OpenWispr
Star Download
Multilingual

Multilingual dictation, without the surprise translation

A specific, documented complaint about the category leader: speak in one language, and the app spontaneously translates to another without being asked. It's a real bug, named by real users, and worth understanding structurally before picking a dictation app for a multilingual workflow.

Download for macOS Get it on Google Play
OpenWispr/Use cases/Multilingual
The documented bug

"As far as I know, live translation is not even a feature"

Two separate, dated organic complaints describe the same failure mode in Wispr Flow: "I speak English (mostly) and Portuguese… Wispr started to translate from one language to the other… After the ~20th time, I gave up and disabled Portuguese" (2026-06-15), and "Wispr Flow live translates when I speak Swedish into English. As far as I know, live translation is not even a feature" (2026-06-30). Wispr Flow's auto-detect was also removed at some point, which reportedly angered European users who relied on it to switch languages mid-session without manual configuration.

This isn't a claim that every cloud dictation product has this exact bug — it's a specific, sourced complaint about one product. It's included here because it points at a structural question worth asking about any dictation app you're evaluating for multilingual use: what happens between what you said and what lands on the page, and how many opportunities are there for that pipeline to do something you didn't ask for?

The structural difference

Fewer moving parts between your voice and the transcript

OpenWispr's on-device pipeline runs a speech model — NVIDIA Parakeet-TDT by default, or Whisper via whisper.cpp — directly on your device, with no network round-trip that could route audio through a different model, service version, or configuration than the one you started with. That's a structural property of the architecture, not a benchmarked claim about translation accuracy specifically — this page isn't asserting OpenWispr has been tested head-to-head against the exact failure mode described above, only that there's no cloud-side model swap or hidden mode change in the pipeline to produce it.

For context on language breadth elsewhere in this category: Muesli publishes a model table showing Parakeet v3 covering 25 languages and Nemotron 3.5 covering 100+ locales, on-device — a useful reference point for how far local models have come on multilingual coverage generally, separate from the specific translation bug discussed above.

Questions

Good questions, honest answers.

Does Wispr Flow really mistranslate instead of transcribing? +
Two separate, dated organic user reports describe exactly that — speaking Portuguese or Swedish and getting unrequested English translation back. Their auto-detect feature was also reportedly removed. This is a sourced complaint about that specific product, not a claim about the category as a whole.
Has OpenWispr been tested against this specific translation bug? +
Not benchmarked head-to-head — this page makes a structural argument, not a tested-and-confirmed one. OpenWispr's on-device pipeline has no network round-trip that could swap models or modes mid-session, which is the mechanism most likely to produce that kind of surprise behavior, but that's an architectural observation, not a claim of measured multilingual accuracy.
How many languages does OpenWispr support? +
It uses NVIDIA Parakeet-TDT by default or Whisper via whisper.cpp, both of which are multilingual models — but this page isn't citing a specific tested language count for OpenWispr itself. If exact language coverage matters for your use case, verify directly against the current model documentation on GitHub.
Which competitor publishes the clearest multilingual model information? +
Muesli, among the apps covered in this research — a published table showing Parakeet v3 at 25 languages and Nemotron 3.5 at 100+ locales, on-device. See the OpenWispr vs Muesli comparison for the full picture, including where Muesli is ahead.
Is auto-detecting between multiple spoken languages mid-session supported? +
This is a real, named gap for Wispr Flow specifically (auto-detect was removed). This page doesn't make a specific claim about OpenWispr's current auto-detect behavior — check current documentation on GitHub for the latest state.
Compare
OpenWispr vs Wispr Flow (cloud-only)
Compare
OpenWispr vs Muesli (published multilingual model table)
Use case
One free, open-source app for macOS and Android

Start dictating privately.

Open source and entirely on your device. Android from Google Play, macOS from GitHub — no account, no sign-up, just a download.

Download for macOS Get it on Google Play
OpenWispr Voice to text, on your device.
GitHub Privacy Policy Features vs Wispr Flow vs superwhisper On-device Android dictation MIT © 2026