Tag

PersonaPlex

Real‑time full‑duplex speech‑to‑speech system that controls conversational role via text prompts and voice timbre via audio-conditioned embeddings. Built on Moshi; optimized for low-latency, persona-consistent spoken interactions.

Pocket TTS

Generates low-latency, streaming text-to-speech entirely on CPUs (no GPU or cloud API required), using an ~100M-parameter model with voice cloning and multilingual support. Optimized for low resource use (2 CPU cores, ~200ms to first audio chunk) — suited for local, privacy-sensitive, or embedded TTS.

SGLang-Omni

Orchestrates low-latency, multi-stage pipelines for omni and multimodal models by running each stage with its own scheduler and using zero-copy shared memory for tensor transfer. Emphasizes per-stage bottleneck tuning and OpenAI-compatible streaming endpoints, suitable for TTS and multimodal serving.

Waxal NLP Datasets

Provides open ASR and TTS speech data for 24 Sub‑Saharan African languages to train and evaluate speech models. Includes ~1,250 hours of transcribed ASR and ~235 hours of single‑speaker TTS with train/validation/test/unlabeled splits and mixed CC-BY licenses.

Qwen3-TTS-12Hz-1.7B-CustomVoice

Generates controllable multilingual speech from text with nine predefined timbres and custom-voice control; supports voice design, quick voice cloning and low-latency streaming (first audio packet after a single character), suitable for real-time TTS and voice-design workflows.

Voicebox

Local-first voice cloning studio that runs on your machine to clone voices, generate speech in 23 languages, apply audio effects, and compose multi-voice projects. Includes five switchable TTS engines, a REST API, and native GPU/MLX support for privacy-sensitive offline workflows.

Anything → NotebookLM

Fetches multi-source content (webpages, YouTube, PDFs, WeChat, paywalled articles, podcasts), uploads it to Google NotebookLM, and generates outputs such as podcasts, PPTs, mind maps, or quizzes. Differentiators: automatic paywall-bypass pipeline, Claude Code Skill integration, and CLI + MCP components for WeChat and document scraping.

ACE-Step UI

Provides a Spotify-like local UI for running ACE-Step 1.5 to generate full songs (including vocals), batch variations, and manage a local music library, with reference-audio styling and built-in editing/stem tools for users running the model locally.

MOSS-TTS Family

Generates high‑fidelity, expressive speech and environmental sounds from text. The MOSS‑TTS Family provides specialized models for long‑form TTS, multi‑speaker dialogue, voice design and realtime streaming, plus torch‑free inference paths (llama.cpp / ONNX) and Hugging Face releases.

Marco-LongSpeech Dataset

Provides multi-task long-speech evaluation data for eight speech-understanding tasks (ASR, summarization, QA, translation, emotion, speaker counting, content separation, language detection). Includes 101,822 long audio files and ~204,881 annotated examples with JSONL task splits for easy loading.

WeChat 4.x Database Decryptor

Extracts derived keys from running WeChat 4.x processes to decrypt SQLCipher 4 databases and .dat media files, and provides a real-time message monitor with a Web UI. Cross-platform (Windows/Linux/macOS) but requires process-memory or local-data access and is intended for decrypting your own WeChat data only.

google/gemma-4-E4B-it

An instruction‑tuned Gemma 4 E4B multimodal model on Hugging Face that accepts text, images and audio and generates text; notable for 128K long context support, built-in thinking mode, and an on‑device‑friendly E4B architecture under an Apache‑2.0 license.