Speech Recognition

The whisper.cpp repository provides a C and C++ port of OpenAI’s Whisper model.

CMUSphinx is an open source speech recognition system for mobile and server applications.

Faster Whisper runs Whisper transcription through the CTranslate2 inference engine.

The whisper.cpp project ports OpenAI’s Whisper speech recognition model to C and C++.

Voice Notepad converts speech to text in a browser and lets users copy, save, publish, or email dictated content.

WhisperS2T is an optimized speech-to-text pipeline for the Whisper model with support for multiple inference engines.

LilySpeech lets Windows users dictate emails and documents with speech-to-text voice recognition.

NVIDIA NeMo provides a framework for language, multimodal, and speech AI, including recognition and text to speech.

Vosk provides an offline speech recognition API for mobile devices and servers, with several programming language interfaces.

ESPnet includes tools for end to end speech processing and related speech tasks.

Kaldi provides an open toolkit for speech recognition and speech processing research.

NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants.

TalkTyper provides browser-based speech-to-text dictation, with language options including English, French, German, and Spanish.

OpenAI Whisper is a general-purpose speech-recognition model trained with large-scale weak supervision.

FunASR supports speech recognition training and inference, streaming, punctuation, diarization, and model serving.

The wav2letter project provides an automatic speech recognition toolkit from Facebook AI Research.

AI Dictation turns mixed Russian, Ukrainian, or Belarusian speech into text while preserving English work terms.

Offer Bull provides AI interview practice, real-time speech recognition, and live answer suggestions for job seekers preparing for online interviews.

Transcribro offers private, on-device speech recognition through an Android keyboard and speech-to-text app.

OpenQuack provides local voice dictation on macOS, inserting Whisper transcripts at the cursor.

Superwhisper turns speech into polished text for use in apps such as Slack and Gmail, with recognition options listed for four operating systems.

VoiceToText transcribes speech online for writing emails and documents, according to its page.

Vocova transcribes audio and video into text in more than 100 languages and accepts imports from named services.

WhisperX provides speech recognition with word-level timestamps and speaker diarization, according to its project description.