Prompt EngineOpen-source NPM library by Microsoft for programmatically crafting, managing, and optimizing prompts for Large Language Models like GPT-3 and Codex.(0)0
TensorRT LLM NVIDIANVIDIA TensorRT is an SDK for optimizing and accelerating deep learning inference on NVIDIA GPUs, featuring TensorRT-LLM, quantization tools, and up to 36x speedup over CPU.(0)0
OpenVoiceOpenVoice is a free, open-source voice cloning AI by MIT and MyShell that supports zero-shot cross-lingual cloning, tone color replication, and granular voice style control.(0)0
AIGCPanelAIGCPanel is a free, open-source AI digital human platform supporting video synthesis, voice cloning, voice synthesis, and live streaming with local model management on Windows, macOS, and Linux.(0)0
S StyleTTS 2StyleTTS 2 achieves human-level TTS synthesis using style diffusion and adversarial training with large speech language models. Open-source and free to use.(0)0
UltraschallUltraschall is a free, open-source REAPER extension that turns the DAW into a powerful podcast studio with StudioLink, multi-track recording, N-1 routing, and a workflow built around how podcasters actually work.(0)0
ChatterboxChatterbox is a free, MIT-licensed open-source TTS and voice cloning model by Resemble AI with emotion control, 60+ language support, and benchmark-beating quality.(0)0
Soundscape CommunityOpen-source iOS app by Microsoft Research that uses spatialized audio to help visually impaired users navigate their surroundings with confidence.(0)0
NVDA (NV Access)NVDA is a free, open-source Windows screen reader by NV Access. Converts on-screen content to speech or Braille, supporting blind and vision-impaired users(0)0
KoboldCppKoboldCpp lets you run GGUF large language models locally with a built-in KoboldAI UI and OpenAI-compatible API. No installation needed — just download and run on Windows, Linux, macOS, or Android.(0)0
