julius-speech/julius

Open-Source Large Vocabulary Continuous Speech Recognition Engine

51
/ 100
Established

This is a high-performance tool for converting spoken audio into written text. It takes audio recordings or live microphone input and outputs a transcription of the words spoken, along with other details like word confidence or timing. Researchers and developers working on speech-enabled applications or analyzing spoken language would find this useful.

1,930 stars. No commits in the last 6 months.

Use this if you need to accurately transcribe large vocabularies of continuous speech in real-time, whether from pre-recorded files or live audio input.

Not ideal if you're looking for a simple, out-of-the-box voice assistant or a pre-trained model for common voice commands without custom development.

speech-to-text audio-transcription linguistics-research voice-processing speech-technology
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,930

Forks

305

Language

C

License

BSD-3-Clause

Last pushed

Jun 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/julius-speech/julius"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.