mlsanityData to 7 Oct 2026

Voxtral Realtime

arXiv 2602.11298 ↗First posted 11 Feb 2026cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

22 of 30 references.

References · 22

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2020Longformer: The Long-Document Transformercited by 3,362
  6. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  7. 2020GLU Variants Improve Transformercited by 1,724
  8. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  9. 2019Root Mean Square Layer Normalizationcited by 1,425
  10. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
  11. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 455
  12. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 391
10 more
  1. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  2. 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 111
  3. 2020Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Datasetcited by 94
  4. 2021SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitioncited by 77
  5. 2021Earnings-21: A Practical Benchmark for ASR in the Wildcited by 60
  6. 2022Earnings-22: A Practical Benchmark for Accents in the Wildcited by 46
  7. 2025Streaming Sequence-to-Sequence Learning with Delayed Streams Modelingcited by 24
  8. 2023Turning Whisper into Real-Time Transcription Systemcited by 23
  9. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  10. 2016The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Familycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Raon-Speech Technical Reportcited by 4
  2. 2026X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Predictioncited by 1
  3. 2026X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASRcited by 0
  4. 2026Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?cited by 0
  5. 2026Benchmarking Automatic Speech Recognition Tools for Iberian Languagescited by 0