speaches is an OpenAI API-compatible server supporting streaming transcription, translation, and speech generation. Speach-to-Text is powered by faster-whisper and for Text-to-Speech piper and Kokoro are used. This project aims to be Ollama, but for TTS/STT models.
**Nvidia GPU Use:** Using the Unraid Nvidia Plugin to install a version of Unraid with the Nvidia Drivers installed and add **--runtime=nvidia --gpus=all** to "extra parameters" (switch on advanced view)