AIGC-Audio/AudioGPT
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Integrates multiple specialized foundation models (Whisper, VITS, DiffSinger, Make-An-Audio, GeneFace) through a unified LLM interface, enabling chained audio tasks like speech recognition→style transfer→synthesis. Leverages LangChain and Hugging Face infrastructure to compose diverse audio/speech/singing/video generation pipelines from natural language prompts, with support for cross-modal tasks including image-to-audio and audio inpainting.
10,210 stars. No commits in the last 6 months.
Stars
10,210
Forks
865
Language
Python
License
—
Category
Last pushed
Jul 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AIGC-Audio/AudioGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
nerdaxic/glados-voice-assistant
DIY Voice Assistant based on the GLaDOS character from Portal video game series. Works with home...
sebastienrousseau/akande
An innovative, open-source voice assistant powered by OpenAI's GPT-3, designed to provide...
BonifacioCalindoro/whatsapp-AI-assistant
AI assistant that reads you whatsapp conversations and audio messages, and suggests a response...
felivalencia3/RealVoiceGPT
RealVoiceGPT is a web application that lets you have voice conversations with ChatGPT. The...
Shyguy99/Whatsapp-bot
A simple WhatsApp Bot made using open-wa library with some additional features.