Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe.
However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone seems to be vibe coding these days.
jiehong 3 hours ago [-]
Also, this test is English-only, while a strong point of other models is to understand different languages without first having to say which one (so you don't need 3 different keyboard shortcuts if you wanna dictate in 3 languages day-to-day)
frereubu 2 hours ago [-]
Reminds me of the time my neighbours must have wondered if I was having some kind of a breakdown when trying out really basic MacOS voice recognition back in the early 2000s. There was a keyboard shortcut and you could say something like "phone number for firstname lastname" and it would theoretically show you that phone number. Thing is it didn't seem to like a British accent, so I spent a good hour trying out different accents, rotating through various US accents, Australian, South African, Canadian and so on. It seemed to respond best to some kind of a melange of Californian / Australian.
Does anyone have any experience with Mandarin STT? What's a good model for this? The use-case I have is subtitling of Mandarin speech.
verelo 3 hours ago [-]
As an Australian, Apples voice models have always sucked. I've tried using stt (again) more recently and its improved, but i'm so tired of having to Americanize my voice to get it to figure out what the hell i'm saying.
jermaustin1 3 hours ago [-]
As a Texan first, American second, I sympathize with this statement. Siri can't understand me probably 25% of the time. I use STT for iMessage while in the car, and half the time it will take 3+ times to either get it right or me give up, and hope to remember to text them by hand when I next stop.
louthy 2 hours ago [-]
As a Brit, I concur.
verelo 1 hours ago [-]
That checks out.
danabrams 3 hours ago [-]
It also struggles with my NYC-area accent, which is only medium thick.
ChadNauseam 3 hours ago [-]
> there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia
Is parakeet state of the art? It always transcribes speech fragments for me, like if I stutter and say "m-m-m-map" parakeet will dutifully transcribe "m m m map". Which I guess could be a good thing or a bad thing depending on what you want. Whisper does not do that however.
I do like cohere transcribe a lot.
robgough 36 seconds ago [-]
I think that's parakeet doing its job there. That is a closer reflection of what you've actually said. The trick is then throwing that output through some additional deterministic and non-deterministic steps to tidy it up however you prefer. It's exactly what I do with my free and open source dictation app (dictator.robgough.net) for Mac+iOS. And of course, everything stays entirely on-device. Gemma E4B is really wonderful for that second step, it's great at language – but takes up 6-7GB RAM.
If you are using Parakeet for English only then you should be using V2. V3 is for several languages and is worse at English only.
obmelvin 1 hours ago [-]
Parakeet is certainly faster on my machine (m3 max), but I can't stand using it over Whisper for dictating my prompts. It makes a lot more mistakes, possibly because (like you mentioned) large portions of the speech will pause / stutter as I think about what to include.
With whisper v3 turbo, I can almost always live with the few mistakes because the overall stream-of-thought word-salad I provide is still clear at a high level. The bits and pieces of context seem to help, that I might leave out if typing and focused more on traditional conciseness / clean writing. With parakeet, I needed to do frequent editing even for shorter bits of speech.
I realize some applications prioritize the latency.
solenoid0937 1 hours ago [-]
It sounds like post processing should be the job of an LLM. I would like the voice model to be faithful to what was said and then that output can be smoothed over or postprocessed as needed for the use case
obmelvin 1 hours ago [-]
To be clear, I'm talking about high word error rate with parakeet vs whisper, not post processing and cleaning up my speech. Re: being faithful to what was said, one small example, Whisper will often put ellipses when I pause.
parentheses 2 hours ago [-]
Agree on this point. Recent anecdotal testing I did found Whisper is still better than Parakeet.
athnak 3 hours ago [-]
Apple's own Voice Memos app already does automatic transcription since macOS 15 / iOS 18.
al_borland 2 hours ago [-]
Speech-to-text is also already built into the keyboard as well, so it can be used in any app where a user would type.
