AI Agent Skills

Cross-platform, customizable ML solutions for live and streaming media.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Port of OpenAI's Whisper model in C/C++

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.