streaming

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

A comprehensive Go client library for the Perplexity AI API with support for chat completions, async jobs, streaming, multimodal messages, structured outputs, and web search integration

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Orpheus TTS Server with streaming support (TTFB ~160ms)

PyTorch toolkit for streaming speech recognition, speech translation and simultaneous translation based on fairseq.

CLI & async Python library for free AI chat, image & video generation.