Soundbox
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio…
Soundbox is open source (MIT license) and runs on the user's own GPU. Soundbox generates sound effects from descriptions, songs from lyrics, and cloned voices from short clips. Nothing is uploaded and nothing is billed per second during generation.
Soundbox uses audio.cpp for inference, supporting CUDA, HIP, Metal, Vulkan, or CPU backends with no Python in the inference path. Soundbox provides an MCP server that lets agents like Claude Code and Cursor generate, speak, arrange, and export audio. Each model carries its own license, and several forbid commercial use.
After initial download, Soundbox works offline with no account or credits required.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.