Voxtral Realtime is an end-to-end trained streaming ASR model that achieves Whisper-level transcription quality at 480ms delay after scaling pretraining across 13 languages.
Miguel Del Rio, Peter Ha, Quinten McNamara, Corey Miller, and Shipra Chandra
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Voxtral Realtime
Voxtral Realtime is an end-to-end trained streaming ASR model that achieves Whisper-level transcription quality at 480ms delay after scaling pretraining across 13 languages.