Speech Recognition and TTS in less than 500kb

I made a little python wrapper around it to serve an HTTP endpoint that’s OpenAI/elevenlabs compatible https://github.com/clayrosenthal/bootlegger

Quick link to the video where he demos it: https://www.youtube.com/watch?v=kMliOFYBiz4

Wow, it seems like this might beat out flite for very-low-memory TTS? I ended up abandoning a project of mine because I couldn't get high enough quality or low enough memory usage out of flite, so I'm very excited to try this out.

Flite for comparison: https://github.com/festvox/flite

Do you have any accuracy benchmarks?

I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.

Although for the use cases OP is targeting, lower accuracy may be good enough!

I installed the command line version using uv

    uv init
    uv add moonshine-voice
    uv run moonshine-voice mic --language en

good job on a clear readme.md tbh

For TTS I wonder how this compares to nanotts[1] with the en-GB voice, which is sort of unreasonably good.

[1] https://github.com/gmn/nanotts

So at that tiny 500kb size I imagine it could be compiled to web assembly, and run entirely in the browser right?

Couldn’t find a link, is that hard to do?

This looks like an extreme point for AI-based TTS, as formant/tract modeling synths tend to be more accurate if you want TTS in a tiny amount of compute, but sound distinctly robotic.

TTS (neural diphone synth @ 16 kHz) ~1.8 MiB voice pack

This is in the realm of Microsoft Sam.

It looks great, thank you! I'll see if I can use it for my in browser AI assistant project's ( https://aidekin.com ) voice part. It's currently using Nemotron-3.5-ASR and supertonic-3 but overall it requires 1.2gb download.

Given the tiny size of this, I wonder about possible future integration with esphome compatible hardware

https://esphome.io/

this is good to see. i also trained a stt under 500kb for sub dollar chips. it had about 20 words that it could understand(like start, stop, left, right, go, up etc) and then the spell mode where you could say the word spell and then say the individual english alphabets and close with spell. it was super fun to work on. these tend to be extremely unstable though, like confusion between p and t (at least for my accent). will have to try this one now.

Very cool. I've done TTS on a 32K Arduino but it was pretty croaky. https://youtu.be/ErGDboTpwM0

Voice is one of the most latency-sensitive modalities in AI. Moonshine is doing awesome stuff

The voice activity detection alone here is compelling - very useful for doing things like highlighting a speaker who's transmitting in realtime. At that rate the impact on perf will be so minimal that you could easily run it in the browser across devices.

Thank you for this. I love your work on Curb Your Enthusiasm.

Is the dataset open

very nice I love it

ngl, it looks incredible

Great work!