Microsoft launches MAI-Transcribe-2-Streaming, takes #1 streaming STT spot at 2.5% WER
mustafasuleyman · x · 2026-10-02
Microsoft AI's Mustafa Suleyman announced MAI-Transcribe-2-Streaming, which tops Artificial Analysis' streaming WER leaderboard with 2.5% final-transcript accuracy, beating Grok Voice Transcribe 2.0 (2.7%), and returns first partials 0.13s after end of speech vs 0.49s for the prior leader. Suleyman claims it's 55% faster and 60% cheaper than ElevenLabs; it's priced at $0.54/hour of audio, with an invite to build agents on the platform.
Related event: Microsoft's MAI-Transcribe-2-Streaming Tops Speech Transcription Benchmarks(2 posts)→
More from Models
- Leaked-looking model list teases Opus 5.5, Fable 5.1, Sol 6.1 and more — sloppenheimer · 2026-10-02
- JevBench v1.5.4 ditches cost-weighted scoring; Original Jev returns to top of leaderboard — airesearch12 · 2026-10-02
- Dan Shipper says models fail at impersonating him because he agrees only 34% of the time — danshipper · 2026-10-02
- Blogger teases Gemini 4 outputs, says "I'm impressed" — iruletheworldmo · 2026-10-02
- Opus 5.5 high vs GPT-6.1 Sol max: AA data shows Sol's value edge is mostly latency, not intelligence — Wsz2020 · 2026-10-02
- Claude Sonnet 3.7 "returns to its room" and finds notes left in May — repligate · 2026-10-02