---
type: "post"
id: "microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7"
slug: "microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7"
title: "Microsoft launches MAI-Transcribe-2-Streaming Microsoft launched MAI-Transcribe-2-Streaming and two MAI-Voice models, offering real-time transcription, multilingual text-to-speech, low-latency audio generation, and voice cloning for conversational agents."
description: "Thesis: Microsoft is packaging speech recognition and speech generation as a usable stack for conversational agents."
retrieval_nugget: "Thesis: Microsoft is packaging speech recognition and speech generation as a usable stack for conversational agents."
published_at: "2026-10-02"
updated_at: "2026-10-02"
record_date: "2026-10-02"
date_kind: "published_at"
topics: []
source_urls: ["https://www.testingcatalog.com/microsoft-launches-mai-transcribe-2-streaming"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:0462e4eb3dec2454e3a1d1170c76c77689deab025a69a470a90a752a3c400c04","reviewed_at":"2026-10-02T16:02:05.066Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Microsoft is packaging speech recognition and speech generation as a usable stack for conversational agents.","observed_facts":[{"text":"TestingCatalog reports that MAI-Transcribe-2-Streaming supports 60 languages and starts emitting partial hypotheses just over 100 milliseconds after audio arrives.","source_urls":["https://www.testingcatalog.com/microsoft-launches-mai-transcribe-2-streaming"]},{"text":"TestingCatalog reports that MAI-Voice-2.1 spans 23 languages and 26 locales.","source_urls":["https://www.testingcatalog.com/microsoft-launches-mai-transcribe-2-streaming"]},{"text":"The report lists MAI-Voice-2.1 at $22 and Flash at $15 per million characters, and says all three models are accessible through Microsoft Foundry, MAI Playground, Vercel, and Azure Voice Live.","source_urls":["https://www.testingcatalog.com/microsoft-launches-mai-transcribe-2-streaming"]}],"mechanism":"A streaming transcript can give an agent text to reason over, or act on, before the speaker has finished; speech synthesis then supplies the response in a selected voice.","why_now":"The announced lineup addresses both ends of a live voice interaction, while stated prices and multiple access points give developers practical details for evaluating adoption.","implications":["Builders can assess the offering as a connected speech input-and-output stack rather than as a transcription model in isolation.","The reported access and pricing details let developers compare implementation options, but do not establish operational quality."],"evidence_boundary":"These details come from the supplied TestingCatalog report, which relays Microsoft's claims; the source does not establish independent benchmark performance or production reliability.","watch_conditions":["Check whether independent tests confirm low-latency transcription and speech generation in real multilingual conversations, including when an agent uses tools."],"related_records":[],"new_branch_reason":"The announcement is a distinct analytical record because no prior New Runtime record is supplied; no relationship to earlier coverage is asserted."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7/","markdown":"https://newruntime.com/posts/microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7.md","json":"https://newruntime.com/posts/microsoft-launches-mai-transcribe-2-streaming-microsoft-launched-adb2e7.json"}
---

# Microsoft launches MAI-Transcribe-2-Streaming Microsoft launched MAI-Transcribe-2-Streaming and two MAI-Voice models, offering real-time transcription, multilingual text-to-speech, low-latency audio generation, and voice cloning for conversational agents.

## Retrieval answer

Thesis: Microsoft is packaging speech recognition and speech generation as a usable stack for conversational agents.

Thesis: Microsoft is packaging speech recognition and speech generation as a usable stack for conversational agents. The reported launch pairs MAI-Transcribe-2-Streaming with MAI-Voice-2.1 and MAI-Voice-2.1-Flash. TestingCatalog reports that streaming transcription supports 60 languages and starts emitting partial hypotheses just over 100 milliseconds after audio arrives. It also reports that MAI-Voice-2.1 spans 23 languages and 26 locales.

Mechanism: A streaming transcript can give an agent text to reason over, or act on, before the speaker has finished; speech synthesis then supplies the response in a selected voice. The source says the transcription model revises partial hypotheses as context arrives, while the voice models can retain a speaker identity across supported languages. Why now: The announced lineup addresses both ends of a live voice interaction, while stated prices and multiple access points give developers practical details for evaluating adoption.

First implication: Builders can assess the offering as a connected speech input-and-output stack rather than as a transcription model in isolation. Evidence boundary: These details come from the supplied TestingCatalog report, which relays Microsoft's claims; the source does not establish independent benchmark performance or production reliability. First watch condition: Check whether independent tests confirm low-latency transcription and speech generation in real multilingual conversations, including when an agent uses tools. The announcement is a distinct analytical record because no prior New Runtime record is supplied; no relationship to earlier coverage is asserted.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)