Jiang·Alexandre Cahill·Alexandre Gavaudan·Alexandre Sablayrolles·Amélie Héliou·Amos You·Andrew Bai·Andrew Zhao·Angele Lenglemetz·Anmol Agarwal·Anton Eliseev·Antonia Calvi·Arjun Majumdar·Arthur Fournier·Artjom Joosen·Avi Sooriyarachchi·Aysenur Karaduman Utkur·Baptiste Bout·Baptiste Rozière·Baudouin De Monicault·Benjamin Tibi·Bowen Yang·Charlotte Cronjäger·Clémence Lanfranchi·Connor Chen·Corentin Barreau·Corentin Sautier·Cyprien Courtot·Darius Dabert·Diego de las Casas·Elizaveta Demyanenko·Elliot Chane-Sane·Emmanuel Gottlob·Enguerrand Paquin·Etienne Goffinet·Fabien Niel·Faruk Ahmed·Federico Baldassarre·Gabrielle Berrada·Gaëtan Ecrepont·Gauthier Guinet·Genevieve Hayes·Georgii Novikov·Giada Pistilli·Guillaume Kunsch·Guillaume Martin·Guillaume Raille·Gunjan Dhanuka·Gunshi Gupta·Han Zhou·Harshil Shah·Hope McGovern·Hugo Thimonier·Indraneel Mukherjee·Irene Zhang·Jacques Sun·Jan Ludziejewski·Jason Rute·Jérémie Dentan·Joachim Studnia·Jonas Amar·Joséphine Delas·Josselin Somerville Roberts·Julien Tauran·Karmesh Yadav·Kartik Khandelwal·Kilian Tep·Kush Jain·Laurence Aitchison·Laurent Fainsin·Léonard Blier·Lingxiao Zhao·Louis Martin
View original source ↗Read source document ↗Export metadata ↓

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 speech tokens with flow-matching for acoustic tokens. These tokens are encoded and decoded with Voxtral Codec, a speech tokenizer trained from scratch with a hybrid VQ-FSQ quantization scheme. In human evaluations conducted by native speakers, Voxtral TTS is preferred for multilingual voice cloning due to its naturalness and expressivity, achieving a 68.4\% win rate over ElevenLabs Flash v2.5. We release the model weights under a CC BY-NC license.

Explore related subjects

cs.AI

Keep this discovery

BibTeXRIS

Mistral-AI, :, Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Henry Lagarde, Jean-Malo Delignon, Jaeyoung Kim, John Harvill, Khyathi Raghavi Chandu, Lorenzo Signoretti, Margaret Jennings, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Samuel Humeau, Soham Ghosh, Srijan Mishra, Van Phung, Abdelaziz Bounhar, Abhinav Rastogi, Adrien Sadé, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Amélie Héliou, Amos You, Andrew Bai, Andrew Zhao, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Arthur Fournier, Artjom Joosen, Avi Sooriyarachchi, Aysenur Karaduman Utkur, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Benjamin Tibi, Bowen Yang, Charlotte Cronjäger, Clémence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Emmanuel Gottlob, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jacques Sun, Jan Ludziejewski, Jason Rute, Jérémie Dentan, Joachim Studnia, Jonas Amar, Joséphine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, Léonard Blier, Lingxiao Zhao, Louis Martin. 2026-03-26. Voxtral TTS. https://arxiv.org/abs/2603.25551

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows

Agentic LLM workflows consist of sequences of model turns interleaved with tool interactions, so their end-to-end completion time depends not only on inference speed but also on when ready turns are released. Most runtimes release each turn immediately upon readiness. Under contention, this eager release policy can accumulate released but unfinished work; once submitted, those turns can no longer be reordered by the workflow-level policy, increasing tail latency. We present a tail-risk-aware turn release scheduling method that jointly decides which ready turn to release next and how much released but unfinished work to maintain. The method uses a mean--Conditional Value-at-Risk (CVaR) objective to capture the evolving tail risk of unfinished workflows, incorporates online estimates of turn work when prioritizing ready turns, and adapts the released work budget to observed queue pressure. We evaluate the method using real agent execution traces from software engineering tasks across multiple LLMs and workflow arrival rates. The method performs comparably to eager release under light load and substantially reduces the P95 of workflow flow time under contention, achieving up to a \(3.50\times\) speedup.

cs.AI↗
arXiv2026

Demystifying the Privacy-Utility Trade-off in LLM Interactions

The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ context-agnostic static rules, causing severe utility degradation. However, the specific mechanisms governing how sanitization impacts downstream performance remain largely underexplored. To address this, we conduct a systematic analysis to deconstruct the privacy-utility trade-off, uncovering three underlying mechanisms: (1) Context-Dependent Utility, which first establishes when to sanitize by revealing that data value shifts from critical constraints to dispensable noise based on user intent; (2) Strategic Adaptation, which subsequently determines how to sanitize by dictating that the choice between removal and replacement depends on the task's reliance on factual integrity versus structural coherence; and (3) Combinatorial Interplay, which finally extends the protection scope by demonstrating that attributes form a semantic web of synergistic dependencies or antagonistic redundancies. Guided by these insights, we introduce an intent-driven local protection framework. By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto frontier.

cs.AI↗
arXiv2026

Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks

The term agent in artificial intelligence lacks a standard definition, complicating the evaluation, comparison, and reproducibility of AI agent research. We address this ambiguity through a survey organized around five dimensions of agenticness: environmental interaction, learning and adaptation, autonomy, goal-directed behavior, and temporal coherence. For each dimension, we examine how the underlying capability has been conceptualized across prior work and synthesize the metrics, benchmarks, and evaluation frameworks used to assess it. This review provides a structured account of the current landscape of agent evaluation, highlighting both established approaches and areas where evaluation remains limited or inconsistent. We additionally introduce the Agent Compendium, a public-facing digital resource that organizes and extends the evaluation methods identified through this review. Together, the survey and compendium provide a common structure for evaluating and comparing agent capabilities across AI systems, supporting more reproducible research, clearer communication, and more systematic study of artificial agents.

cs.AI↗