# Voxtral Realtime

arXiv: https://arxiv.org/abs/2602.11298 · HTML: https://mlsanity.com/paper/2602.11298/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition](https://mlsanity.com/paper/2010.10759/) (2020)
- [Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset](https://mlsanity.com/paper/2010.11395/) (2020)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [Earnings-22: A Practical Benchmark for Accents in the Wild](https://mlsanity.com/paper/2203.15591/) (2022)
- [Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling](https://mlsanity.com/paper/2509.08753/) (2025)
- [Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2312.17279/) (2023)
- [Turning Whisper into Real-Time Transcription System](https://mlsanity.com/paper/2307.14743/) (2023)
- [The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family](https://mlsanity.com/paper/1604.08859/) (2016)

## Built on by (most cited first, 6 of 6)

- [Raon-Speech Technical Report](https://mlsanity.com/paper/2605.23912/) (2026)
- [X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction](https://mlsanity.com/paper/2608.10878/) (2026)
- [X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR](https://mlsanity.com/paper/2609.08672/) (2026)
- [Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?](https://mlsanity.com/paper/2609.28713/) (2026)
- [Benchmarking Automatic Speech Recognition Tools for Iberian Languages](https://mlsanity.com/paper/2609.36920/) (2026)
- [Factorized Delayed Streams Modeling for LLM-based Streaming ASR](https://mlsanity.com/paper/2610.04333/) (2026)

## 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.