# Audio-only observations should default to 'animals'

**URL:** <https://forum.inaturalist.org/t/audio-only-observations-should-default-to-animals/75200>\
**Category:** Feature Requests\
**Created:** [January 30, 2026, 1:55pm UTC](https://forum.inaturalist.org/t/audio-only-observations-should-default-to-animals/75200 "2026-01-30T13:55:16Z")\
**Posts on this page:** 1\
**Showing post:** 11

<div class="post-metadata">

**Author:** ![upupa-epops](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/upupa-epops/32/1972_2.png) [@upupa-epops](https://forum.inaturalist.org/u/upupa-epops)\
**Post date:** [January 30, 2026, 5:59pm UTC](https://forum.inaturalist.org/t/audio-only-observations-should-default-to-animals/75200/11 "2026-01-30T17:59:07Z")

</div>

Merlin technically trains on the spectrogram images of the recordings rather than the audio itself. This works with the eBird/Macaulay Library audio database because a spectrogram is automatically generated for all uploaded audio. iNat [currently doesn’t produce spectrogram images](https://forum.inaturalist.org/t/automatically-add-a-spectrogram-view-to-observations-with-sounds/3579) so CV training on them isn’t an option at this point, although it’s theoretically a possibility for the future.

---

_[View the full topic](https://forum.inaturalist.org/t/audio-only-observations-should-default-to-animals/75200)._