Rendered at 09:09:13 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
almogo 3 hours ago [-]
Stt/tts systems always seem to me so promising, but I pretty much never use voice to interface with a computer. Sometimes instead of typing on my phone, I use a voice dictation. I would be keen to use voice to control Claude code, but I've always felt that the way I speak is different from the way I write good prompts.
Fishing for anecdotes here, does anyone have any good tts/stt experiences?
kleiba2 33 minutes ago [-]
I've always dreamed of having the ability to just talk to my computer (in the right circumstances) so I actually worked in the field for many years. The main reason I never use speech recognition today is because I have zero interest of sending recordings of my voice to the servers of some global corporations.
Running speech recognition and TTS locally is quite feasible, as projects like this one show.
arend321 2 hours ago [-]
I do a ton of coding (codex) with a tts/stt wrapper. During walks, cycling, in the car. Not every task is suited to this style of interaction, but many are. Long form codex replies are condensed, code blocks are suppressed all in the name of making it work for tts feedback. So it works best on well defined projects with guardrails, where you know the agent can perform well.
hathawsh 20 minutes ago [-]
That's fantastic. I have long, winding trails near me also and one of these days I also want to start prompting a coding agent on my bike with a headset. Do you recommend any particular type of headset?
Edit: never mind, I see you already suggested the Shokz OpenComm2 in another comment. Thanks!
VBprogrammer 32 minutes ago [-]
I can't honestly think of a case where this would be remotely useful. This goes somehow beyond vibe coding to vibe interaction, where the only feedback comes via the AI. I'd love to see a concrete example of this working practice.
fragmede 2 hours ago [-]
During cycling! Do you have a phone mount on your bike that you use while biking or is it all in-ear?
arend321 2 hours ago [-]
I have my phone in my pocket, no screen interaction is required. I use a headset (Shokz OpenComm2) with wind muff (when cycling).
I made an Android app that listens for codex turn-complete or intermediate updates and plays them back to me. My answer is transcribed and pasted back to the relevant codex (tmux) session on the server (which I can select by voice) a tiny layer helps with things like /new, /plan, answer selection, etc.
cafebabbe 2 hours ago [-]
... I cannot think of an activity less suitable for coding (except scuba diving)
I would die In minutes
arend321 52 minutes ago [-]
Think long winding, quiet, dedicated cycling roads in forested areas and natural parks. Not busy roads shared with cars and lorries.
mattmanser 46 minutes ago [-]
This is extremely dangerous and you should stop doing it.
I'm founder of ottex.ai, I use stt pretty much all the time when work with AI and quite often for communications to draft emails and chat messages.
I started ottex half a year ago after I tested gemini 2.5 flash native audio support. I was blown away by the quality of transcripts and decided to built an app to use it myself.
Currently the default model in the app is Gemini 3 flash, but you can connect to 9 providers and God knows how many models to play with.
I would suggest you to try this models for ai prompting:
One of my side projects is a tool that lets you control your entire system with STT. It's built on Whisper and supports hot swapping custom profiles, so you can add easy commands for any software.
I intend to use it to work on low stakes vibe coding projects while I'm doing other stuff. Todays LLMs are a lot better at interpreting rambling dictation with mid-message corrections.
There are a few paid programs out there that do the same, but they made my vibe slop sense tingle and are not aimed at development.
Joel_Mckay 2 hours ago [-]
Industry leading Interactive Voice Response systems have become very good at filling in ambiguous information from context, and modulating pronunciation to Ape emotional information.
However, being able to interact with these natural language systems in uncontrolled settings is still a fools errand. For STT, there is also regional dialect, slang, and individual differences.
Witnessing blind users hit unrecognizable reading-speeds on old Gordon 8 TTS systems was surprising. I learned people adapt to imperfect systems pretty quickly. =3
fragmede 2 hours ago [-]
For STT, wispr flow has a generous free tier. For TTS, I have Claude read out loud what it just finished as a stop hook, so I know which claude finished up.
This is awesome. I am trying to build a full scale ASR system within 20-25MB. Now that we have Claude code to run experiments, I have started running some experiments. Promising results so far. First realization is that you can capture the nuances of speech in just 3300 embedding vectors(786d). This sequence can be decoded with a small CTC system to get text. Next experiments are on reducing the 768 dimension space into a 64D space. Thats also show some promising results. Hooking up my system so that the agent blogs the results everyday[1]. So my research "claw" setup does the experiments and posts results which I check in the morning and adjust the experiment direction as needed. Its not fully automated yet, but almost there.
I think Google's Conformer paper is SOTA at the <30M model size, where I think they put an incredible amount of flops into a 10M param model to reach around 2% lsc clean (the whole model and RNN decoder were trained domain specific to librispeech here).
