Voxtral Realtime

• URL: http://arxiv.org/abs/2602.11298v1
• Date: Wed, 11 Feb 2026 19:17:10 GMT
• Title: Voxtral Realtime
• Authors: Alexander H. Liu, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Sandeep Subramanian, Soham Ghosh, Srijan Mishra, Abhinav Rastogi, Alan Jeffares, Albert Jiang, Alexandre Sablayrolles, Amélie Héliou, Andrew Bai, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Benjamin Tibi, Clémence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elliot Chane-Sane, Enguerrand Paquin, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Gaëtan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Martin, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Indraneel Mukherjee, Irene Zhang, Jaeyoung Kim, Jan Ludziejewski, Jason Rute, Joachim Studnia, John Harvill, Jonas Amar, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kush Jain, Laurence Aitchison, Léonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Margaret Jennings, Marie Pellat, Mark Prins, Mathieu Poirée, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philomène Chagniot, Pierre Stock, Piotr Miłoś, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Sagar Vaze, Samuel Humeau, Siddharth Gandhi, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Théo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Valeriia Nemychnikova, Van Phung, Vedant Nanda, Victor Jouault, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yihan Wang, Zaccharie Ramzi, Zhenlin Xu,
• Abstract summary: Voxtral Realtime is a streaming automatic speech recognition model.<n>It matches offline transcription quality at sub-second latency.<n>We release the model weights under the Apache 2.0 license.
• Score: 134.66962524291424
• License: http://creativecommons.org/licenses/by/4.0/
• 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 Realtime is trained end-to-end for streaming, with explicit alignment between audio and text streams. Our architecture builds on the Delayed Streams Modeling framework, introducing a new causal audio encoder and Ada RMS-Norm for improved delay conditioning. We scale pretraining to a large-scale dataset spanning 13 languages. At a delay of 480ms, Voxtral Realtime achieves performance on par with Whisper, the most widely deployed offline transcription system. We release the model weights under the Apache 2.0 license.

Related papers

• Real-Time Streamable Generative Speech Restoration with Flow Matching [35.33575179870606]
  Stream$.$FM is a frame-causal flow-based generative model with an algorithmic latency of 32 milliseconds (ms) and a total latency of 48 ms.<n>We show that high-quality streaming generative speech processing can be realized on consumer GPUs available today.
  arXiv  Detail & Related papers  (2025-12-22T14:41:17Z)
• VoXtream: Full-Stream Text-to-Speech with Extremely Low Latency [17.067283475630095]
  We present VoXtream, a fully autoregressive, zero-shot streaming text-to-speech (TTS) system for real-time use that begins speaking from the first word.<n>VoXtream directly maps incoming phonemes to audio tokens using a monotonic alignment scheme and a dynamic look-ahead that does not delay onset.<n>Built around an incremental phoneme transformer, a temporal transformer predicting semantic and duration tokens, and a depth transformer producing acoustic tokens, VoXtream achieves, to our knowledge, the lowest initial delay among publicly available streaming TTS: 102 ms on
  arXiv  Detail & Related papers  (2025-09-19T13:26:46Z)
• CarelessWhisper: Turning Whisper into a Causal Streaming Model [31.38962687054824]
  We present an analysis explaining why it is not straightforward to convert an encoder-decoder transformer to a low-latency streaming model.<n>Our proposed method modifies the existing (non-causal) encoder to a causal encoder by fine-tuning both the encoder and decoder.<n> Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches.
  arXiv  Detail & Related papers  (2025-08-17T09:32:40Z)
• Streaming Non-Autoregressive Model for Accent Conversion and Pronunciation Improvement [52.89324095217975]
  We propose a first streaming accent conversion model that transforms non-native speech into a native-like accent.<n>Our approach enables stream processing by modifying a previous AC architecture with an Emformer encoder and an optimized inference mechanism.
  arXiv  Detail & Related papers  (2025-06-19T20:05:29Z)
• StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling [50.537794606598254]
  StreamMel is a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms.<n>It enables low-latency, autoregressive synthesis while preserving high speaker similarity and naturalness.<n>It even achieves performance comparable to offline systems while supporting efficient real-time generation.
  arXiv  Detail & Related papers  (2025-06-14T16:53:39Z)
• Streaming Audio-Visual Speech Recognition with Alignment Regularization [69.30185151873707]
  We propose a streaming AV-ASR system based on a hybrid connectionist temporal classification ( CTC)/attention neural network architecture. The proposed AV-ASR model achieves WERs of 2.0% and 2.6% on the Lip Reading Sentences 3 dataset in an offline and online setup.
  arXiv  Detail & Related papers  (2022-11-03T20:20:47Z)
• End to End Lip Synchronization with a Temporal AutoEncoder [95.94432031144716]
  We study the problem of syncing the lip movement in a video with the audio stream. Our solution finds an optimal alignment using a dual-domain recurrent neural network. As an application, we demonstrate our ability to robustly align text-to-speech generated audio with an existing video stream.
  arXiv  Detail & Related papers  (2022-03-30T12:00:18Z)
• SoundStream: An End-to-End Neural Audio Codec [78.94923131038682]
  We present SoundStream, a novel neural audio system that can efficiently compress speech, music and general audio. SoundStream relies on a fully convolutional encoder/decoder network and a residual vector quantizer, which are trained jointly end-to-end. We are able to perform joint compression and enhancement either at the encoder or at the decoder side with no additional latency.
  arXiv  Detail & Related papers  (2021-07-07T15:45:42Z)
• Transformer Transducer: One Model Unifying Streaming and Non-streaming Speech Recognition [16.082949461807335]
  We present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. We show that we can run this model in a Y-model architecture with the top layers running in parallel in low latency and high latency modes. This allows us to have streaming speech recognition results with limited latency and delayed speech recognition results with large improvements in accuracy.
  arXiv  Detail & Related papers  (2020-10-07T05:58:28Z)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.