#whisper

One TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (58+ servers), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

FFmpeg bindings for Node.js. Features both low-level and high-level APIs, full hardware acceleration, TypeScript support, and modern async patterns