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

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

An agent skill that scans web projects for common AI-generated design patterns and suggests or applies fixes to remove them.

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2, 3, and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

A modular agent skill package for directing Seedance 2.0 filmmaking workflows across text, image, video, audio, references, safety rewrites, and production handoff.

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

(eBook，PDFs Translation) A multilingual eBook processing tool supporting all eBook formats. Features online and offline translation while preserving original layouts. Compatible with both scanned and digital PDFs. Elegant user interface. The world's highest-performing open-source layout-preserving eBook translator.

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Kandinsky 2 — multilingual text2image latent diffusion model

MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java