Stars
Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
SoTA open-source TTS
SoTA open-source TTS for Audiobook and Podcast Generation
Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"
An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
ACE-Step: A Step Towards Music Generation Foundation Model
A virtual audio driver for macOS that sends all audio to another output
Official code for "EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
A simple, hackable text-to-speech system in PyTorch and MLX
A TTS model capable of generating ultra-realistic dialogue in one pass.
Lets make video diffusion practical!
VoiceStar: Robust, Duration-controllable TTS that can Extrapolate
Experience email the way you want with Mail0 – the first open source email app that puts your privacy and safety first. Join the discord: https://discord.gg/mail0
Official repository of DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech, ICASSP 2023
AlpinDale / mergekit-LGPL
Forked from arcee-ai/mergekitTools for merging pretrained large language models.
A Conversational Speech Generation Model