STT is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named STT among their alternatives. The relationship is not symmetric — how STT rates them is a separate judgement, made when STT is analysed in its own right.
calls STT “Independent STT toolkit with its own models and training; choose it if you don't need Whisper specifically.”
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
calls STT “choose for training custom STT models, though unmaintained.”
Speech recognition module for Python, supporting several engines and APIs, online and offline.
calls STT “Older DeepSpeech-based toolchain with C++ runtime, suitable if you need an offline STT model with a simple C API and don't need Whisper.”
Port of OpenAI's Whisper model in C/C++
calls STT “Choose if you need a trainable DeepSpeech-based STT toolkit for lightweight edge deployment, despite being older.”
Faster Whisper transcription with CTranslate2
calls STT “choose for a standalone custom-trainable STT toolkit if you accept stale maintenance (2.5 years since last push).”
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 STT “successor to DeepSpeech with same API; choose for its model hub if you accept stale code.”
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
calls STT “Choose when you need a simple, standalone STT training/decoding toolkit and can tolerate an older codebase with limited activity.”
A PyTorch-based Speech Toolkit
calls STT “when you need an older lightweight offline STT engine/training with MPL license; stale”
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
calls STT “legacy training/deployment toolkit for English STT; choose only if you need to train your own models and can accept no maintenance.”
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.