Open Source Speech Recognition Projects
Speech recognition, also called automatic speech recognition, converts spoken audio into written text. It can make recordings searchable, support captions and dictation, and let people interact with software by voice. Systems may process live audio or transcribe stored files, and can run locally or rely on remote services. Accuracy depends on factors such as accents, background noise, vocabulary, audio quality, and the language being recognized.
Open source tools in this area include recognition engines, model runtimes, transcription applications, and libraries for integrating speech input into other software. When choosing one, consider supported languages, accuracy for your audio, latency, hardware and offline requirements, license terms, maintenance activity, and integration options. These tools are useful to developers building voice features, researchers evaluating recognition methods, and organizations that need control over their transcription workflows.
2 repositories · updated October 3, 2026
parakeet-mlx: Nvidia's Parakeet ASR Models on Apple Silicon with MLX
parakeet-mlx is an open-source project that implements Nvidia's advanced Automatic Speech Recognition (ASR) Parakeet models for Apple Silicon, leveraging the MLX framework for optimized performance. This Python library offers both a command-line interface and a flexible Python API, enabling efficient transcription of audio files, including real-time streaming capabilities. It provides a powerful solution for developers and researchers working with speech processing on Apple hardware.
whisper.cpp: Transcribe Speech with Whisper in C/C++
whisper.cpp runs OpenAI Whisper speech recognition through a lightweight C/C++ implementation. It suits developers building offline transcription into applications across desktop, mobile, browser, and server environments.