hectdev 2 hours ago [-]
From my experience, Speech-to-text falls way short of Wispr flow and I would assume the ones that are said to be better than that. It lacks context awareness and formatting
FuckButtons 1 hours ago [-]
Yeah, apple will be optimizing a model to work on ANE and then turn it into a native app. My only hope is that it has a reasonable api so that I can use that as a generic input source across iOS / macOS that’s equivalent to the ubiquity of the keyboard.
swiftcoder 5 minutes ago [-]
Presumably the existing transcribe button on the keyboard will route through this on iOS 26?
z2 52 minutes ago [-]
I don’t know how Apple divides computation between the GPU and the Neural Engine, but one major benefit, especially for real-time transcription on laptops, is the improved power and thermal efficiency. I noticed better accuracy after switching my app to SpeechAnalyzer, and I suspect part of that improvement for me came from the microphone no longer having to compete with jet-engine fan noise.
saturn8601 2 hours ago [-]
I hope they replace their awful voice to text on their keyboard. I can't stand that terrible bit of software.
Adrig 1 hours ago [-]
> RIP to a lot of the paid apps that simply wrap Whisper
I started using a few open source apps for transcription and eventually subscribed to a paid one...
On paper, it's not hard to compete, but for this use case, a few rough edges make it really frustrating to use. Like a keyboard that sometimes doubles the letter "e"
Automatic dictionary, seamless language switch, no issues with accents, etc... Putting the effort in the last mile makes a world of difference.
If anyone has better options, I'm willing to have a look. The best open source solution I found was Handy, and I currently use Wispr Flow
orbital-decay 2 hours ago [-]
Of these only Parakeet is <1B, it looks better than Apple's model, however it's not builtin. I wonder how it compares on latency and efficiency.
hendersoon 2 hours ago [-]
Parakeet is incredibly fast and accurate even on CPU, and it supports streaming now also in TDT3.
parl_match 1 hours ago [-]
Apple likely needed a model that ran on their NPU natively.
- parakeet usually runs on Bfloat16. NPU doesn't support that
- CPU is not as fast as the NPU for these ops on A-series, and even on modern CPUs, there's a latency delay
- Parakeet latency is fine but "fine" may not be good enough for Apple's UX team.
- CPU increases power consumption over dedicated float blocks
So I would say that Parakeet was a non-option for Apple to ship, although it should be in the benchmarks anyways!
foobarqux 1 hours ago [-]
Fluidaudio implements Parakeet on ANE. I'd like to know how SpeechAnalyzer compares in speed.
I’m not sure I agree. There may be better models, but the comparison is still useful so long as whisper is so widely used.
wahnfrieden 3 hours ago [-]
For multilingual and noisy audio the best right now is MOSS-Transcribe-Diarize which was released just a few days ago
Superwhisper does a lot more than just provide a whisper/parakeet UI so I’m not sure Apple will destroy them so easily
satvikpendem 3 hours ago [-]
Thanks, was looking at a better diarization model.
Even for those sorts of apps, MacParakeet which I've been using is FOSS so no payment needed. In reality these days with AI the ability to spin up a free and/or OSS competitor falls to zero.
wahnfrieden 3 hours ago [-]
I’m not even using it for diarisation just transcription and it’s amazing. It also doesn’t need a VAD
A new VAD I found though is FireRedVAD which has better benchmark results than TEN and Silero by far
techsystems 2 hours ago [-]
Interesting! And what would you say are MTD top competitors?
foobarqux 1 hours ago [-]
16GB! Compared to Parakeet 2.3GB (but no diarization).
Also doesn't seem to be tailored to Apple hardware (i.e. no MLX or ANE variant/implementation)
elAhmo 1 hours ago [-]
I use handy.computer and it is pretty much everything I want from a transcribing app.
permalac 1 hours ago [-]
Hey. Yes.
I did vive code one as an exercise yo learn how to publish to apple store.
Listen and transcribe felt like the easiest thing to do.
Distavo.com
The source is open for anyone to use, and the builds are in github.
I found quite interesting that claude didn't help too much on how to publish to SetApp until Fable.
BeetleB 1 hours ago [-]
How many of the Whisper competitors will work at a reasonable speed using only CPU (on Linux, not Apple)?
(Genuine question - I'm a happy Whisper user but am always looking for improvements).
bellowsgulch 2 hours ago [-]
> However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone seems to be vibe coding these days.
What's insane to me is that you have all of these low-quality me-too apps, and literally no one could bother to read the damn Human Interface Guidelines or follow iOS design conventions.
Doing so is literally LESS WORK than trying to make your own custom awful iOS UI.
ChrisMarshallNY 1 hours ago [-]
Not if your app is a Web wrapper, which so many of these are.
If you use SwiftUI (the native recommendation by Apple), it severely penalizes you, if you want to paint outside the lines (which is a big reason that I don't use SwiftUI for shipping apps). It's insanely easy to write a native app that is 100% in line with HIG.
llm_nerd 41 minutes ago [-]
This particular product used Whisper, so that was obviously the right model to compare it against. Further this is explicitly on device, and Nemotron 3.5, as one example, is 2.5GB for the model.
And if someone were broadly comparing all on-device models (instead of just looking at how this new on-device ones compares to what a specific product uses), Nemotron 3.5's WER are actually a bit higher than what they report for SpeechAnalyzer, for both tests.
trencedamp 3 hours ago [-]
Came here to post this. I use handy on my own machine and it's perfect with parakeet. If I switch to whisper it makes lots of mistakes
mchusma 1 hours ago [-]
I will plug Willow for mac recording. IMO it's basically to me a "better than perfect transcription" as it cleans things up and is almost instant. I liked Superwhisper but switched to Willow as it was a big difference.
Its so good that I'm not sure that it's possible to get any better. Speech to text seems like basically a solved problem, if not now then definitely in 5 years. I don't know if any of these speech to text businesses will work in the long run, but for consumers they are great. My guess is the 2030 version of Apple's SpeechAnalyzer will be so good that nobody will need to use 3rd party software.
ashivkum 3 hours ago [-]
Just ran it against Whisper-Large-V2 on a math lecture (my primary use case for ASR is subtitling math lectures), and it was substantially faster and only slightly worse. Very usable for live transcription though I'll probably stick with whisper for the time being since I don't really need the subtitles to be generated in real time.
seviu 3 hours ago [-]
Been using it for a podcast app I have been developing for half a year lol (I hope I publish it by version 27) and I can confirm it’s real fast.
Splitting the audio in multiple segments and firing it up without hitting the maximum limit of concurrent decoding streams makes it blazing fast. Fair enough you loose the cut, but it’s good enough for just podcast. In one minute it chews through one hour of audio. This on an iPhone 17 Pro.
rokkamokka 19 minutes ago [-]
You could perhaps run over the segment splitting points (plus a few seconds back and forward) in a second batch then merge the results in the end so you don't miss anything.
satvikpendem 3 hours ago [-]
What's different about your podcast app?
seviu 3 hours ago [-]
Nothing really, except that I get to play with SpeechAnalyzer APIs, foundation models, translations. It’s basically my playground where to try all things. Been listening a lot of Chinese podcasts lately, transcribed and translated by local models.
Edit: all that said, the app is irrelevant. What I want to say is that live transcripts on iOS using Apples frameworks works very well. Only thing I miss is diarization support.
Chu4eeno 3 hours ago [-]
If it was faster but worse, maybe compare it to a smaller whisper model?
generalizations 3 hours ago [-]
I imagine because quality of transcription is what matters.
wgm 49 minutes ago [-]
Is this the new dictation engine that I'm not allowed to run on my 1-YEAR-OLD IPHONE 17 because it's not Pro?
monster_truck 30 minutes ago [-]
Why did you buy the cheap one, that's your own fault
wgm 28 minutes ago [-]
At the time, there was very little advantage to buying the Pro model. Ironically, it's the first time I've ever bought the base model.
modeless 4 hours ago [-]
Whisper small/tiny/base are almost four years old (they were not updated for Whisper v2 or v3). Is there really nothing better to benchmark against by now?
satvikpendem 3 hours ago [-]
There are many [0], you can search and filter by streaming and open weight only as well.
Looks like Voxtral and Nvidia's Nemotron are best.
There's tons, Parakeet was the last I remember seeing which seemed to gain traction (independent lightweight implementations etc).
garblegarble 3 hours ago [-]
I have tried everything (that will run on a 12GB RTX 4070) and I have yet to find anything with better accuracy than Whisper V2 Large for my dataset (discord audio from TTRPG sessions, isolated per-speaker, mostly non-American accents)
xd1936 3 hours ago [-]
Same, for my English-only podcast
modeless 2 hours ago [-]
Not v3?
satvikpendem 3 hours ago [-]
Nvidia's Nemotron subsumes their older Parakeet model now even for real time streaming.
daemonologist 3 hours ago [-]
Parakeet is way faster (on Nvidia hardware) but not quite as accurate in my experience.
meatmanek 3 hours ago [-]
It's also super fast on CPU.
behnamoh 3 hours ago [-]
Parakeet isn't as good as whisper large.
MBCook 4 hours ago [-]
Impressive. Apple said they improved the models in 27 didn’t they? It would be interesting to see the numbers the beta turns in.
summarity 3 hours ago [-]
Vs Voxtral would be a better comparison. No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts. Seems to understand/infer all the technobabble I use at work. Never have to edit anything. Whisper was catastrophically bad.
pants2 2 hours ago [-]
I typically disable autocorrect on Apple products because of this, cautiously optimistic about their improved speech models, but definitely worried that it's going to 'correct' technical jargon to more common words.
dsalzman 18 minutes ago [-]
If you are running ios 27 beta is this the model when you hit voice to text on the native keyboard?
dclowd9901 1 hours ago [-]
I'm always confused by these phrases:
> The new API cuts word error rate by 3.5 to 4x on the same audio: from 9.02% to 2.12% on clean speech
Shouldn't they have said "cuts error rate by 78%" or something?
clickety_clack 54 minutes ago [-]
I don’t like it written that way either, and it always seems like the type of number you put on a slide for a head of sales or something. It rankles because:
- it implies that error could be increased n-times, but a 15x _increase_ in 9% error would be an error rate of 135%, which is nonsensical.
- a reduction from 90% error to 20% error is clearly a bigger improvement in rightness to a reduction from 9% to 2%. One is “almost all wrong to almost all right”, the other is “more right”, but they are both a 4.5x reduction in error which means that the 4.5 quantity doesn’t have a constant meaning.
The answer is something like log odds ratios, but that introduces the additional need for a reader to know what that is, and that would be unusual.
port3000 3 hours ago [-]
I use Spokenly, offline-only mode with the Nvidia model. All local, totally free. Highly recommend
endymi0n 2 hours ago [-]
Finally. I‘d be delighted though if they actually implemented language autodetection (like everywhere else) though. There’s little more frustrating in my day to day than having dictated half a page to find that it‘s complete gibberish because Apple forces you to select the right language first…
QGQBGdeZREunxLe 1 hours ago [-]
Same with the keyboard. Apple is completely incapable of taking context into account for the input mechanisms of the operating system.
If I start typing and the existing text is in Spanish, then a sensible default is to select the Spanish keyboard I have installed and let me adjust otherwise.
App developers should also be allowed to supply mini-dictionaries within a context to allow autocorrect to work correctly in that context, so for example in this thread [SpeechAnalyzer, API, Whisper, Parakeet, Nemotron] should be supplied so that these terms are autocorrected.
Tsarp 3 hours ago [-]
Any chance you can benchmark against whisper large and large v3 turbo? These run comfortably on older Macbooks and are still far more accurate in real life dictation compared to even the parakeet models( despite ASR leaderboards) with an RTF < 1.
wahnfrieden 3 hours ago [-]
Try MOSS-Transcribe-Diarize from a few days ago. I’m getting better results than those whisper models. And it’s very fast and small. Better suited to noisy audio too.
sudb 2 hours ago [-]
For my current purposes, I need a speech-to-text model/API to also emit word-level timestamps - for now, that makes ElevenLabs's Scribe v2 the best multiplatform, multi-language choice though it does look like this SpeechAnalyzer API provides them (although only for English).
gdonelli 4 hours ago [-]
I second that! Can you run your benchmarks against the iOS 27 beta?
dubeye 1 hours ago [-]
Cloud is so cheap and quick. I use local too but my api bill is like 3 quid a month. You would have to be very cheap or have compliance needs to tolerate the error gap
mmis1000 2 hours ago [-]
Every single asr model I tested so far did not support timestamps properly though. Some use external aligner to create timestamp, but the accuracy is still much inferior than whipser in case the audio is noisy.
elicash 1 hours ago [-]
I'm looking for good and cheap transcription + speaker diarization on my Mac for a small personal project. Recs?
sherlock-holmes 1 hours ago [-]
i wish they had benchmarked it against parakeet-unified-en-0.6b and cohere-transcribe-03-2026. i am using parakeet with https://handy.computer daily and it's amazing.
ks2048 3 hours ago [-]
Lots of comments are "you should compare against X and Y" - even better, just get the results on a standard benchmark, so you can compare against all,
Supports SRT/TXT/VTT or JSON-with-optional-word-level-timestamps output and progress meter.
Also it can transcribe live system audio.
m3kw9 3 hours ago [-]
Yeah i do find apple's speech to text very good lately and no need to use openai or anything that seem to market their services better
drnick1 3 hours ago [-]
If this isn't open source/weights and can't run locally, I don't see how this is a replacement for Whisper or other open models, e.g. within Home Assistant.
satvikpendem 3 hours ago [-]
It's a local model so it's essentially open weight such that you could feasibly export it somehow since it's already on the laptop somewhere. Apfel is a wrapper app like ChatGPT but using Apple Foundation Models, I assume something similar will happen with this transcription model.
It's not open weight, but the point is to be an on device (and thus local, privacy preserving) option. The article mentions that as the caveat
> What this means if you just want good transcription
> If you are on a current iPhone or Mac, the best on-device transcription engine for English is already in the operating system, and the private option is no longer the compromise option
drnick1 3 hours ago [-]
> It's not open weight, but the point is to be an on device (and thus local, privacy preserving) option.
How can you be sure this isn't leaking data or metadata to Apple? Can Apple really be trusted?
edude03 18 minutes ago [-]
The article states:
> If you are on a current iPhone or Mac
Presumably if you don't trust apple you wouldn't purchase their products and even if you were for example forced to use it via work or something you wouldn't use this feature ... so it doesn't really change the calculus as presented by this article - IF you ALREADY HAVE a MODERN Mac (and trust apple) this is your best option
madeofpalk 2 hours ago [-]
Test it! Does it make network requests? Unplug the internet and see if it still works!
drnick1 1 hours ago [-]
You are being naive. An Apple device makes dozens of network requests every minute or so to Apple. It is neigh on impossible to verify what is being requested or sent. Also unplugging the Internet and verifying that something still works does not mean the app won't phone home behind your back when it can. These things are designed to fail silently.
wahnfrieden 3 hours ago [-]
It is local
The appeal is that users only have to download it once across all apps that use it. Instead of convincing a user to give a couple gigs for just your one app
pmkary 3 hours ago [-]
This is great marketing, I had no idea what inscribe was, but a blog like this going viral did something no ad could do for me.
canadiantim 3 hours ago [-]
Anyone know the best choice these days specifically for speaker diarization?
petesergeant 2 hours ago [-]
I'd be interested too. Last time I looked the state of the art was pretty bad.
pzo 3 hours ago [-]
I stopped reading after seeing they compared only with Whisper Small, Base, Tiny
This is useless test and benchmark when you have these day Whisper-V3-Large and Whisper V3-Turbo that you can faster than realtime on 5 years old macbook on apple sillicon (ANE). They didn't even compared to parakeet v2 or parakeet v3. And only english language...
hendersoon 2 hours ago [-]
OK, but how does it compare against Parakeet TDT2 (english), TDT3 (many languages), and Parakeet TDT3 Streaming? And what about whisper large?
tancop 4 hours ago [-]
this is amazing. if i had a mac i would try to reverse engineer the code, extract the weights and port it to something that works on linux/windows like torch or burn. then put the code on github and weights on a torrent site. lifes too short to let apple keep their models exclusive.
ks2048 3 hours ago [-]
Probably not worth the effort (or legal trouble), unless you can show it's better than other recent open models like Cohere Transcribe.
kridsdale1 4 hours ago [-]
Is that copyright infringement?
nodja 3 hours ago [-]
This hasn't been tested in court. But there's a high chance that model weights are not copyrightable, only the code to generate them is.
Cloud models are usually protected by trade secret laws, leaking them would get you in trouble. However if the model is made available publicly, as long as you don't break the law to get them, anything after that would be fair game unless Apple can prove that humans have significant authorship over the weights, which hasn't been tested and is a significant burden to prove/disprove.
layer8 3 hours ago [-]
Copyright protects original forms of expression, not arbitrary data. It is very arguable whether it applies to model weights. However, it would likely constitute a license violation.
altmanaltman 3 hours ago [-]
Aside from the legality of it, I think you are underestimating how complex it can be to do that. It is possible in theory but not something that will be a fun side quest like you are making it seem.
johncoatesdev 3 hours ago [-]
With a IDA Pro decompiler license & MCP server, paired with Codex/Claude Code... it would be a fun side quest.
edude03 3 hours ago [-]
You likely don't need to disassemble the inference code, the weights are "just an array of numbers" in MLX format.
saagarjha 6 minutes ago [-]
I believe they are are protected on disk
bilbo0s 3 hours ago [-]
This.
The Jedi Hand Wave-y nature of the way people talk about AI these days is going to make reigning in the AI superpowers nearly impossible. Because there are people out here who believe models of this quality are easily replicated or reverse engineered. Neither is really doable on any reasonable timeline by people who are not AI experts. Real AI experts. Not TF/PyTorch monkeys or Agent Slop Slingers.
And those people are already highly incentivized to not make anything performing better than SOTA models open source.
polycancel 3 hours ago [-]
[dead]
paul7986 4 hours ago [-]
Im hoping Apple gets the new Siri working better on older phones. I was excited to use it but the latest beta / Siri runs too slow on my iPhone Pro Max 15.
Im looking for the same experience I have when talking to chatGPT. As for past two years or more talking to GPT within it's app and on my iPhone Pro Max 15 it runs smooth as butter :-). This is the experience I was and still am hoping with Apple, but Im thinking all the extra layers of privacy and security might be slowing them down?
Overall, Apple who is suing Open AI should just buy them and let me have the best conversational AI out there baked into my old ass iPhone. Because as so far the new Siri on my old phone (tho again GPT works great talking to it and for years) doesnt come close. It's the same old "Could you try that again," Siri. BOO!!!
realityfactchex 4 hours ago [-]
Yeah, ChatGPT voice is great experience vs. Siri on that phone. In case you haven't done something like this already:
1. In Shortcuts app, make shortcut named "AI Voice Mode" (or whatever you want, YMMV)
2. Set it to run the ChatGPT action "Voice Mode" (requires at least the minimum paid tier, I think)
3. To trigger, say "Hey Siri, AI Voice Mode" (or whatever you called the shortcut)
This is a pretty slick integration, but yeah, if it were baked in that would be all the better.
kridsdale1 4 hours ago [-]
You can also map the Action Button to GPT voice mode.
paul7986 3 hours ago [-]
Ridiculous that for past many years we can talk to GPT on our iPhones without any hiccups and this new Siri is still the same old horse crap (at least for me and this latest beta). Buy them already Apple or possibly be replaced by them as their path & trajectory (working on Ai devices now and they are stealing like Jobs did with Xerox) mirrors yours in the late 1970s.
