OmniVoice uses a Qwen3 backbone (28 layers, hidden_size=1024, ~500M params) as its LLM component. The baseline TRT-LLM engine runs in FP16 on NVIDIA L4. Quantization provides two benefits: Reduced ...
Ssemble uses AI to automatically find the best moments in your videos and create short-form clips optimized for TikTok, YouTube Shorts, and Instagram Reels. Available as an MCP server for integration ...