Soundbox
Soundbox is a local app that generates sound effects, music, speech and cloned voices on your own computer for game and content creators.
What it is good for
- Generating sound effects from a text description
- Making instrumental music or songs with lyrics
- Creating speech and cloning voices offline
- Letting an AI agent produce audio for a project
At a glance
- Who it is for
- Setup
- Install a desktop app or browser extension
Level 3 of 5. Download and install it like any other app or extension.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Claude Code, Cursor, Codex
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 127
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Soundbox free?
- Yes. It is free and open source.
- Do I need to know how to code to use Soundbox?
- No. Download and install it like any other app or extension.
- What does Soundbox work with?
- According to its own documentation, it works with Claude Code, Cursor, and Codex.
- What is Soundbox good for?
- Generating sound effects from a text description, making instrumental music or songs with lyrics, creating speech and cloning voices offline, and letting an AI agent produce audio for a project.
Similar agents to Soundbox
- earshot
earshot is an agent app that lets coding agents hear and check sound for films, demos, and games for developers making sound in code.
- OpenCreator
OpenCreator is a desktop app that handles video translation, dubbing, and content creation with AI agents for creators and social media publishers.
- DramaClaw
DramaClaw is a self-hosted video production line that turns a script into a finished film for creators who want to run it themselves.
- html-video
html-video is a local tool that turns a prompt, article link, or GitHub repo into an animated MP4 video using a coding agent for creators and marketers.
- ffmpeg-skill
ffmpeg-skill is an Agent Skill that gives coding agents 42 local FFmpeg tools to cut, caption, reframe, and export video for creators.
- BeefTV
BeefTV is a desktop video creation workspace where an AI agent helps plan and generate storyboards, clips, and narration on an infinite canvas for video creators.