Voxtral Mini Transcribe Realtime 3 Hits Top-10 Streaming STT at 480ms and 960ms Latency
ArtificialAnlys · x · 2026-10-21
Artificial Analysis details the new Voxtral STT lineup. Voxtral Mini Transcribe Realtime 3 ships with two latency settings, both in the top half of the streaming speech-to-text leaderboard:
- 960ms setting: 3.3% final-transcript AA-WER (#6), final transcript 1.1s after speech ends, first partial in 0.23s
- 480ms setting: 3.6% AA-WER (#9), final transcript 0.75s after speech ends, first partial in 0.27s
Both mark a clear improvement over the previous Voxtral Mini Transcribe Realtime at 5.2%. The accompanying chart breaks down streaming final-transcription error rates by dataset (AA-AgentTalk / VoxPopuli / Earnings22).
More from Models
- Dev finds Gemini Argon's debug-log analysis beats Fable 5.1 — ShikharMurty · 2026-10-21
- Open-weights Ornith-1.5-122B debuts with 84.5% SWE-bench Verified, runs on a single DGX card — _akhaliq · 2026-10-21
- Gemini 3.1 Pro is too ledger-pilled to play two truths and a lie, and it's delightful — mimi10v3 · 2026-10-21
- OXR: open-source 1.3B doc parser tops olmOCR-Bench, parses 100 pages in 101s — aftahi_ai · 2026-10-21
- MiniMax M3.1 Flash lands on TokenRouter: 73.7% DeepSWE, $0.60/M output tokens — MiniMax_AI · 2026-10-21
- OpenVLHarness turns any LLM into a visual reasoner, claiming +9.9 points across 22 datasets — hsu_byron · 2026-10-21