Libraries & frameworks
vosk-api
alphacep/vosk-api
An offline speech recognition toolkit with small models and bindings for many languages, built for apps and devices.
Topics
Related projects
speech-to-text-benchmark699A minimalist, extensible Python framework for benchmarking speech-to-text engines, comparing accuracy, latency, memory and compute across local and cloud providers on standard datasets.
faster-whisper26.7kA fast Whisper transcription library built on CTranslate2, with quantization, batching, VAD filtering, and word timestamps.
ncnn24kA high-performance neural network inference framework optimized for mobile, embedded, and desktop model deployment.
sherpa-onnx15.8kAn offline speech toolkit built on next-gen Kaldi and onnxruntime, providing ASR, TTS, speaker diarization, VAD and more across 12 programming languages and many platforms.
openFrameworks10.5kopenFrameworks is a community-developed C++ toolkit for creative coding, bundling graphics, audio, video, computer vision and networking libraries for building interactive projects across platforms.
nomily-app1kBYOK voice-recording mobile app with ASR transcription, speaker diarization and AI summaries.