AudioGPT
Audio toolkit
An audio processing toolkit that provides pre-trained models and tools for tasks like speech synthesis, music generation, sound detection, and talking head creation.
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
10k stars
135 watching
868 forks
Language: Python
last commit: 7 months ago
Linked from 2 awesome lists
audiogptmusicsoundspeechtalking-head
kyrolabs/awesome-langchain
ewingyangs/awesome-open-gptRelated projects:
| Repository | Description | Stars |
|---|---|---|
 hahahumble/speechgpt | An application that enables users to converse with ChatGPT via speech and text interfaces. | 2,752 |
 haoheliu/audioldm | A Python-based audio generation tool that can produce speech, sound effects, music, and more, using text as input or guided by user description. | 2,483 |
 speechbrain/speechbrain | A PyTorch-based toolkit for building conversational AI systems with advanced speech and text processing capabilities. | 9,066 |
 nvidia/waveglow | Generates high-quality speech from mel-spectrograms using a flow-based network architecture | 2,294 |
 facebookresearch/audiocraft | A deep learning library for generating high-quality audio | 21,134 |
 pyannote/pyannote-audio | A toolkit for speaker diarization using PyTorch and speech activity detection. | 6,508 |
 archinetai/audio-diffusion-pytorch | An audio generation library that uses diffusion models to produce high-quality audio samples from noise or text input | 1,975 |
 pytorch/audio | A PyTorch module providing tools and functions for audio signal processing | 2,561 |
 futantan/opengpt | A platform for creating and running custom ChatGPT applications with user-created apps and support for API tokens and internationalization. | 3,935 |
 waylaidwanderer/node-chatgpt-api | Provides client-side access to ChatGPT and Bing AI APIs using Node.js | 4,210 |
 cogentapps/chat-with-gpt | An open-source ChatGPT app with added features and customization options | 2,327 |
 open-mmlab/mmagic | A toolkit for building and experimenting with generative AI models for image and video generation, restoration, enhancement, and other tasks. | 6,986 |
 williamfzc/chat-gpt-ppt | Automates the creation of PowerPoint presentations using ChatGPT as a backend. | 909 |
 suno-ai/bark | A text-to-audio model that generates realistic speech and other audio | 36,433 |