I think my small Talon models are next, around 3% lsc clean at ~28M (greedy CTC decoding, no external encoder, no LM, not trained in a domain specific way). I reached around 6.5% at 10M.
I've been working on some new baselines I want to release soon as public artifacts. This article is inspiring me to try pushing the param size down a bit. I suspect we can do large vocabulary end to end in the <5M range.
(Also, I know it's besides the point but this might be the most painful way to connect to Wifi physically possible. "Make normal everyday tasks slow, tedious and painful" is a bit of an odd choice for a product demo.)
Say, speaking of Sam, what were the memory requirements for SAM (Software Automatic Mouth) on C64. I guess they were not more than 64K? Although, the bulk here is probably for the speech recognition, not the TTS. (And this one does sound a little nicer :)
There are two Sams here, the Microsoft one and the C64 one. I don't believe there's any connection between the two other than the name.
According to [1], the weight of a modern runnable version is around 39k.
The ratio of how good it sounds compared to how much computing power it uses is ridiculous. The C64 has ballpark 3 orders of magnitude less CPU throughput as an RP2350, and the codebase uses an impressive array of tricks to do actual formant synthesis (barely) and a pretty refined form of Elovitz text to phoneme conversion. One of my favorite tricks is its up and down bouncy pitch, which is not random, but based on the opposite contour as the first formant. It's simplistic but enough to make it not sound like a robotic monotone.
I've been playing around with this some myself and SAM is an inspiration, along with other landmark systems like MITalk (predecessor to DECtalk), SP0256, and other. I believe it's possible to use modern techniques to get pretty good sounding speech in, say, 64k and 10% of the throughput of a RP2350. It's really cool to see projects like OP, especially under permissive license.
Amazing that this works. As an aside, and I appreciate this is just a demo, if the use case is to get a device to join a WiFi network - would a single or double line lcd with 3 buttons not be cheaper than 520KB?
pxx 4 hours ago [-]
the target rp2350 is a sub-$1 chip. a 16x2 LCD module is over $1. but more importantly, you might have this much ram sitting around unused on whatever you're building anyway.
8bitsrule 7 hours ago [-]
Thanks for that ... impressive!
Kyuren 16 minutes ago [-]
This makes me want to have a server room with 5 of these around my house and control everything that house in LabRats
jedberg 12 hours ago [-]
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!
amelius 11 hours ago [-]
> I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.
This actually holds for everything in AI.
jedberg 10 hours ago [-]
Very true!
kamranjon 11 hours ago [-]
If you look at this chart here it seems the tiny model has a WER of ~12%… not sure about the micro model:
That's the error rate for STT, not TTS. TTS is generally easier than STT because you only need to produce one valid pronunciation and don't need to handle variation within and between individuals.
senkora 12 hours ago [-]
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.
uv init
uv add moonshine-voice
uv run moonshine-voice mic --language en
super nice to be able to run it to test it like this
good job on a clear readme.md tbh
pwgawron 11 hours ago [-]
`uvx moonshine-voice mic --language en` That is even simpler.
stanko 2 hours ago [-]
This is really impressive.
If I get time, I would like to try compiling it to WASM. This would allow me to swap my robot poet’s native browser voice synthesis for it. Not sure if it is worth it, but it will be fun to play around with.
Will it be able to understand my English with an Indian accent?
userbinator 9 hours ago [-]
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.
Presumably it's not, but the TTS voice in the video sounds to me more like formant synthesis than diphone - it reminds me of my DECtalk.
The project credits does mention espeak (which is formant based) as well as various other TTS projects, although it sounds like they are only using the pronunciation part of espeak, not the voice synthesis.
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.
dwa3592 10 hours ago [-]
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.
schoen 5 hours ago [-]
Could you get people to use the NATO phonetic alphabet for the spelling part? I suppose a challenge is that many people don't know the whole thing, even if they're aware it exists.
NooneAtAll3 10 hours ago [-]
I remember someone training smart kettle to use its speaker as microphone
laidoffamazon 9 hours ago [-]
IIRC the Alexa enabled voice remotes also used a similarly small model though perhaps not this small
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.
walrus01 8 hours ago [-]
Given the tiny size of this, I wonder about possible future integration with esphome compatible hardware
I suppose, but for home automation, esps are best for getting the audio to something more powerful. If this lets a raspberry pi do voice recognition really fast, that alone is worth it.
nserrino 8 hours ago [-]
Voice is one of the most latency-sensitive modalities in AI. Moonshine is doing awesome stuff
10 hours ago [-]
irfan_99 9 hours ago [-]
Is the dataset open
sgt 5 days ago [-]
Great work!
