AI Vtuber for Streaming on Youtube/Twitch
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
Build voice agents with open-source models