CMU Sphinx-4

by CMU Sphinx

Don’t want to install CMU Sphinx-4? 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.

The classic Java speech engine from CMU.

JVM  ·  free

TL;DR

Best for legacy Java systems still on Sphinx. Pricing: free.

Category
Open source
License
NOASSERTION
Stars
★ 1.4k
Last push
2022-10-18
Pricing
free
Platforms
JVM

What it is

A pure-Java HMM/Gaussian-mixture engine. BSD-2-Clause.

Best for: Legacy Java systems still on Sphinx.
Watch out for: Largely superseded; minimal recent commits.

Install / use

What people actually do with CMU Sphinx-4-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-timeYes
Languages supported15
HIPAA eligibleNo

Links

GitHub repo ↗

CMU Sphinx-4 vs Whipscribe

FeatureCMU Sphinx-4Whipscribe
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
StreamingYesNo
Languages1599
PlatformsJVMWeb, API, MCP

Alternatives to CMU Sphinx-4

Frequently asked about CMU Sphinx-4

Is CMU Sphinx-4 free?

Yes. CMU Sphinx-4 is free and open source.

Does CMU Sphinx-4 work on Mac, Windows and Linux?

CMU Sphinx-4 runs on JVM. It is not listed for other platforms; check the vendor for anything beyond JVM.

How do I install CMU Sphinx-4?

Clone and run it from source: `git clone https://github.com/cmusphinx/sphinx4`. Expect to install its dependencies yourself — the README has the exact steps per OS.

How many languages does CMU Sphinx-4 support?

CMU Sphinx-4 lists 15 languages.

Does CMU Sphinx-4 identify different speakers?

No. CMU Sphinx-4 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 CMU Sphinx-4 give word-level timestamps?

Yes — CMU Sphinx-4 produces timing per word, which is what subtitle cues and clip boundaries need.

Can CMU Sphinx-4 transcribe live audio?

Yes — CMU Sphinx-4 supports streaming / live input, not just finished files.

Is CMU Sphinx-4 HIPAA compliant?

CMU Sphinx-4 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 CMU Sphinx-4?

Largely superseded; minimal recent commits.

Who is CMU Sphinx-4 best for?

Legacy Java systems still on Sphinx.

Does CMU Sphinx-4 run offline?

CMU Sphinx-4 runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.

Can I use CMU Sphinx-4 in the browser?

No — CMU Sphinx-4 is a JVM application, not a web app. You install it rather than sign in to it.

Where is the CMU Sphinx-4 source code?

On GitHub at github.com/cmusphinx/sphinx4.

What kind of tool is CMU Sphinx-4?

In this directory CMU Sphinx-4 is filed under toolkit, framework, legacy as a open-source tool.

What are the alternatives to CMU Sphinx-4?

There is a side-by-side page at /tools/sphinx4-alternatives comparing CMU Sphinx-4 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 how to transcribe an MP3 of any length, transcribing a podcast episode and the SRT file generator.

Comparing tools before you pay?

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