0xnyn 12 hours ago [-]
ngl, it looks incredible
irfan_99 9 hours ago [-]
very nice I love it
jkwang 1 hours ago [-]
[flagged]
2 hours ago [-]
Ecko123 3 hours ago [-]
[dead]
zarmin 12 hours ago [-]
Thank you for this. I love your work on Curb Your Enthusiasm.
Fishing for anecdotes here, does anyone have any good tts/stt experiences?
Running speech recognition and TTS locally is quite feasible, as projects like this one show.
Edit: never mind, I see you already suggested the Shokz OpenComm2 in another comment. Thanks!
I would die In minutes
https://etsc.eu/tiny-proportion-of-drivers-understand-danger...
I started ottex half a year ago after I tested gemini 2.5 flash native audio support. I was blown away by the quality of transcripts and decided to built an app to use it myself.
Currently the default model in the app is Gemini 3 flash, but you can connect to 9 providers and God knows how many models to play with.
I would suggest you to try this models for ai prompting:
- Gemini 3 / 3.5 flash - Soniox rtt v5 - Mistral transcribe v2 - assembly 3.5 pro
I intend to use it to work on low stakes vibe coding projects while I'm doing other stuff. Todays LLMs are a lot better at interpreting rambling dictation with mid-message corrections.
There are a few paid programs out there that do the same, but they made my vibe slop sense tingle and are not aimed at development.
However, being able to interact with these natural language systems in uncontrolled settings is still a fools errand. For STT, there is also regional dialect, slang, and individual differences.
Witnessing blind users hit unrecognizable reading-speeds on old Gordon 8 TTS systems was surprising. I learned people adapt to imperfect systems pretty quickly. =3
[1] https://blog.trulm.com/posts/speech-as-independent-parts/
I think my small Talon models are next, around 3% lsc clean at ~28M (greedy CTC decoding, no external encoder, no LM, not trained in a domain specific way). I reached around 6.5% at 10M.
I've been working on some new baselines I want to release soon as public artifacts. This article is inspiring me to try pushing the param size down a bit. I suspect we can do large vocabulary end to end in the <5M range.
(Also, I know it's besides the point but this might be the most painful way to connect to Wifi physically possible. "Make normal everyday tasks slow, tedious and painful" is a bit of an odd choice for a product demo.)
Say, speaking of Sam, what were the memory requirements for SAM (Software Automatic Mouth) on C64. I guess they were not more than 64K? Although, the bulk here is probably for the speech recognition, not the TTS. (And this one does sound a little nicer :)
Browser demo of a reversed SAM:
https://discordier.github.io/sam/index.html
According to [1], the weight of a modern runnable version is around 39k.
The ratio of how good it sounds compared to how much computing power it uses is ridiculous. The C64 has ballpark 3 orders of magnitude less CPU throughput as an RP2350, and the codebase uses an impressive array of tricks to do actual formant synthesis (barely) and a pretty refined form of Elovitz text to phoneme conversion. One of my favorite tricks is its up and down bouncy pitch, which is not random, but based on the opposite contour as the first formant. It's simplistic but enough to make it not sound like a robotic monotone.
I've been playing around with this some myself and SAM is an inspiration, along with other landmark systems like MITalk (predecessor to DECtalk), SP0256, and other. I believe it's possible to use modern techniques to get pretty good sounding speech in, say, 64k and 10% of the throughput of a RP2350. It's really cool to see projects like OP, especially under permissive license.
[1]: https://simulationcorner.net/index.php?page=sam
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!
This actually holds for everything in AI.
https://github.com/moonshine-ai/moonshine#when-should-you-ch...
Flite for comparison: https://github.com/festvox/flite
[1] https://github.com/gmn/nanotts
good job on a clear readme.md tbh
If I get time, I would like to try compiling it to WASM. This would allow me to swap my robot poet’s native browser voice synthesis for it. Not sure if it is worth it, but it will be fun to play around with.
Edit: typo
[0] https://muffinman.io/bard/
Couldn’t find a link, is that hard to do?
TTS (neural diphone synth @ 16 kHz) ~1.8 MiB voice pack
This is in the realm of Microsoft Sam.
The project credits does mention espeak (which is formant based) as well as various other TTS projects, although it sounds like they are only using the pronunciation part of espeak, not the voice synthesis.
https://github.com/moonshine-ai/moonshine#acknowledgements
Having it run on a pico would be pretty impressive =3
http://cmuflite.org/
https://github.com/festvox/flite
https://github.com/ggml-org/whisper.cpp/
https://esphome.io/
Played by the great Richard Kind, who my wife swears she saw on the Highline in NYC.