# Voxtral TTS

arXiv: https://arxiv.org/abs/2603.25551 · HTML: https://mlsanity.com/paper/2603.25551/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 29 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [Scaling Transformers for Low-Bitrate High-Quality Speech Coding](https://mlsanity.com/paper/2411.19842/) (2024)
- [MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder](https://mlsanity.com/paper/2505.07916/) (2025)
- [TS3-Codec: Transformer-Based Simple Streaming Single Codec](https://mlsanity.com/paper/2411.18803/) (2024)
- [vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Models](https://mlsanity.com/paper/2602.02204/) (2026)
- [Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective](https://mlsanity.com/paper/2401.08833/) (2024)
- [MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation](https://mlsanity.com/paper/2512.10264/) (2025)
- [STAB: Speech Tokenizer Assessment Benchmark](https://mlsanity.com/paper/2409.02384/) (2024)

## Abstract (arXiv)

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.