# Cactus Compute releases 16.9 MB speech model for local CPU use

_Published Thursday, October 8, 2026 at 1:58 PM EDT · AI · Latest · Tier 2 — Notable_

Cactus Compute released Whistle, a 16.9 MB speech recognition model that it says runs on a device's CPU without dependencies. It transcribes up to 30 seconds of audio in seven languages and can return word timestamps or speech representations without producing a transcript.

The weights are on Hugging Face, with source and an engine on GitHub. Prebuilt engines cover seventeen targets, including Android, iOS, watchOS, Windows on ARM and RISC-V. Cactus reports better results than Whisper base on several speech benchmarks, while Whisper base leads on TED-LIUM, AMI and the MLS average. Whistle's transcript is capped at 320 tokens.

## Sources

- [cactuscompute.com](https://cactuscompute.com/blog/whistle)

---
Canonical: https://techandbusiness.org/newswire/VXuoBNFntJnqbzlro22mzp
Published: 2026-10-08T17:58:28.266Z
Story chronology: 2026-10-08T16:59:39.000Z
Retrieved: 2026-10-08T20:39:15.021Z
Publisher: Tech & Business (techandbusiness.org)