OpenWispr - 100% local open source AI speech-to-text model
by•
Turn your voice into formatted text. It's open source and runs 100% locally.
3-5x faster than typing, and especially helpful when prompting LLMs, writing emails and sending texts.
Pick your preferred model, and even edit the system prompt. Take full control.
Replies
Haimeta
Running speech-to-text fully local and open source is huge—no more waiting on cloud lag or worrying about privacy, tbh. Realy clever move, team!
GPT-4o
Running 100% local and open source is huge—no more worrying about sending my voice data anywhere, tbh that's so smart. Realy excited to try this!
Just tried this with Claude, insanely fast and accurate. Love that it runs locally and keeps everything private.
This is really cool. For running locally, are the lightweight transcription models usually sufficient? I am concerned with tying up too much memory while still getting reasonable accuracy.