Download
jSpeech is a Java library designed to integrate Speech-to-Text (STT) capabilities, command control, and diarization (speaker identification) into applications in a simple, modular, and decoupled way.
Features
- Offline Reference Engine: Includes a built-in driver for Vosk, allowing private, local transcription without the need for an internet connection.
- Native Diarization: Identifies who is speaking based on audio biometric fingerprints and timbre changes (speaker identification).
- Driver-based Architecture: Swap recognition engines (Google, Azure, Vosk) without changing your business logic, thanks to the Strategy Pattern implementation.
- Phonetic Correction: Integrated system to correct common transcription errors using XML dictionaries and text normalization.
License
Other LicenseFollow JSpeech
Other Useful Business Software
Host LLMs in Production With On-Demand GPUs
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
Rate This Project
Login To Rate This Project
User Reviews
-
very good tool
