{"slug": "mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena", "title": "Mistral AI’s Voxtral Mini Transcribe 3 takes second place on Voice Arena leaderboard", "summary": "Mistral AI's Voxtral Mini Transcribe 3, a 4 billion parameter speech model, ranked second of nine models on Voice Arena's diarization and speech recognition leaderboard with a 40.4% Diarization Error Rate, edging out its larger sibling Small Transcribe 3 at 41.1% DER in fourth place. Voice Arena built the evaluation on 139 English-language spontaneous conversations with human-verified references, and both Voxtral models correctly identified speaker count 83.5% of the time. Mistral AI unveiled the Voxtral 3 suite on October 20, 2026, with Mini batch transcription priced at $0.0035 per minute versus $0.004/min for Small and $0.008/min for realtime, though Small held a slim word-accuracy edge on AA-WER at 2.1% versus Mini's 2.2%.", "body_md": "# Mistral AI’s Voxtral Mini Transcribe 3 takes second place on Voice Arena leaderboard\n\nThe 4 billion parameter speech model edged past its larger sibling in an independent test of who said what in real conversations\n\n[Mistral AI](https://cryptobriefing.com/markets/mistral/)’s smallest new transcription model just beat its bigger sibling at one of the hardest jobs in speech recognition. Voxtral Mini Transcribe 3 ranked second out of nine models on Voice Arena’s diarization and speech recognition leaderboard.\n\nThe larger Small Transcribe 3 landed in fourth. In AI, size usually wins the argument. This time, the little one got the last word.\n\n## What Voice Arena actually measured\n\nDiarization is the part of transcription that figures out who is talking and when. Think of a court stenographer who not only types every word but also labels each line with the right speaker’s name.\n\nVoice Arena scores this with a metric called Diarization Error Rate, or DER. Lower is better. It roughly tracks how much of a conversation gets attributed to the wrong speaker, missed, or wrongly flagged as speech.\n\nVoxtral Mini Transcribe 3 posted a **40.4% DER**, good for the number two spot among the nine models tested. Small Transcribe 3 came in at **41.1% DER**, placing fourth on the same board.\n\nVoice Arena built its evaluation on real-world audio from 139 English-language conversations. These were spontaneous exchanges, not scripted reads, and the references were verified by humans.\n\nMini performed particularly well on in-person recordings. Both Voxtral models correctly identified how many speakers were in a conversation 83.5% of the time.\n\nOverlapping speech remains the sticking point. When two people talk at once, the models still struggle to untangle them, and that is flagged as a key focus area for developers.\n\n## The specs and the price tag\n\nMistral AI unveiled the Voxtral 3 suite of speech models on October 20, 2026. Voxtral Mini Transcribe 3 is the flagship, built with 4 billion parameters and designed for batch transcription.\n\n### AI, tech, and the markets they move—in one daily briefing.\n\nDaily. Free. Join 34,000+ readers across crypto, finance, and policy.\n\nThe model supports a 32,000 token context.\n\nPricing is where things get interesting for anyone running transcription at volume:\n\n**Mini batch transcription:** $0.0035 per minute\n\n**Small batch transcription:** $0.004/min\n\n**Realtime transcription:** $0.008/min\n\nSo the cheaper model is also the one that ranked higher on diarization.\n\n## Word accuracy tells a slightly different story\n\nDiarization is only half the picture. The other half is whether the model gets the words themselves right, which is measured by word error rate, or WER.\n\nOn AA-WER, Mini scored 2.2%, ranking fifth. Small Transcribe 3 scored 2.1%, ranking third.\n\nSo the bigger model holds a slim edge on raw word accuracy, while the smaller one does better at keeping speakers straight.\n\nOn the multilingual side, benchmark results show the Voxtral models outscoring Whisper large-v3 on FLEURS WER across 45+ languages. FLEURS is a standard multilingual speech test, and Whisper large-v3 is a widely used reference point in the field.\n\nThat matters because the Voice Arena diarization test was English only.\n\n## What this means for the speech AI market\n\nA 40.4% DER still means a meaningful share of the conversation gets mislabeled, and overlapping speech remains an unsolved problem across the board.\n\nThe test also covered 139 English conversations. That’s a rigorous sample of messy real-world audio, but performance in other languages, accents, or noisy environments may differ.\n\n**Disclosure:** This article was edited by Diego Almada Lopez. For more information on how we create and review content, see our [Editorial Policy](https://cryptobriefing.com/editorial-policy/).", "url": "https://wpnews.pro/news/mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena", "canonical_source": "https://cryptobriefing.com/mistral-voxtral-mini-transcribe-3-voice-arena/", "published_at": "2026-10-28 09:55:37+00:00", "updated_at": "2026-10-28 10:15:21.219651+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "ai-products"], "entities": ["Mistral AI", "Voxtral Mini Transcribe 3", "Small Transcribe 3", "Voice Arena", "Whisper large-v3", "Diego Almada Lopez"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena", "markdown": "https://wpnews.pro/news/mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena.md", "text": "https://wpnews.pro/news/mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena.txt", "jsonld": "https://wpnews.pro/news/mistral-ais-voxtral-mini-transcribe-3-takes-second-place-on-voice-arena.jsonld"}}