Microsoft AI · Speech-to-Text
MAI-Transcribe-1.5
Microsoft AI's new speech-to-text model with state-of-the-art average WER across 43 languages and #1 in 18 of them. Launched at Build 2026 alongside MAI-Thinking-1, MAI-Image-2.5 and MAI-Voice-2.
Open the source ↗Similar Audio & Speech releases
- NVIDIA Nemotron 3.5 Transcribe 30B-A4B
NVIDIA · Open multilingual ASR · Week 45, 2026
- Hy-SimulMT
Tencent Hunyuan · Simultaneous speech translation · Week 45, 2026
- Underdog Bark 3.0
Underdog · Speech Recognition · Week 44, 2026
- FluidVoice 1.6.11
altic-dev · Local Dictation App · Week 43, 2026
- Phonon-2
Fermion Research · Compressed English ASR · Week 41, 2026
- Whistle
Cactus Compute · Tiny On-Device ASR · Week 41, 2026
More from Microsoft AI
- MAI Playground
Microsoft AI · MAI Model Playground · Week 41, 2026
- MAI-Image-2.5
Microsoft AI · Text-to-Image · Week 23, 2026
- MAI-Voice-2
Microsoft AI · Text-to-Speech · Week 23, 2026
- MAI-Thinking-1
Microsoft AI · Reasoning · Week 23, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.