GitHub - nyosegawa/speech.cpp: Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-

AI Summary

This open-source project implements speech synthesis, speech recognition, and voice activity detection in C++ using the ggml framework, supporting models like Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, Parakeet, and Silero VAD. The library runs on Metal, Vulkan, and CPU backends, providing a unified command-line tool and C API for voice conversation applications.