Radar
New projects people are discovering or following across Pinokio.
Separate Anything You Describe (https://huggingface.co/spaces/Audio-AGI/AudioSep)
Your own AI radio: it writes the lyrics, sings them with YuE2 on your own GPU, and plays them on channels you define. Android app included.
Open the current project in the Freebuff Desktop app (Windows 64-bit).
Image-Text-to-Text model with 321B parameters. Download, explore files and run it on Hugging Face.
Zero-Shot Text-Based Audio Editing Using DDPM Inversion https://huggingface.co/spaces/hilamanor/audioEditing
Contribute to tazmannner/ComfyUI-H3-AnimeCadence development by creating an account on GitHub.
Speech-to-video inference: an avatar video generated from a reference frame and a speech track
Automatically create music videos. Synchronize the cuts to the music's beat.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Tencent Hunyuan AuK — 1.5B speech generation & editing. Rewrite what is SAID in an existing recording (fix a mispronounced word) while keeping the original voice and delivery. Also zero-shot TTS, emotion/timbre/whisper edits, denoise, dereverb and speaker separation. MIT licensed.
