{"slug":"kyutai-stt","name":"Kyutai STT","domain":"kyutai.org","best_rank":10,"categories":1,"entries":[{"slug":"best-open-source-speech-to-text-model","title":"Best open-source speech-to-text model","rank":10,"of":11,"score":1,"appearances":1,"modelRanks":{"Claude":5},"reason":"The best open option for real-time streaming — purpose-built for low-latency (~0.5-2.5s delay) transcription with semantic VAD and word timestamps, CC-BY-4.0, scaling to hundreds of concurrent streams per GPU; fills the production niche (voice agents, live captions) that batch-oriented Whisper-style models handle poorly.","reasons":[{"model":"Claude","reason":"The best open option for real-time streaming — purpose-built for low-latency (~0.5-2.5s delay) transcription with semantic VAD and word timestamps, CC-BY-4.0, scaling to hundreds of concurrent streams per GPU; fills the production niche (voice agents, live captions) that batch-oriented Whisper-style models handle poorly."}],"fixes":[{"model":"Claude","fix":"Covers only English and French at launch-model quality, so it's a specialist tool for live voice products, not a general transcription workhorse."}],"updated":"2026-07-15","api":"https://modelsagree.com/api/v1/best/best-open-source-speech-to-text-model.json"}],"page":"https://modelsagree.com/product/kyutai-stt","check":"https://modelsagree.com/check?q=Kyutai%20STT","updated":"2026-07-16T03:47:53.793Z","attribution":"modelsagree.com, CC BY 4.0"}