-
FunASR
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
-
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
-
Whisper Transcribe
Transcribe audio files locally via Whisper — runs whisper.cpp under the hood.