Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet
sherpa-onnx is listed under Speech & Transcription Engines, in the AI Models & Local Execution category on Flocci AI Tools. Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet. It is free, with no paid plan attached, and it lives at github.com.
sherpa-onnx is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
sherpa-onnx works in a normal browser tab with no install. It is available on the command line, Linux, Mac, Windows, Android, iOS, self-hosting and the web.
sherpa-onnx does 3 things the catalog singles out: Offline speech-to-text, text-to-speech, vad and speaker diarization without internet; runs on android, ios, raspberry pi, webassembly and desktop with many language bindings; apache-2.0.
NVIDIA Canary-Qwen 2.5B is the closest free alternative: it sits in the same Speech & Transcription Engines sub-category and is free. NVIDIA Parakeet, faster-whisper and FunASR also start free. The full list is on the alternatives page.
See the full list →