MAI-Transcribe-2 released
Microsoft · Model release
Source confirmed
MAI-Transcribe-2
Released Sep 3, 2026 — see all recent releases
Decision reading
MAI-Transcribe-2 is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Data as of September 10, 2026 · How the score is built
Share or export
Voice benchmark evidence
MAI-Transcribe-2 launch evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
FLEURS average WER (60 languages)
5.2%
Independent WER leaderboard rank
#2
Speed vs GPT-Transcribe
10x faster
Price
$0.10 per hour
Provider API ID
MAI-Transcribe-2
Provider snapshot · Microsoft AI · 2026-09-03
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- MAI-Transcribe-2Microsoft model documentation
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- In preview in Microsoft Foundry since September 3, 2026 (version 2026-09-03) with 60 languages, automatic language detection, speaker diarization, word-level timestamps, keyword biasing, and verbatim or clean transcription styles.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordMicrosoft model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Sep 3, 2026 · you are here
MAI-Transcribe-2Not publicly ranked · Price not listed
Base entry
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track MAI-Transcribe-2, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
MAI-Transcribe-2 is a proprietary model with a N/A context window. No explicit reasoning mode is documented in this profile.
In preview in Microsoft Foundry since September 3, 2026 (version 2026-09-03) with 60 languages, automatic language detection, speaker diarization, word-level timestamps, keyword biasing, and verbatim or clean transcription styles.
MAI-Transcribe-2 is a display-only speech recognition model. Transcription results remain separate from BenchLM’s weighted text-model ranking.
The profile has no source-displayable benchmark row yet.
Radar
Full release historyMAI-Transcribe-2 release history
Radar confirmed these at the source. Use MAI-Transcribe-2 in your work? Explore Radar to follow supported changes and choose your alerts.
Frequently asked questions
How does MAI-Transcribe-2 perform overall in AI benchmarks?
MAI-Transcribe-2 does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Does MAI-Transcribe-2 have full benchmark coverage on BenchLM?
No. MAI-Transcribe-2 currently has 0 source-displayable rows across 434 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of MAI-Transcribe-2?
MAI-Transcribe-2 has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.
Compare MAI-Transcribe-2 with every tracked model482 comparisons
Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch MAI-Transcribe-2 in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.