Stars
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation
An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
High-Quality Voice Cloning TTS for 600+ Languages
The official Implementation of PeriodWave and PeriodWave-Turbo
A Conversational Speech Generation Model
Worlds first open-source real-time end-to-end spoken dialogue model with personalized voice cloning.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
Official implementation of paper: Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech
A highly compressive and high-quality neural audio codec for speech models.
🐍 CRo-DL (Český Rozhlas Downloader) - MůjRozhlas.cz 📻 offline
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
Training code and dataset cleasing with Sidon
PyTorch implementation of adversarial attacks [torchattacks]
[NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.
Tidy Tunes is an easy-to-use pipeline for mining high-quality audio data for speech generation models. To do so, it chains multiple open source models while minimizing dependencies.
A PyTorch baseline attack example for the NIPS 2017 adversarial competition
Voice Activity Detector (VAD) : low-latency, high-performance and lightweight
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
A TTS model capable of generating ultra-realistic dialogue in one pass.