microsoft
Microsoft AI: MAI-Voice-2-Flash
microsoft/mai-voice-2-flash
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Per its OpenRouter catalog listing, the only evidence in this source pack since no independent model card was available, microsoft/mai-voice-2-flash is a low-latency text-to-speech model from Microsoft AI. It converts text input into expressive 24 kHz mono speech and is positioned for interactive uses such as voice agents, assistants, call centers, accessibility and narration. OpenRouter also reports Design Arena entries in audio-realism and text-to-speech categories; treat those as arena measurements rather than vendor-verified claims, and validate latency and voice quality on your own workloads.[1]
Strengths
Limitations
- Evidence comes only from the OpenRouter catalog; no independent model card was available in this source pack, so reported capabilities need workload-level validation.[1]
- The catalog description is truncated, so details such as full language or voice coverage remain unknown.[1]
- The listing carries an expiration date of 2026-12-31, which may limit long-term availability.[1]
Where to use it
- Potentially a good fit for voice agents and interactive assistants where response latency matters, per the catalog's positioning.[1]
- Worth evaluating for call-center and accessibility speech output, pending in-house quality testing.[1]
- A candidate for narration and other interactive spoken-content applications, subject to validation on real workloads.[1]
Sources
- [1] OpenRouter catalog · Microsoft AI: MAI-Voice-2-FlashSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...
Specifications
- Model ID
- microsoft/mai-voice-2-flash
- Canonical ID
- microsoft/mai-voice-2-flash-20260723
- Creator
- microsoft
- Added to OpenRouter
- 23.07.2026
- 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 51.2% · rank 2 | 1,137Elo | —Not rated | 13.11.2026 |
| Design Arena | models · text-to-speechwin rate 43.8% · rank 3 | 1,125Elo | —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 | — | — | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.