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.
I honestly couldn’t justify paying for another ai tool subscription, so I built this one myself.
OpenWispr, is an open source speech-to-text tool that runs 100% locally and helps you write 3-5x faster than typing.
It's especially helpful for prompting in ChatGPT, Claude and/or Cursor but really I use it for everything. I have found that LLMs are able to match your tone more closely when you speak to them, rather than when you type (as it forces you to articulate yourself more and you edit out your natural tone).
It's completely free if you clone the repo and run it yourself, otherwise for a small contribution you get access to automatic updates as they roll out.
Try it out and let me know what you think! DM me if you need help setting it up :)
OpenWispr empowers seamless and secure voice communication through AI-driven whisper technology. Experience crystal-clear, low-latency audio solutions built for privacy, clarity, and real-time collaboration across platforms and devices.
Another awesome open-source product! How many language does it currently detect?
Was looking for this for long time. Thank you.
Can you add model API providers with free limits eg. Groq and Gemini?
nice workk, team. What languages/accents does it handle well right now, and is there real‑time streaming for live captions? Also, is there a quickstart (Docker or one‑click) so I can go from install → first transcript in under 10 minutes?
This is super awesome. I actually really wanted a local version of @Aqua Voice and this might be the answer. @gabe_stein awesome job. How does it compare in terms of speed & accuracy agains @Wispr Flow or @Aqua Voice ?
Getting it as I type!
@gabe_stein Congrats on the launch! A local, open source voice-to-text tool sounds incredibly useful for faster prompting and writing.
Wow, running everything locally without sending my voice data anywhere? That’s huge—I’m always sketchy about cloud stuff. Love that you let us edit the system prompt too!
About OpenWispr on Product Hunt
“100% local open source AI speech-to-text model”
OpenWispr launched on Product Hunt on July 30th, 2025 and earned 191 upvotes and 21 comments, placing #10 on the daily leaderboard. 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.
OpenWispr was featured in Productivity (649.8k followers), Open Source (68.3k followers), Artificial Intelligence (466.2k followers) and GitHub (41.2k followers) on Product Hunt. Together, these topics include over 243.7k products, making this a competitive space to launch in.
Who hunted OpenWispr?
OpenWispr was hunted by Ben Lang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how OpenWispr stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ben Lang
I honestly couldn’t justify paying for another ai tool subscription, so I built this one myself.
OpenWispr, is an open source speech-to-text tool that runs 100% locally and helps you write 3-5x faster than typing.
It's especially helpful for prompting in ChatGPT, Claude and/or Cursor but really I use it for everything. I have found that LLMs are able to match your tone more closely when you speak to them, rather than when you type (as it forces you to articulate yourself more and you edit out your natural tone).
It's completely free if you clone the repo and run it yourself, otherwise for a small contribution you get access to automatic updates as they roll out.
Try it out and let me know what you think! DM me if you need help setting it up :)