Every tool here is open source, which means you can read how it works, adapt it, and in many cases run it on your own hardware instead of sending your data to someone else's server.
CosyVoice provides an AI-assisted audio workflow for creators, developers, researchers, or teams working with...
Freemium
Free plan Open source
CosyVoice 3 provides an AI-assisted audio workflow for creators, developers, researchers, or teams working wit...
Freemium
Free plan Open source
EchoMimic supports AI-generated presenters, talking characters, lip-sync or related avatar video workflows.
Free
Free plan Open source
F5-TTS provides open source TTS for creators, businesses, educators, and developers who need practical audio w...
Free
Free plan Open source
FunASR converts spoken audio into searchable text for meetings, research, media workflows, or developers.
Freemium
Free plan Open source
Hookpad Aria uses AI or machine learning to generate, arrange, transform, or analyze music for creators and pr...
Freemium
Free plan Open source
MagicPose helps creators generate AI-assisted video from prompts, images or other creative inputs.
Free
Free plan Open source
RVC provides an AI-assisted audio workflow for creators, developers, researchers, or teams working with sound.
Freemium
Free plan Open source
SAM 2 helps creators generate AI-assisted video from prompts, images or other creative inputs.
Free
Free plan Open source
Soniox STT converts spoken audio into searchable text for meetings, research, media workflows, or developers.
Freemium
Free plan Open source
Ultimate Vocal Remover applies AI or machine learning to clean, separate, enhance, master, or transform record...
Freemium
Free plan Open source
Open-source TypeScript toolkit for building AI-powered web applications, chat interfaces, tool calls, and agen...
Free
Free plan Open source
YuE provides an AI-assisted audio workflow for creators, developers, researchers, or teams working with sound.
Freemium
Free plan Open source
AnimateDiff Lightning helps creators generate AI-assisted video from prompts, images or other creative inputs.
Free
Free plan Open source
AnimateDiff Motion LoRA supports AI-assisted motion capture, character animation or movement transfer for digi...
Free
Free plan Open source
ComfyUI MusicGen uses AI or machine learning to generate, arrange, transform, or analyze music for creators an...
Freemium
Free plan Open source
CosyVoice 2 provides an AI-assisted audio workflow for creators, developers, researchers, or teams working wit...
Freemium
Free plan Open source
DDSP-SVC provides an AI-assisted audio workflow for creators, developers, researchers, or teams working with s...
Freemium
Free plan Open source
Demucs applies AI or machine learning to clean, separate, enhance, master, or transform recorded audio.
Freemium
Free plan Open source
DSPy helps developers framework for programming and optimizing language-model pipelines rather than manually c...
Free
Free plan API Open source
FLAVR helps creators generate AI-assisted video from prompts, images or other creative inputs.
Free
Free plan Open source
HiFi-GAN provides an AI-assisted audio workflow for creators, developers, researchers, or teams working with s...
Freemium
Free plan Open source
Kyutai STT converts spoken audio into searchable text for meetings, research, media workflows, or developers.
Freemium
Free plan Open source
LosslessCut helps creators generate AI-assisted video from prompts, images or other creative inputs.
Free
Free plan Open source
What to check before you choose
Open source covers a wide range in practice. Some of these are fully self-hostable and will run offline on your own machine; others are open clients that still call a commercial API behind the scenes, so the licence tells you about the code rather than about where your data goes. Licences differ too — a permissive licence and a copyleft or source-available licence place very different conditions on commercial use. If self-hosting or licensing is the reason you are here, check the project's own repository before committing: that is the authoritative source, and it changes faster than any directory.
