speech recognition / Whisper inference
Faster Whisper is a Python library that reimplements OpenAI's Whisper speech-to-text models with CTranslate2 for faster, lower-memory transcription.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose if you need a full ASR toolkit with streaming, VAD, punctuation, and diarization alongside a different model family.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Choose if you need lightweight offline speech recognition on mobile, Raspberry Pi, or servers with small-footprint Kaldi models.
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Choose if you want a PyTorch toolkit to train or customize your own ASR models rather than just running Whisper.
A PyTorch-based Speech Toolkit
Choose if you need Whisper inference in C/C++ for embedded or Python-free environments.
Port of OpenAI's Whisper model in C/C++
Choose if you are on Apple Silicon and want MLX-native speech-to-text, plus TTS/STS in one library.
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
Choose if you need on-device speech recognition in Swift on Apple platforms.
On-device Speech AI for Apple Silicon
Choose if you need real-time on-device ASR with ncnn and Kaldi models, especially for offline mobile/edge use.
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose if you run on TPU and need a JAX-native Whisper implementation, though it is stale and TPU-only.
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
Choose if you need a trainable DeepSpeech-based STT toolkit for lightweight edge deployment, despite being older.
🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Choose if you want a command-line Whisper client compatible with OpenAI's CLI instead of embedding a Python library.
Whisper command line client compatible with original OpenAI client based on CTranslate2.
These projects were analysed and named faster-whisper among their alternatives. The relationship is not symmetric — how faster-whisper rates them is a separate judgement, made when faster-whisper is analysed in its own right.
calls faster-whisper “Use it when you need Whisper transcription in Python and prefer a CTranslate2 backend over a C/C++ embedded library.”
Port of OpenAI's Whisper model in C/C++
calls faster-whisper “choose for a faster Whisper implementation with CTranslate2.”
Speech recognition module for Python, supporting several engines and APIs, online and offline.