Last refreshed 2026-10-06. Next refresh: weekly.
Why use MAI-Transcribe-2-Streaming on Microsoft Foundry?
Microsoft Foundry offers MAI-Transcribe-2-Streaming with competitive pricing. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.
Compare MAI-Transcribe-2-Streaming across 2 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: MAI-Transcribe-2-StreamingModel ID
MAI-Transcribe-2-StreamingRequest example
Curated snippets for this provider are not sourced yet. Use Microsoft Foundry documentation with model ID
MAI-Transcribe-2-Streaming.Gotchas
- Use provider model ID "MAI-Transcribe-2-Streaming", not the LLMReference slug "mai-transcribe-2-streaming".
Compare MAI-Transcribe-2-Streaming Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Microsoft Foundry | — | — |
| Vercel AI Gateway | — | — |
Capabilities
MultimodalAudio
About MAI-Transcribe-2-Streaming
MAI-Transcribe-2-Streaming is Microsoft AI's first streaming speech-to-text model, launched 1 October 2026. Audio streams over a WebSocket and transcripts return incrementally while the speaker talks, with partial results that are then finalised. It is offered at an introductory $0.54 per hour of audio through the end of 2026.
Get Started
Model Specs
Released2026-10-01
ArchitectureAudio / Speech