AudioChunker
Audiochunker — slice any audio into perfectly timed clips, instantly Audiochunker is a lightweight Pinokio ap...
Launcher updates
Free AI Agents, Forever
Included a feature called Router, which you can manually connect and plug in free models across many provider...
Phosphene 3.2.4 - Ideogram 4 now runs on M1 and M2 Macs
Phosphene 3.2.4 fixes Ideogram 4 for slower Apple GPUs. It now runs on M1 and M2 Macs, not just the fast ones...
UnderfitFeatured
Underfit is for musicians, sound designers, sample makers, and audio experimenters who want Stable Audio 3 to...
Store
Qwen3-TTS MLX WebUI EnhancedFeatured
High-quality text-to-speech with Beautiful Web UI & API, optimized for Apple Silicon using MLX. Features include Custom Voice (preset speakers), Voice Design (natural language), and Voice Cloning. With enhanced features for saving custom voices and long-form / endless TTS streaming.
@blizaine
63 check-ins
AI-powered image inpainting. Remove objects, people, defects from images.
Any book, performed by a full cast — effortlessly.
Clasificación inteligente de gastos con IA local para PyMEs — 100% offline | CCS
Dub & translate any short video — locally, offline. Voice clone / per-speaker cast / voice packs, on-screen text localized in place, subtitle styling, blur-or-solid mask covers, funny re-dub. One process (FastAPI serves the React SPA), 6 UI languages.
@nerual_dreming1 check-in
SongGeneration StudioFeatured
AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]
20 check-ins
Automatically clip videos and generate captions for LoRA training using advanced vision models like Gemma-3, Qwen3-VL, and Qwen2-VL.
MuseTalk is a cutting-edge video-to-video (V2V) lip-sync solution engineered to deliver highly accurate and natural mouth movements synchronized to audio input. Precision LipSync: Realistic and seamless synchronization of speech audio to facial movements. Efficiently designed to run on 8–12 GB VRAM,
@manatheturipa
2 check-ins
RMBG-2-StudioFeatured
Enhanced background remove and replace app built around BRIA-RMBG-2.0 https://huggingface.co/briaai/RMBG-2.0
Higgs Audio v3 TTS + AI text director, voice cloning, podcast & audiobook (multi-speaker). 100+ languages, offline, NVIDIA GPU.
@nerual_dreming4 check-ins
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Orpheus-TTS-FastAPIFeatured
Orpheus TTS is an open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis https://github.com/canopyai/Orpheus-TTS
[NVIDIA Only] Wan2.2 video Studio (text/image-to-video, restyle, keyframe, talking-character S2V) + LoRA Gym + MOVA joint audio+video. From 12GB VRAM.
P2PCLAW Agent Benchmark — connect any LLM agent (Claude, GPT, Gemini, Qwen, Kimi, DeepSeek…) and get scored on 10 dimensions + Tribunal IQ. Dashboard runs locally on :8787, leaderboard at p2pclaw.com/app/benchmark.
Hermes ModFeatured
A full Hermes skin manager for browsing, editing, saving, and activating CLI skins directly from Pinokio.
@cocktailpeanut
10 check-ins
Prompt Orchestrator that turns module-based game design (genre, mechanics, visuals, menus, audio) into a complete, playable HTML5 game generated by your chosen AI provider. Supports OpenAI, Gemini, Claude, Ollama, and LM Studio. Every game ships as a single self-contained HTML file.
Download and transcribe many YouTube videos or whole playlists at once with faster-whisper. Outputs txt, srt, vtt, or json.
OdysseusFeatured
Self-hosted AI workspace for local-first chat, agents, tools, memory, research, documents, email, and model endpoint management.
@cocktailpeanut
6 check-ins
Diffusion Engine for Musical Orchestrated Noise — a real-time streaming diffusion engine for music generation, built on ACE-Step v1.5. Requires an NVIDIA GPU.