offline speech-to-text
Offline speech recognition API for multiple languages and platforms with bindings for Python, Java, C#, Node, and mobile/embedded devices, based on Kaldi.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
actively maintained offline STT with onnxruntime, broader features, and no Kaldi dependency.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
optimized for ncnn on mobile/embedded, use when low memory and fast inference matter.
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.
ultra-low-latency local STT for voice agents, with fewer languages but very fast inference.
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
PyTorch toolkit for training and fine-tuning custom models, heavier than Vosk.
A PyTorch-based Speech Toolkit
Rust-native STT with LLM post-processing, if you prefer Rust and built-in refinement.
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
Apple-only CoreML speech models for native iOS/macOS apps.
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
full ASR toolkit with training and serving, more flexible but far heavier for simple transcription.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Apple Silicon speech toolkit using MLX/CoreML, best for native Apple apps.
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
self-hosted REST API around Whisper, choose for service-based deployments.
OpenAI Whisper ASR Webservice API
real-time STT server with streaming and diarization, OpenAI-compatible API.
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
older offline STT engine; choose only to run existing DeepSpeech models, as it is no longer maintained.
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
successor to DeepSpeech with same API; choose for its model hub if you accept stale code.
🐸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.
end-user subtitling tool, not a library.
Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具，输出json、srt字幕、纯文字格式
Linux note-taking app with STT and TTS, not a library.
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
These projects were analysed and named vosk-api among their alternatives. The relationship is not symmetric — how vosk-api rates them is a separate judgement, made when vosk-api is analysed in its own right.
calls vosk-api “Choose for lightweight offline ASR with Kaldi-based models and simple APIs across mobile and server, if you don't need Whisper's accuracy.”
Port of OpenAI's Whisper model in C/C++
calls vosk-api “Choose if you need lightweight offline speech recognition on mobile, Raspberry Pi, or servers with small-footprint Kaldi models.”
Faster Whisper transcription with CTranslate2
calls vosk-api “Choose when you need a lightweight, multi-platform offline ASR API without training your own models.”
A PyTorch-based Speech Toolkit
calls vosk-api “when you need lightweight offline streaming ASR with bindings for many languages; no diarization/translation”
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
calls vosk-api “choose for modern offline SR with a lightweight API.”
Speech recognition module for Python, supporting several engines and APIs, online and offline.
calls vosk-api “choose for lightweight offline ASR with simple APIs for mobile and server.”
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
calls vosk-api “choose for lightweight offline ASR on mobile/embedded devices with simple APIs and no GPU training.”
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
calls vosk-api “Use when you only need mature offline ASR with many language models and lightweight bindings, and can forego TTS/diarization/other tasks.”
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
calls vosk-api “choose when you want a simple, established offline ASR API for mobile/server and don't need TTS or intent.”
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
calls vosk-api “Choose when you need lightweight offline ASR APIs for mobile/servers without training, but only for speech recognition.”
End-to-End Speech Processing Toolkit
calls vosk-api “Choose when you need only offline speech recognition for mobile/embedded without MLX.”
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.