MAI-Transcribe-2
MAI-Transcribe-2 is worth evaluating for vision when its provider route and context window match the workload.
Use it for
- Teams evaluating vision
- Buyers comparing 1 tracked provider route
Do not use it for
- Strict JSON or tool-calling flows
- Family
- MAI
- Released
- 2026-09-03
- Architecture
- Audio / Speech
- Specialization
- speech-recognition
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 1 route · Microsoft Foundry
About
MAI-Transcribe-2 (Azure Speech enhancedMode.model id MAI-Transcribe-2) is Microsoft AI's third-generation speech-to-text / ASR model, announced September 3, 2026. Specialized transcription API, not a chat LLM. First-party: 60 languages; speaker diarization; word-level timestamps; keyword biasing; verbatim/clean transcription styles; code switching; automatic language identification; noise-robust real-world audio. Microsoft reports first place on FLEURS across 60 languages at 5.2% average WER, Artificial Analysis accuracy-latency Pareto leadership, and second place on the Artificial Analysis WER leaderboard. Available to demo via Microsoft Foundry, MAI Playground, and Open Router; Azure Speech docs mark MAI-Transcribe as public preview. Compare it for Speech recognition.
Top use-case fit
Vision
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Microsoft Foundry | - | - | ServerlessPartial |
Available via routers & gateways(5)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong AI Gateway
GatewayMulti-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
Capabilities
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
MAI-Transcribe-2Cheapest of 1 route · Microsoft Foundry