MAI-Transcribe-2Microsoft AI
|
SpeechData.aiSpirelight ApS
|
|||||
Related Products
|
||||||
About
MAI-Transcribe-2 is Microsoft AI’s most capable transcription model yet, designed to deliver fast, accurate speech recognition across a broad range of real-world audio. It supports speaker diarization to distinguish speakers and attribute words to the right person, along with word-level timestamps for precise alignment, search, navigation, and editing. Keyword biasing helps recognize domain-specific terminology, abbreviations, names, and other terms that can be difficult to distinguish from context alone. Developers can choose between configurable transcription styles: a verbatim setting that preserves filler words and false starts for compliance and analysis, or a clean setting that removes fillers for more readable captions, notes, and published transcripts. The model supports code-switching for conversations that naturally move between languages, including blended language pairs such as Hinglish and Spanglish, and can automatically identify the language being spoken.
|
About
SpeechData.ai is a commercial catalogue and collection service for conversational speech data used to build and evaluate ASR, TTS and other voice-AI systems. Its website lists 60 conversational datasets across 60 languages and dialects, totaling 73,000 audio hours from 7,250 speakers. Listings describe spontaneous two-person recordings, dual-channel audio, time-aligned human-verified transcripts, speaker metadata and consent documentation, with catalogue prices of USD 60–95 per audio hour. Buyers can request samples and commission additional collection to a brief. The provider also offers transcription and audio annotation. Typical buyers include teams sourcing speech for model training and evaluation. Dataset availability, licensing and final price depend on language, collection scope and the terms agreed for the project.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Not Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Developers, enterprises, and product teams seeking to build fast, multilingual speech-to-text applications with speaker identification, precise timestamps, and robust transcription in real-world conditions
|
Audience
Teams procuring conversational speech data or speech collection, transcription and annotation services for ASR, TTS and voice AI training and evaluation.
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Not Supported
|
|||||
Screenshots and Videos |
Screenshots and VideosNo images available
|
|||||
Pricing
No information available.
Free Version
Not Supported
Free Trial
Not Supported
|
Pricing
USD 60 per audio hour
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationMicrosoft AI
Founded: 2024
United States
microsoft.ai/news/mai-transcribe-2-is-the-fastest-most-accurate-and-cheapest-speech-recognition-model-in-the-world/
|
Company InformationSpirelight ApS
Founded: 2019
Denmark
www.speechdata.ai/
|
|||||
Alternatives |
AlternativesNo Alternatives
|
|||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Microsoft Azure
Not Supported
Microsoft Foundry
Not Supported
|
||||||
|
|
|