VANIV Studio is building local-first AI tools for voice, video and multilingual content creation. Our focus is practical workflows for AI dubbing, voice cloning, TTS, subtitles, localization and GPU-accelerated creator tools — with privacy, control and local processing at the core.
Our stack
Local AI, ONNX Runtime, NVIDIA/AMD/Intel acceleration, Whisper, VAD, speaker diarization, multilingual TTS, voice cloning, FFmpeg, local video processing, Python, TypeScript and Windows/WSL workflows.
