MAI-Transcribe-2-Streaming
Notable release: A meaningful new model: a new size or version, or a strong free-to-download model from a known lab.
Microsoft's first model that turns speech into text as it's spoken, offered to developers online rather than as a free download.
Key facts
- Released
- Oct 1, 2026
- What it does
- Listens: Understands speech and other sounds.Makes sound: Creates speech, music or other audio.
View moreView less
- How
- For developers, through an API
- Announced as
- “Our first streaming transcription model debuts at no. 1 on Artificial Analysis”
From trckr's archive of releases before it started watching. Date and details from Epoch AI's database of AI models (CC BY 4.0).
Compare MAI-Transcribe-2-Streaming with
It came out 28 days after MAI-Transcribe-2, the lab's previous model.
The details
Streaming Speech-to-text: Turns spoken audio into written text. Also called transcription or ASR. model from Microsoft, available through API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet. access with no public size or download listed.
Get alerts like this the moment they happen.
From Microsoft and every other major lab.
Free, no account needed. Push, Telegram, Discord, email or RSS.