microsoft
Microsoft AI: MAI-Voice-2
microsoft/mai-voice-2
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
MAI-Voice-2 is a text-to-speech model from Microsoft AI, listed in the OpenRouter catalog. According to the catalog, it is an expressive voice model intended for conversational assistants, media narration, accessibility, education and other long-form voice work, with support for 15 languages. In measured results reported by the catalog, it performed strongly in a design arena for audio realism and text-to-speech. No independent model card was available in this source pack, so these capabilities and results should be validated on your own workloads before adoption.[1]
Strengths
Limitations
- All evidence comes from the OpenRouter catalog; no independent model card was in this source pack and the catalog description is truncated, so capabilities require validation on real workloads.[1]
- The catalog listing carries an expiration date at the end of 2026; confirm continued availability before depending on it.[1]
Where to use it
Sources
- [1] OpenRouter catalog · Microsoft AI: MAI-Voice-2Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18...
Specifications
- Model ID
- microsoft/mai-voice-2
- Creator
- microsoft
- Added to OpenRouter
- 02.06.2026
- Context length
- 0
- Modality
- text->speech
- Input modalities
- text
- Output modalities
- speech
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- 31.12.2026
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · audiorealismwin rate 61.1% · rank 1 | 1,208Elo | —Not rated | 13.11.2026 |
| Design Arena | models · text-to-speechwin rate 52.8% · rank 2 | 1,166Elo | —Not rated | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Azure | 0 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.