Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
Leonxlnx/earshot
Sound effects for coding agents: ask in plain words and earshot renders the sound in code. CPU-only, no audio model, open source.
- Stars
- 5,486
- +7 days
- —
- Forks
- 382
- Language
- Python
- License
- MIT
- Last push
- 22 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This open-source audio tool enables coding agents and developers to generate sound effects from plain-language prompts on a CPU without generative audio models. It renders audio from a catalogue of 922 code-based designs, constructs missing sounds from layered recipes, and inspects audio files through acoustic analysis and listening models. Developers can integrate it directly into workflows using an MCP server, a Claude Code plugin, the CLI, or Python.
Use it when
- Generate sound effects for apps, games, or videos directly within Claude Code using plain-text prompts
- Need a lightweight, CPU-only MCP server to synthesize UI and foley sounds without external audio APIs
- Analyze, measure, or critique audio files against text queries and timing cues within agent workflows
Install
/plugin marketplace add Leonxlnx/earshot/plugin install earshot@earshotclaude mcp add earshot --scope user -e EARSHOT_THREADS=3 -- earshot mcpCommands quoted from the repo's README. Read the README before running them.
Needs a token or API key.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.