cactuscompute.com
Whistle: Speech to Text in 16.9 MB
Whistle is an open 16.9 MB speech‑recognition model that runs on CPU, transcribes seven languages in 11 ms first‑token latency, and integrates with the Needle engine for on‑device tool calls.
One line. Many voicesSeek and you shall find
cactuscompute.com
Whistle is an open 16.9 MB speech‑recognition model that runs on CPU, transcribes seven languages in 11 ms first‑token latency, and integrates with the Needle engine for on‑device tool calls.