DEVOURED
MAI-Transcribe-2
Microsoft launched MAI-Transcribe-2, a high-efficiency speech recognition model featuring diarization and word-level timestamps at a cost of $0.10 per hour.
What: MAI-Transcribe-2 offers faster and more accurate speech recognition compared to models like Whisper V3-Large and GPT-Transcribe, with added capabilities for speaker diarization and configurable transcription styles.
Decoder
- Diarization: The process of partitioning an audio stream into homogeneous segments according to the speaker's identity.
Original article
MAI-Transcribe-2 is the fastest, most accurate, and cheapest speech recognition model in the world. It has new features like diarization, configurable transcription styles, and word-level timestamps. MAI-Transcribe-2 can handle a broader range of real-world audio than leading models like Gemini 3.5 Transcribe, GPT-Transcribe, Whisper V3-Large, and ScribeV2. The model costs just $0.10 per hour of audio.
Explore all 54 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi