Curious if you thought their approach was necessary, it seemed like a ton of complexity to reduce one of the faster parts of a voice AI setup. Having a fast model and accurate VAD seems way more important than fine tuning WebRTC transit times.
I think It’s a case of you improve what you own. The owners of WebRTC servers were aggressively improving their part. They don’t own the inference servers.
I read parts of it a while ago when I had an idea on using webRTC data channels to pass data from databases to browser clients via a CLI. Your book made me understand that it's probably not a great fit for my use case. I just used a centralized control plane and websockets instead.
I still feel like there is something fun that we can do with webRTC data channels + zero copy Apache Arrow arraybuffers + duckdb WASM, but haven't figured it out yet
You can't beat Websockets :) Especially since you have so much tooling/existing stuff that works with HTTP.
I have been trying to get a website off the ground that does Datachannels + SQlite in the browser and then users sync between each other. I have gotten distracted so many times though.
import ("github.com/go-sql-driver/mysql")
To me go code looks like somebody vomitted stuff in the root dir and i have to wade through that every time. No namespacing. nothing
And you're right, fanboys are in every language. But resorting to changing the argument by whataboutism is a bit reductive.
There’s an oft-repeated pattern where valid specific criticisms morph into broad criticism, which morphs into judgement, which breeds defensiveness, which feeds the criticism. Once you recognise this pattern, you see it everywhere.
I also suffer from finding the appropriate word I want as I've gotten older and slower, and this fast-voice-gpt just ends up frustrating me more than helping. I have to sit there and think out the whole sentence in my head before I say anything -- not very natural.
Suppose you have 100ms audio latency and no wait time. Then, natural pause will trigger response immediately but you won't notice it has started until after ~200ms (round-trip time). Twice as annoying.
If you meant there is a case where reducing the network latency at the same delivery reliability for a given audio stream is actually a negative then I'd love to hear more about it as I'm a network guy always in search of an excuse for latency :D.
And GP is correctly pointing out that the only negative here (silence waiting latency maybe being too low) is tunable separately from the network latency number.
But we won't get any of that, because the prime directive of LLMs is to burn tokens like there's no tomorrow. Burn tokens on a naïve answer without asking clarifying questions. Burn tokens on writing, debugging, and running a Python script or accessing and parsing 10 websites without asking for consent. Burn tokens on half-baked images with misspellings and 31 fingers. Burn tokens arguing "how many 'r's in strawberry?". Burn tokens asking a followup question at the end of every single answer, begging the user to re-engage and burn more tokens.
There is a little red "Stop" control when text output is being produced, at least, but does "Stop" halt everything and throw away the context? Re-prompt from the beginning?
The "maximize tokens burnt" prime directive is not to be found in any system prompt or user documentation. It is seemingly a common feature of the training for any consumer model.
Currently, if I'm using voice for an LLM, I use the voice dictation in the keyboard feature, because then the response is in text. There is no way to prevent "responding in kind" if I query the thing with audio. Or in Swahili.
I think the solution is to handle pauses more intelligently rather than having a higher latency protocol. With low latency you can interrupt and the bot can immediately stop rambling.
I often use it while I’m walking and tell it to not respond until I initiate a conversation.
This would be a killer feature for me and something I’ve tried to use on cross-country road trips.
Knowing when to respond requires semantic understanding, which probably only the model itself is capable enough.
Maybe it’s hard for them to train it to only respond once it seems appropriate to do so?
However things like 'Call center helpline' turn based actually seems better! You don't want to be interrupted when giving information back and forth (I think?)
I also think it spends most of its iq on sounding good rather than thinking about the problem. “Yeah absolutely I can see why you’d like to…” etc. This is likely because it’s on a timer and maybe voice is more expensive to process? Text responses spend more time on the task.
I don’t think it even has reasoning tokens, so it’s no surprise that it’s as most as smart as the “instant” models (i.e., not very).
I've tried to convey this to OpenAI through various available channels (dev forums, app feedback, etc.).
Grok solves this by having an optional push-to-talk mode, but this is not hands-free and thus more cumbersome than just having a user-configurable variable like seconds_delay_before_sending_voice_input.
1-2s replies feel natural and like you pointed out pausing for 2-3s mid sentence is super normal.
The actual implementation is at fault. I had some luck with instructing the model to only respond with "Mhm" until I've explicitly finished my thought and asked it a question. Makes this much less of an issue.
But I've decided that their voice mode is completely unusable for a different reason: the model feels incredibly dumb to interact with, keeps repeating and re-phrasing what I said, ends every single answer with a "hook" making the entire interaction idiotically robotic, completely ignores instructions when you ask it to stop that, and - most importantly - doesn't feel helpful for brainstorming. I was completely surprised how bad it is in practice; this should be their killer app but the model feels incredibly badly tuned.
Still, it’s worth to keep in mind that these are not frontier models, differently from when they were released.
(Please Sam, if you read this, release the new realtime audio models)
Just give me a option to have a slower response but better model…
Google’s Gemini flash live 3.1 is better, especially used via the API - it can do tool calling (including to other, even smarter LLMs if you set it up yourself), you can set the reasoning level (even high is still close enough to realtime) and it can ground answers in google search. I love bidirectional voice and right now it’s probably the best option. You can try it in AI studio
Another option is to use pipecat with their VAD and separate STT and TTS and any (fast) LLM of your choice - but it’s more plumbing and not a true speech to speech model
Surely the number refers to the total users of ChatGPT overall, and the fraction of those who use voice features is considerably smaller, is it not?
That’s the kind of thing that influences business decisions like knowing how much hardware and software optimization to throw at a problem.
Pipecat's smart turn model is really good for VAD - https://huggingface.co/pipecat-ai/smart-turn-v3
https://github.com/zarldev/zarl & https://www.zarl.dev/posts/hal-by-any-other-name
I've found that LiteRT-LM has a much lower DRAM footprint than Ollama. I've also made tons of optimizations in the code - for eg, you can do quite a bit with a 16k context window for a voice assistant while managing a good footprint, so I keep track of the token usage and then perform an auto-compaction after a while. I use sub-agents and only do deep-think calls with them, so the context window is separated out. In a multi-turn conversation, if Gemma 4 directly processes audio input, the KV cache fills up within a few turns, so I channel it all via Whisper.
Also, by far the biggest optimization is: 3-stage producer-consumer architecture. The LiteRT-LM streams tokens and I split them into sentences. A synthesizer thread then converts each sentence to audio via Kokoro TTS - the main thread then plays audio chunks sequentially. There's a parallel barge-in monitor thread. https://github.com/pncnmnp/strawberry/blob/main/main.py#L446
I did not want to use openWakeWord or Picovoice because they had limitations on which wake word you could choose. Alternative was to train a model of my own. So I created my own wake word detection pipeline using Whisper Tiny - works surprisingly well: https://github.com/pncnmnp/strawberry/blob/main/main.py#L143...
Also, I have VAD going with smart turn v3 (like I mentioned above) + I use browser/websocket for AEC + Barge-in (https://github.com/pncnmnp/strawberry/blob/main/audio_ws.py).
I'm using the MacBook's built-in microphones for this, though, and I haven't fully tested it with other microphones. I've been ironing out the rough edges on a daily basis. I should write a quick blog on this too.
lol, definitely didn't need to know there's 900M weekly users for this post. I mean yeah, there's a lot of users and they serve globally, that's relevant. But this is just pulling out your biggest stat because you can. How many voice users you have would actually be relevant and interesting but, to baselessly speculate on motivation here, might be a number that doesn't add as much fuel to an upcoming IPO as reminded people that you're almost at a billion users does.
- openai is wrong. almost of the issues they described are issues with libwebrtc, not with webrtc, kubernetes, network architecture, etc. the clue was when they said "the conventional one-port-per-session WebRTC model."
- there are no alternatives worth trying. everything else open source in the ecosystem, like pion, coturn, stunner, are too immature.
- libwebrtc is the only game in town.
- they haven't discovered libwebrtc feature flags or how it works with candidates, which directly fix a bunch of latency issues they are discovering. a correct feature flag can instantly reduce latency for free, compared to pay for twilio network traversal style solutions
- 99% of low latency voice END USERS will be in a network situation that can eliminate relays, transceivers, etc. it is totally first class on kubernetes. but you have to know something :)
this is the first time i'm experiencing gell mann amnesia with openai! look those guys are brilliant, but there is hardly anyone in the world who is doing this stuff correctly.
Even for clients you have things like libpeer that libwebrtc can't hit.
i think the challenge is that pion is an excellent product today. it would benefit me if its innovations were subsumed into libwebrtc, because eventually those innovations will show up in the iOS stack, which is one of the customers that matter to me. it is subjective if it is the MOST important customer, that is my belief and it is probably true of openai, at least until they get their own device out the door.
there can be many, many use cases though! not everything has to be, try to make the thing for 1b people that has to interact with all the most powerful and meanest businesses on the planet.
(though knowledge cutoffs in practice can be bit fuzzy)
Take any popular technology problem that has been around for a few years such as... wrangling Kubernetes with YAML config files. There's probably hundreds of thousands of discussions, source code samples from GitHub, official docs, blogs, bug reports, pull requests, etc... all discussing the nuances, pitfalls, pros/cons, etc. During pre-training the AIs internalise this and can utilise it later.
Now compare this with anything recent and (relatively) obscure, such as new .NET 10 features which were first officially publishing in November 2025, a month before GPT 5.5 cutoff.
As a human developer, these new language capabilities are on the same "level" for me in my day-to-day work as the features from .NET 9 or .NET 8. Similarly, my IDE has native refactoring and code cleanup support that can take C# code from the previous years and bring it up to the idiomatic style of $currentyear.
The AIs just can't do this, because one single Microsoft release note and one learn.microsoft.com page is nowhere near enough training data! The AI hasn't seen millions of lines of code written with .NET 10, taking advantage of .NET 10 improvements, and hasn't seen thousands of discussions about it. Not yet.
This is a fundamental issue with how LLMs are (currently) trained! Simply moving the cutoff date is not enough.
Human learning is second-order. If I see even the tiniest bit of updated information that invalidates a huge pile of older information, my memory marks everything old as outdated and from that second onwards I use only the new approach.
AI learning is first-order. It has to be given the discussions/blogs/posts that say "Stop using the legacy way, it's terrible! Start using the new hotness"! That, it can learn, but it'll be perpetually behind the rest of us by at least a few years.
Not to mention that thanks to AI forums like StackOverflow are dying, so... where is it going to get this kind of training data from in the future!?
AI training needs to switch to "second order", but AFAIK this is an unsolved problem at this time.
WebRTC + Kubernetes
Yet another reason to not consider anything else like that for low-latency networking. Golang (or even Rust and C++) is unmatched for this use-case.
Node.js's initial release was May 27, 2009
Golang 's initial release was November 10, 2009
They're different, yes, but it's not like