DEDUPEDWho it is forSound-curious developer who wants a custom click, whoosh or key press made entirely in code
The problemStock effects never quite fit, and an agent cannot judge a synthesized sound without hearing it.
The outcomeA folder of rendered WAVs, a report in the critic's words, spectrogram comparisons and an audition file.
What you need first
- Python
- CPU only, no GPU needed
- Local models load on first call (about 20 to 40 seconds per CLI call)
- No account or paid key for core features
- Optional Gemini key only for the `llm` command
- Reference recordings for `forge --refset` are not in the repo; bring your own with `--refs DIR`
Steps
- Run
earshot forge --listto see recipes like click, impact, keypress and whoosh. - Run
earshot forge keypress --refs path/to/real/keypresses/ --budget 144 --variants 4 --dir made/keypresswith your own reference folder. - Open report.md and compare.png in the output folder and listen to audition.wav.
- Re-render a pick with
earshot forge --render keypress --params made/keypress/report.json --seeds 1 2 3 --dir made/again.
Prompt for your agent
Use earshot forge to make four variants of a <sound type> against my reference folder <refs dir>, then read report.md and tell me which pick is closest to the references. Verify by listening to audition.wav, not just the scores.
Caveat. The search optimizes earshot's own models and can fool them (the README notes this), so check spectrograms and listen; the v1 blind test was a coin flip on one listener and 15 trials.
About earshot
Gives coding agents ears: they can listen to audio, review it and generate sound. Runs on a plain CPU and is open source. View Leonxlnx/earshot on GitHub.
More with earshot
- Pick the best sound from a pile of downloads Rank candidate files against a text description and trim the best moment from a long recording.
- Get a written description of any audio file Turn a sound file into plain words, tags and measurements an agent can reason about.
- Score a launch film's audio against pro launch films Run a scorecard that lists timestamped fixes for your film's soundtrack and mix.
- Turn a recording into code you can vary Fit a recording to a small synthesis model and get a Python recipe you can tweak or morph.
- Build a sound kit for a code-made film Pick one sound per role from a bank of 201 effects and render them with measured sync points.
- Give Claude Code ears with the MCP server Run earshot as an MCP server so your agent can listen without reloading models each call.
- Check that sound hits land on your video cuts Get a second-by-second listening transcript of a film and see if hits match the picture cuts.
- Tell a real recording from a code-made sound Score files for realness and compare them to reference recordings or each other.
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page