Amphion license, foundation and stars

Image, video and speech generation · MIT (open source) · 10,332 stars

GitHubSuggest a correction

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

More in image, video and speech generation

AGPL v3165k starsstable-diffusion-webuiStable Diffusion web UI.+24 a weekGPL v3146k starsComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.+1,572 a weekCustom or mixed (see the LICENSE file)73.6k starsstable-diffusionA latent text-to-image diffusion model.+16 a weekMIT64.7k starsGPT-SoVITS1 min voice data can also be used to train a good TTS model!+368 a weekCustom or mixed (see the LICENSE file)60.2k starsReal-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time.+12 a weekMIT56.9k starsVibeVoiceOpen-Source Frontier Voice AI.Microsoft · +338 a weekGPL v353.9k starsFooocusFocus on prompting and generating.+100 a weekApache 2.042k starsVoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.+581 a week

Project	License	Stars	Per week	Latest release
stable-diffusion-webuiStable Diffusion web UI.AGPL v3	AGPL v3	165k	+24	-
ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.GPL v3	GPL v3	146k	+1,572	-
stable-diffusionA latent text-to-image diffusion model.Custom or mixed (see the LICENSE file)	Custom or mixed (see the LICENSE file)	73.6k	+16	-
GPT-SoVITS1 min voice data can also be used to train a good TTS model!MIT	MIT	64.7k	+368	-
Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time.Custom or mixed (see the LICENSE file)	Custom or mixed (see the LICENSE file)	60.2k	+12	-
VibeVoiceOpen-Source Frontier Voice AI.MicrosoftMIT	MIT	56.9k	+338	-
FooocusFocus on prompting and generating.GPL v3	GPL v3	53.9k	+100	-
VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.Apache 2.0	Apache 2.0	42k	+581	-