voice-enhancement

Clean up noisy speech in real time with DPDFNet - open-source streaming speech enhancement for research, audio apps, and edge devices. Includes pretrained models, PyTorch code, ONNX/TFLite inference, 8/16/48 kHz support, and live demos.

Official Repository of Paper: "Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios"(AAAI 2026)

A local first pipeline for processing meeting recordings with audio preprocessing (loudness normalization, voice enhancement, conversion), transcription, diarization for local and groq based processing.

High-quality Easy Effects presets for voice clarity and cinematic audio enhancement. Optimized for Fifine microphones, streaming, and immersive listening.

Extract main speech (loudest speech) from other speeches in audio.

🎤 Voice enhancement CLI + TUI — extract vocals, apply pro-grade 6-filter FFmpeg chain, output clean WAV files. Presets, configurable, cross-platform.

Enhance image quality using a FastAPI and PyTorch-based pipeline to upscale or restore low-resolution photos.