As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/m/cactus-whistle/ # Cactus Whistle (16.9 MB on-device speech-to-text) Cactus Compute, Needle family. Status: current. Type: speech and audio. Released: 2026-10-02. ## How to call it | Provider | Model id | Endpoint | Docs | |---|---|---|---| | Hugging Face | `Cactus-Compute/whistle` | | https://huggingface.co/Cactus-Compute/whistle | | GitHub (engine) | | | https://github.com/Cactus-Compute/needle3 | | Browser demo | | | https://cactuscompute.com/blog/whistle | ## Pricing - Price not published. - Last checked: 2026-10-03 ## Specs - Input: audio - Output: text - Context window: not published - Max output: not published - Open weights: yes - Licence: apache-2.0 ## Where it stands - Newer speech and audio models in the registry since its release: 10. The 5 newest: - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/ - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/ - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/ - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/ - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/ - Weights are public under a permissive licence (Apache-2.0). ## What stands out - Speech recognition in a 16.9 MB file, on CPU: One 16.9 MB file with no dependencies, running in the same C++ engine as Cactus's Needle model; ~11 ms to first token; transcribes up to 30 s per pass in English, German, French, Spanish, Italian, Dutch and Polish with language detection, word timestamps and speech embeddings. Vendor benchmarks: ahead of Whisper base on most sets at ~9× smaller and ~6× faster. Source: https://cactuscompute.com/blog/whistle ## Notes Aimed at phones, wearables, robots, smart home, cars and microcontrollers. Compared with Whisper base (a small 2022 model), not with large ASR models; vendor-run numbers. Launch post ~167k views; Nobara/GE-Proton maintainer GloriousEggroll reported it made his home assistant respond 'SO damn fast'. Launch: https://x.com/cactuscompute/status/2106083041265562075 · Related: [phonon-2](phonon-2.md), [whisper-large-v3](whisper-large-v3.md). Model page: https://postcutoff.com/m/cactus-whistle/