ComfyUI node for F5-Text To Speech

Speech-to-text server framework with next-gen Kaldi

Unified automatic quality assessment for speech, music, and sound.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

F5-TTS 推理加速，速度提升约4倍！

A generative world for general-purpose robotics & embodied AI learning.

Turn any common eBook file into an HQ Audiobook with F5-TTS (Easy Install)

A Survey of Spoken Dialogue Models (60 pages)

UTokyo-SaruLab MOS Prediction System

Easy-to-Use Speech MOS predictors

Implementation of F5-TTS in MLX

first base model for full-duplex conversational audio

GLM-4-Voice | 端到端中英语音对话模型

Running the F5-TTS by ONNX Runtime

AI powered speech denoising and enhancement

GUI for a Vocal Remover that uses Deep Neural Networks.

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Collection of Open Source Speech Data

Multilingual G2P in 100 languages

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

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

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Text to speech alignment using CTC forced alignment