Code for the paper "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"

first base model for full-duplex conversational audio

Interface for OuteTTS models.

[ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer

GLM-4-Voice | 端到端中英语音对话模型

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

An easy-to-understand framework for LLM samplers that rewind and revise generated tokens

Codebase for Aria - an Open Multimodal Native MoE

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Entropy Based Sampling and Parallel CoT Decoding

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling

An Open-Sourced LLM-empowered Foundation TTS System

LlamaVoice is a llama-based large voice generation model, providing inference and training ability.

My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

All generative model in one for better TTS model

DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability

VALL-E 2 reproduction

Official Demo Page for DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer

A fast multimodal LLM for real-time voice

Training code for FAcodec presented in NaturalSpeech3

SpeechFlow neural network implementation

Supervoice diffusion enhance

FlashSpeech: Efficient Zero-Shot Speech Synthesis

Lumina-T2X is a unified framework for Text to Any Modality Generation