Speech (STT / TTS)

Robust open-weight speech recognition and translation model and reference code

C/C++ port of OpenAI Whisper for fast local speech-to-text on CPU/GPU

Deep-learning toolkit for local text-to-speech including XTTS voice cloning

Transformer-based text-to-audio model for local speech, music and effects

CTranslate2 reimplementation of Whisper for faster local transcription

Whisper with word-level timestamps and speaker diarization for local ASR

Fast, local neural text-to-speech optimized for Raspberry Pi and edge devices

Offline speech recognition toolkit with small models for many languages

Lightweight 82M-parameter open-weight TTS model with fast local inference

Flow-matching TTS with high-quality zero-shot voice cloning (weights CC-BY-NC)