Find tools › Open-source projects › Images, video & voice

earshot

Open-source project · by Leonxlnx

Gives your computer assistant the ability to hear, analyze, and generate sound effects using code.

Some setupWell known

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Describe and match audio recordings using plain language descriptions
  • Synthesize and refine sound effects directly in code
  • Audit videos for sound quality and audio-visual timing sync

How to start

  1. Verify your local setup and model downloads by running earshot doctor.

  2. Inspect any audio sample in plain words with earshot describe <file>.

  3. Generate code-synthesized sound effects using earshot forge --list.

  4. Run earshot mcp to connect audio tools directly into your coding assistant.

Good to know. Each standalone command-line run reloads the models and takes 20 to 40 seconds to start; use the MCP server or Python library for repeat tasks. Reference audio datasets are not bundled and must be provided locally.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

An open-source, CPU-only audio engine that lets AI agents and developers hear, critique, and synthesize sound effects through code.

AI agents building games or videos cannot hear their output or check audio-video sync. Use earshot when an agent needs to evaluate audio quality, match sounds against descriptions, or generate synthetic sound effects in code.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-17. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map