[1]: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

I built a macOS dictation app (https://github.com/T0mSIlver/localvoxtral) on top of Voxtral Realtime, and the UX difference between streaming and offline STT is night and day. Words appearing while you're still talking completely changes the feedback loop. You catch errors in real time, you can adjust what you're saying mid-sentence, and the whole thing feels more natural. Going back to "record then wait" feels broken after that.

Curious how Moonshine's streaming latency compares in practice. Do you have numbers on time-to-first-token for the streaming mode? And on the serving side, do any of the integration options expose an OpenAI Realtime-compatible WebSocket endpoint?

I'd love a faster and more accurate option than Whisper, but streamers need something off-the-shelf they can install in their pipeline, like an OBS plugin which can just grab the audio from their OBS audio sources.

I see a couple obvious problems: this doesn't seem to support translation which is unfortunate, that's pretty key for this usecase. Also it only supports one language at a time, which is problematic with how streamers will frequently code-switch while talking to their chat in different languages or on Discord with their gameplay partners. Maybe such a plugin would be able to detect which language is spoken and route to one or the other model as needed?

For voice agents, the painful failure mode is partials getting rewritten every few hundred ms. If you can share it, metrics like median first-token latency, real-time factor, and "% partial tokens revised after 1s / 3s" on noisy far-field audio would make comparisons much more actionable.

If those numbers look good, this seems very promising for local assistant pipelines.

The minimum useful data for this stuff is a small table of language | WER for dataset

The authors do acknowledge this though and give a slightly too complex way to do this with uv in an example project (FYI, you dont need to source anything if you use uv run)

There was an issue with a demo but it's missing now. I can't recall for sure but I think I got it working locally myself too but then found it broke unexpectedly and I didn't manage to find out why.

Weird to only release English as open weights.

    hear about what people might build with it

Due to the sector being increasingly worried about "hybrid threats" we try to rely on the cloud as little as possible and run things either on device or with the possibility of being self-hosted/on-premise. I really like the direction your company is going in in this respect.

We'd probably need custom training -- we need Norwegian, and there's some lingo, e.g., "bravo one two" should become "B-1.2". While that can perhaps also be done with simple post-processing rules, we would also probably want such examples in training for improved recognition? Have no VC funding, but looking forward to getting some income so that we can send some of it in your direction :)

It's incredible for a live transcription stream - the latency is WOW.

https://www.onresonant.com/

For the open source folks, that's also set up in handy, I think.