MAI-Voice-2.1 and MAI-Transcribe-2-Streaming released
Microsoft · Model release
Source confirmed
Data as of October 1, 2026 · How the score is built
CurrentProprietaryNon-Reasoning
MAI-Voice-2.1-Flash
Decision readingMAI-Voice-2.1-Flash is tracked, but not publicly ranked yet. Published speech or voice results from MAI-Voice-2.1 launch notes appear below. They do not produce a weighted text-model score.
Released Oct 1, 2026 — see all recent releases
MAI-Voice-2.1-Flash will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Voice benchmark evidence
MAI-Voice-2.1 launch notes is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Languages
23
Model inference latency
About 45 ms
Price
$15 per 1M characters
Microsoft-reported specifications, October 1, 2026; inference is separate from end-to-end generation.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyMAI-Voice-2.1-Flash release history
Radar confirmed these at the source. Use MAI-Voice-2.1-Flash in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
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
- Not publishedMicrosoft model documentation
- Context window
- Not publishedAzure Speech audio model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- textAzure Speech audio model documentation
- Output modalities
- audioAzure Speech audio model documentation
- Parameters
- Not disclosed by the provider
- Availability
- Azure Speech · Microsoft FoundryAzure Speech audio model documentation
- Cloud regions
- Not tracked yet
- Lifecycle
- activeAzure Speech audio model documentation
- 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
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-Voice-2.1-Flash, 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-Voice-2.1-Flash is a proprietary model. No explicit reasoning mode is documented in this profile.
Released October 1, 2026. Azure Speech documents public-preview access through SSML voice selectors and the Speech SDK, with Voice Live support. The launch also lists OpenRouter, Microsoft Foundry, MAI Playground, and Vercel; LiveKit is coming soon. Both versions support 23 languages and gated voice cloning.
MAI-Voice-2.1-Flash is a display-only text-to-speech model. Speech results stay separate from weighted text-model rankings.
MAI-Voice-2.1-Flash sits in the MAI-Voice-2.1 family with MAI-Voice-2.1. Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 1, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does MAI-Voice-2.1-Flash perform overall in AI benchmarks?
MAI-Voice-2.1-Flash has published speech or voice results in MAI-Voice-2.1 launch notes. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Which sibling models are related to MAI-Voice-2.1-Flash?
MAI-Voice-2.1-Flash belongs to the MAI-Voice-2.1 family. Related tracked variants include MAI-Voice-2.1. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does MAI-Voice-2.1-Flash have full benchmark coverage on BenchLM?
No. MAI-Voice-2.1-Flash's speech or voice results appear in MAI-Voice-2.1 launch notes, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of MAI-Voice-2.1-Flash?
MAI-Voice-2.1-Flash's provider has not published a context-window limit for this exact model. The profile leaves the value unavailable instead of borrowing a number from an earlier family member or a third-party route. Maximum output length is tracked separately when the provider documents it.