Microsoft UniLM

by Microsoft

Don’t want to install Microsoft UniLM? Drop the file here.

The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.

Home of WavLM, HuBERT++, Speech-T5, BEATs, VALL-E.

Linux  ·  free

TL;DR

Best for pulling SOTA speech encoder pretrains from Microsoft. Pricing: free.

Category
Open source
License
MIT
Stars
★ 22.2k
Last push
2026-01-23
Pricing
free
Platforms
Linux

What it is

Microsoft's foundation-models monorepo with several speech research releases. MIT.

Best for: Pulling SOTA speech encoder pretrains from Microsoft.
Watch out for: Mixed licenses per sub-project — some research-only.

Install / use

What people actually do with Microsoft UniLM-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Wire it into Amazon S3n8nMake.comGoogle DriveZapierSlack

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

Links

GitHub repo ↗

Microsoft UniLM vs Whipscribe

FeatureMicrosoft UniLMWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$6–$24 one-time packs (credits never expire) · first 20 minutes free
Speaker identificationNoNamed in the summary, key quotes and chapters
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinuxWeb, API, MCP

Alternatives to Microsoft UniLM

Frequently asked about Microsoft UniLM

Is Microsoft UniLM free?

Yes. Microsoft UniLM is free and open source.

Does Microsoft UniLM work on Mac, Windows and Linux?

Microsoft UniLM runs on Linux. It is not listed for other platforms; check the vendor for anything beyond Linux.

How do I install Microsoft UniLM?

Clone and run it from source: `git clone https://github.com/microsoft/unilm`. Expect to install its dependencies yourself — the README has the exact steps per OS.

How many languages does Microsoft UniLM support?

Microsoft UniLM lists 99 languages. That is the Whisper-family multilingual set, so quality varies by language — English and the large European languages are strongest.

Does Microsoft UniLM identify different speakers?

No. Microsoft UniLM does not label speakers; a conversation comes back as one continuous text. If you need speaker labels, that is a separate tool or a different service.

Does Microsoft UniLM give word-level timestamps?

Yes — Microsoft UniLM produces timing per word, which is what subtitle cues and clip boundaries need.

Can Microsoft UniLM transcribe live audio?

No — Microsoft UniLM works on finished files, not a live stream.

Is Microsoft UniLM HIPAA compliant?

Microsoft UniLM does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.

What are the limitations of Microsoft UniLM?

Mixed licenses per sub-project — some research-only.

Who is Microsoft UniLM best for?

Pulling SOTA speech encoder pretrains from Microsoft.

Does Microsoft UniLM run offline?

Microsoft UniLM runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use Microsoft UniLM in the browser?

No — Microsoft UniLM is a Linux application, not a web app. You install it rather than sign in to it.

Where is the Microsoft UniLM source code?

On GitHub at github.com/microsoft/unilm.

What kind of tool is Microsoft UniLM?

In this directory Microsoft UniLM is filed under foundation, research, microsoft as a open-source tool.

What are the alternatives to Microsoft UniLM?

There is a side-by-side page at /tools/microsoft-unilm-alternatives comparing Microsoft UniLM with the closest tools in the same category on price, platform and features.

Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

Transcribe your recordings

Explore

Have the recording already?

Skip the setup and send the file or the link: see MP3 to text for long recordings, transcribing a podcast episode and an SRT subtitle file from any recording.

Comparing tools before you pay?

If you would rather pay a service than run software yourself: see the best transcription services side by side, the cheapest way to transcribe an hour of audio and how our transcription services work.