AI Agent Skills

Converts text to speech in realtime

TTS model capable of streaming conversational audio in realtime.

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300M) TTS. OpenAI Realtime API compatible. Voice cloning, barge-in, ~9× realtime o…

Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, a…

[ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

Soprano-Factory: Train your own 2000x realtime text-to-speech model