2 related articles

A deep dive into HuggingFace's speech-to-speech open-source project, covering its modular VAD, STT, LLM, and TTS pipeline architecture and the advantages of local deployment for privacy, cost, and latency.
Moonshine: A Low-Latency Speech Engine…
Moonshine is an open-source, C++-based low-latency speech engine combining STT, intent recognition, and TTS for building voice agents. 9,400+ GitHub Stars.