Mid-tier Anthropic model for everyday work, coding and document creation, with a 1 million token context window
MAI-Transcribe-2-Streaming
New· 4Microsoft AI's real-time speech-to-text model for voice agents, transcribing 60 languages with continuous language detection
- United States
- Redmond, Wa
- Speech Recognition Software
- Artificial Intelligence Software
About MAI-Transcribe-2-Streaming
Voice agents that need to start thinking before a caller has finished speaking are the use case behind MAI-Transcribe-2-Streaming, a real-time speech recognition model that Microsoft AI, the model lab inside the company, released on 1 October 2026.
Partial results in about a tenth of a second
Instead of waiting for a speaker to stop, the model returns first hypotheses, called partials, in just over 100 milliseconds. As more audio comes in the partials are corrected, and a settled transcript is committed afterwards. Microsoft says this lets a voice agent begin reasoning or calling tools while the caller is still talking.
Sixty languages with continuous detection
Sixty languages are covered, and the spoken language is identified continuously, so a conversation can change languages without any reconfiguration.
Microsoft's claims
Microsoft states that on Artificial Analysis the model holds first place for accuracy, for final and partial transcripts alike, and that in its internal tests text shows up twice as quickly as it does with the nearest rival. These are Microsoft's claims, and a team with a particular accent mix or noisy line would want to test it on real audio.
Where to get it
The model is offered through Microsoft Foundry, the MAI Playground, Vercel and Azure Voice Live, and LiveKit is listed as coming soon. Pricing is introductory through the end of 2026. The weights are not published, so it is a hosted service only. A sibling called MAI-Transcribe-2 exists without streaming, which is the one for recordings processed after the fact rather than live conversations.
TrustList summary
MAI-Transcribe-2-Streaming is a real-time speech recognition model from Microsoft AI, the company's in-house model lab, released on 1 October 2026. The model covers 60 languages and keeps detecting which one is spoken, so a call can change language midway without reconfiguration. Without waiting for a speaker to finish, it returns partial results in just over 100 milliseconds, refines them as more audio arrives, and then commits a stable transcript.
Features
- Streaming transcripts: partial results are revised as audio arrives, then committed as a stable transcript.
- Language detection: continuous detection across 60 languages, so the language can change in the middle of a conversation.
- Agent timing: Microsoft says voice agents can start reasoning or calling tools before the caller finishes speaking.
- Access: Microsoft Foundry, MAI Playground, Vercel and Azure Voice Live are routes to it, and LiveKit is listed as coming soon.
Clients
Developers building voice agents and real-time transcription.
Key facts
- Released: 1 October 2026
- Relationship: a separate product from the non-streaming MAI-Transcribe-2
- Weights: not published
Microsoft says it ranks first for accuracy on Artificial Analysis and that words appear twice as fast as with its closest competitor. These are Microsoft's own statements, and no independent press report had been found.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
MAI-Transcribe-2-Streaming launches
Categories & features
- United States
- Redmond, Wa
- Speech Recognition Software
- Artificial Intelligence Software
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/4/2026
What the business tells TrustList
- Founded
- 2026 (0 years) evidence sent
Request a demo or quote from MAI-Transcribe-2-Streaming
Reviews
Write the first review of MAI-Transcribe-2-Streaming
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about MAI-Transcribe-2-Streaming.
MAI-Transcribe-2-Streaming alternatives
Similar listings buyers compare against this one.
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Lower-cost sibling of Cohere's Embed 5 Pro, for high-volume multimodal embedding and indexing across 100+ languages
Black Forest Labs' image generation and editing model with bounding-box layouts, multiple reference images and 4K output
Smaller, latency-optimised Cloudflare decision model that returns probability-scored classifications of text or images
Cohere's larger multimodal embedding model for enterprise search and retrieval, handling text, images and documents in 100+ languages
Diffusion language model from Inception for enterprise teams building real-time voice agents, announced in September 2026
Microsoft AI's text-to-speech model for keeping one voice across 23 languages, with voice cloning from short audio
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- More United StatesBack to the ranked category
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.