Passive acoustic monitoring on your own computer.

GrizCam Desktop is free for bioacoustics, on Windows and macOS; a paid Pro version adds AI for camera traps and more. It opens standard audio files (WAV, FLAC and MP3) from most recorders, and it runs on your own computer. Sign in once; after that it works offline for up to 180 days.

• AI annotate: run BirdNET+ (from the BirdNET team; birds and other wildlife worldwide), Perch 2.0 (birds and many other species), PNW-Cnet (owls and other Pacific Northwest species) and Cry Wolf (wolf howls and wolf choruses) over thousands of recordings from any recorder, and review what they find before adding it to your annotations.
• Build your own AI, no code: train a detector from your own recordings on Perch and Earth Species Project foundation models, tested on whole sites and months it never heard, with its precision, recall and false alarms per hour shown before you trust it.
• WAV, MP3 and FLAC files from any recorder, on Windows or an Apple‑silicon Mac.

And what it does with them

• Recorder maps, call clustering and acoustic indices.
• Biologger and collar tracks over the audio.
• Direction of arrival from GrizCam's six‑microphone array.
• With a GrizCam and Pro, camera captures played with the audio around them.

Point GrizCam Desktop at a folder of recordings, multi-channel included. When the file names carry the site, date and time, it reads them, so every recording and every annotation lands at its clock time.

Run AI detectors over the folder: BirdNET, from the BirdNET team, for more than 11,500 species and sound classes worldwide; Perch 2.0 for birds and other animals; and PNW-Cnet v5 for owls and raptors. Each downloads the first time you use it. Review each detection on the spectrogram, draw your own boxes around calls, and label them. Clustering groups similar sounds so you can find patterns before you label everything.

For the soundscape as a whole, the biodiversity report charts acoustic indices (ACI, entropy, events, background noise) over time. Export annotations and clips for statistics or training data. All of this is in the free version.

When the sound you study has no detector, build your own AI from your own recordings. Annotate the calls, pick one of six bioacoustic foundation models, and train. GrizCam Desktop holds back whole sites and months the detector never trains on, then reports its precision, recall and false alarms per hour on them. Your detector runs in the same list as BirdNET, Perch and PNW-Cnet. Training your own detectors is free too.

The worked example: the Cry Wolf classifier, a wolf-howl detector trained this way on The Cry Wolf Project's Greater Yellowstone recordings.

The recorder map shows every site colored by its detections. The biologger map follows a collared animal's GPS track, with its audio and motion data on the same timeline, so a call ties to the place the animal was.

See it on one wolf: wolf 1513F's journey across Yellowstone's Northern Range, reconstructed from her biologger collar.

The Greater Yellowstone owl bioacoustics pages come from a recorder archive worked in GrizCam Desktop: what each uncommon owl sounds like, with measured frequency and cadence.

GrizCam Desktop is the broadest free software for this work, not the deepest. Other tools cover more species out of the box and identify bats automatically; it does neither.

You need a GrizCam account, even for the free version. Direction of arrival, which estimates where a sound came from, works only on recordings from GrizCam's six-microphone array. And GrizCam Desktop is in beta, so expect change.