- Home
- Speech Recognition Software
- CMU Sphinx
CMU Sphinx
What it is
CMU Sphinx is an open-source toolkit for developers building speech applications. Its maintained components are PocketSphinx, a lightweight C speech recognizer library, and SphinxTrain, tools for acoustic model training. Designed for efficient recognition on low-resource platforms, it supports keyword spotting, grammar searches, language-model searches, and word-level segmentation. Recognition requires acoustic and language models. The toolkit is language-independent, with prebuilt models listed for English, Chinese, French, Spanish, German, and Russian. SphinxTrain supports the process of preparing data, training a model, and testing it to add a language. Noise handling uses MFCC features, noise tracking, and spectral subtraction. The project documents offline and on-device use, including a PocketSphinx Android library and demo, but cautions that its Android tutorial may no longer work with current tools. Audio must be converted to PCM before processing. The BSD-like license allows commercial distribution. The homepage announces PocketSphinx 5.1.0, with Python 3.14 support and prebuilt Linux/arm64 wheels.
For and against
For
- Open-source toolkit with commercial distribution allowed.
- Supports keyword spotting and word-level segmentation.
- Designed for low-resource platforms and offline recognition.
- SphinxTrain provides acoustic model training tools.
Against
- Recognition requires acoustic and language models.
- Input audio must be converted to PCM.
- The Android tutorial may not work with current tools.
- Large-vocabulary recognition is too demanding for phones and small embedded devices.
The verdict
CMU Sphinx offers recognition components and model-training tools for developers building speech applications. Account for the required models, PCM input, and platform limits when considering a use case.
Who it suits
CMU Sphinx is for developers applying speech technology in applications, rather than speech-recognition researchers. Possible uses include voice control, language learning, transcription, closed captioning, speech translation, and voice search.
Plans and prices
CMU Sphinx toolkit
BSD-like license · commercial distribution allowed
Read 5 Oct 2026 · cmusphinx.github.io
On the record
- Android support
- The site documents a PocketSphinx Android library and demo, while cautioning that the tutorial has not been tested for quite some time and may no longer work with current Android tools.cmusphinx.github.io · read 5 Oct 2026
- Commercial use
- The site describes its license as BSD-like and says it allows commercial distribution.cmusphinx.github.io · read 5 Oct 2026
- Current release
- The homepage announces PocketSphinx 5.1.0, released May 6, 2026, with Python 3.14 support and prebuilt Linux/arm64 wheels.cmusphinx.github.io · read 5 Oct 2026
- Developer audience
- The developer tutorial is intended for developers applying speech technology in applications, rather than speech-recognition researchers.cmusphinx.github.io · read 5 Oct 2026
- Input audio requirement
- The decoders do not convert encoded audio formats, so audio must be converted to PCM before processing.cmusphinx.github.io · read 5 Oct 2026
- Languages
- CMU Sphinx is language-independent, but recognition requires acoustic and language models; the site lists prebuilt models for languages including English, Chinese, French, Spanish, German, and Russian.cmusphinx.github.io · read 5 Oct 2026
- Low-resource design
- The tools are designed for efficient speech recognition on low-resource platforms.cmusphinx.github.io · read 5 Oct 2026
- Maintained components
- The currently maintained components are PocketSphinx, a lightweight C recognizer library, and SphinxTrain, acoustic model training tools.cmusphinx.github.io · read 5 Oct 2026
- Model training
- SphinxTrain provides acoustic model training tools, and the toolkit describes collecting data, cleaning it, training a model, and testing it to add a language.cmusphinx.github.io · read 5 Oct 2026
- Noise handling
- CMU Sphinx uses mel-cepstrum MFCC features with noise tracking and spectral subtraction for noise reduction.cmusphinx.github.io · read 5 Oct 2026
- Platform constraints
- The FAQ says large-vocabulary speech recognition is too computationally demanding for phones and other small embedded devices, where limited vocabularies are commonly used.cmusphinx.github.io · read 5 Oct 2026
- Purpose
- CMU Sphinx is an open-source speech recognition toolkit for building speech applications.cmusphinx.github.io · read 5 Oct 2026
- Recognition features
- The toolkit supports keyword spotting, grammar searches, language-model searches, and word-level segmentation through its documented interfaces.pocketsphinx.readthedocs.io · read 5 Oct 2026
- Support
- The site describes commercial support and directs users to GitHub project and issue trackers for help.cmusphinx.github.io · read 5 Oct 2026
- Use cases
- The tutorial lists voice control, language learning, transcription, closed captioning, speech translation, and voice search as possible applications.cmusphinx.github.io · read 5 Oct 2026
