Inference System · Python
VoiceManager
A low latency streaming STT / STT server to add a voice to your LLM. Also supports batch mode.
What it is
VoiceManager is a self-hosted, full-duplex streaming speech-to-text and text-to-speech server over WebSocket, built around a Python FastAPI server and a C++ sidecar process that runs STT/TTS engines. It ships a Python client, an auth/CLI layer, model-download setup, and an optional torch-based turn-taking engine (Tyger) for barge-in and turn-end detection.
Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored
Where it counts
- Machine Learning50%
- NLP & LLMs40%
- AI Agents30%
- MLOps25%
- Data Science5%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the Machine Learning board
Whole board- 04celiumsnnArchitecture Modification / Research · Python72.1AdvancedMario GutierrezMachine Learning
- 05datarustLibrary / Framework · Rust71.0AdvancedMurat GençMachine Learning
- 06VoiceManagerInference System · Python68.9AdvancedTacoTakumiMachine Learning
- 07AECS-schedulerLibrary / Framework · Python67.6AdvancedRickMachine Learning
- 08ORBITLibrary / Framework · Python67.4AdvancedPop AlexandruMachine Learning
