mlsanityData to 14 Oct 2026

Voxtral TTS

arXiv 2603.25551 ↗First posted 26 Mar 2026cs.AIcited by 0

Not on the map. Why?

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.

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

27 of 29 references.

References · 27

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2017Neural Discrete Representation Learningcited by 4,712
  6. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  7. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  8. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  9. 2021Going deeper with Image Transformerscited by 764
  10. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  11. 2022High Fidelity Neural Audio Compressioncited by 687
  12. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
15 more
  1. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 616
  2. 2024Moshi: a speech-text foundation model for real-time dialoguecited by 568
  3. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 447
  4. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 379
  5. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 300
  6. 2023EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesiscited by 98
  7. 2023SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Modelscited by 87
  8. 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 83
  9. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 49
  10. 2025MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encodercited by 48
  11. 2024TS3-Codec: Transformer-Based Simple Streaming Single Codeccited by 25
  12. 2026vLLM-Omni: Fully Disaggregated Serving for Any-to-Any Multimodal Modelscited by 15
  13. 2024Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspectivecited by 5
  14. 2025MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generationcited by 5
  15. 2024STAB: Speech Tokenizer Assessment Benchmarkcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
  2. 2026Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
  3. 2026Training a Compact, Strong, and Realistic Text-to-Speech Model
  4. 2023A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech
  5. 2024CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
  6. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
  7. 2026Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
  8. 2025Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis