Awesome Neural Codec Models, Text-to-Speech Synthesizers & Speech Language Models

Versatile Evaluation of Speech and Audio

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

A Survey of Spoken Dialogue Models (60 pages)

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

✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Multilingual Voice Understanding Model

MARS5 speech model (TTS) from CAMB.AI

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

Open source real-time translation app for Android that runs locally

Foundational model for human-like, expressive TTS

A generative speech model for daily dialogue.

llama3 implementation one matrix multiplication at a time

Inference and training library for high-quality TTS models.

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

Official repo for WavCraft, an AI agent for audio creation and editing

Awesome speech/audio LLMs, representation learning, and codec models

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

A lightweight library for Frechet Audio Distance calculation.

trying to reproduce suno v3

Zero-Shot Speech Editing and Text-to-Speech in the Wild

SOTA Open Source TTS

我的 ComfyUI 工作流合集 | My ComfyUI workflows collection

Open-Sora: Democratizing Efficient Video Production for All

AI powered speech denoising and enhancement

VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.