Thanks for the tip and if Im not mistaken it's similar to asking Siri to ask chatGPT to ask XYZ?
realityfactchex 3 hours ago [-]
> similar to asking Siri to ask chatGPT to ask XYZ
Effectively, it sort of does that, but really it just listens to the wakeword and opens/switches to the requested app & modality.
FWIW, I get a very different functional result using the Shortcut method vs. asking Siri to delegate natively. To compare, I asked Siri (non-beta here) now to "ask ChatGPT <x>" and I got a top-card with some fairly low quality SEO-ranked weblinks.
kridsdale1 4 hours ago [-]
I’m on iPhone 17 Pro Max, 27 beta 3.
New Siri is impressive in that it answers satisfactorily now 80% of the time vs 10% with old Siri.
But it’s slow as shit. GPT, Claude, and Gemini can answer me in 5-10 seconds. Google AI Mode can answer in 2 seconds.
New Siri usually takes 25 seconds to respond to me. This morning it timed out (with strong network connection) when asked a simple multiplication question.
paul7986 3 hours ago [-]
Damn slow on your newer phone too.
rconti 2 hours ago [-]
That's crappy, but it's also a beta, so it's not yet time to render a verdict.
behnamoh 3 hours ago [-]
> Im hoping Apple gets the new Siri working better on older phones.
Apple would never do that, if anything they did not offer their Siri with the most advanced AI on iPhone 16 Pro Max, which is one year-old only.
get-inscribe 4 hours ago [-]
Author here. I ship both Apple speech engines plus WhisperKit side by side in a transcription app, which made it possible to run all five through identical production code on the same audio: LibriSpeech test-clean and test-other, 5,559 utterances, fully on-device on an M2 Pro.
Apple published no accuracy numbers for SpeechAnalyzer (or for SFSpeechRecognizer, ever, as far as I can tell), so the migration question has been guesswork. Short version: the new API cuts WER 3.5-4x vs the old one (2.12% vs 9.02% on test-clean), and it also beat Whisper Small on both splits at about 3x the speed. The old API came in last on clean speech, behind even Whisper Tiny.
On "why should I trust a vendor benchmark": the Whisper column reproduces OpenAI's published LibriSpeech WERs within +0.11 to +0.42 on all six measurements (same corpus, same normalizer, same scorer for every engine), and the raw per-utterance transcripts are downloadable from the article if anyone wants to rescore with their own normalizer.
Limitations worth stating up front: English only, read speech rather than meeting audio, one machine. Precise per-engine timing isn't in the article yet because the accuracy runs shared the machine with a dev workload; WER is load-independent, timing isn't.
Two things that might interest people migrating: SFSpeechRecognizer sends audio to Apple's servers unless you set requiresOnDeviceRecognition, and with SpeechAnalyzer, finishing your input stream is not enough to end a session. If you never call finalizeAndFinishThroughEndOfInput(), the results sequence never terminates and your await hangs forever. I found that one because it was shipping in my own app.
Happy to answer questions about the harness or the normalizer.
coder543 3 hours ago [-]
At this point, I would not recommend ignoring Parakeet TDT 0.6b v2/v3 (english-only versus multilingual). Those models have been out for a year, give or take, and they are both accurate and fast. I would choose Parakeet over Whisper in almost all situations these days. Parakeet works great even on my several year old iPhone 15 Pro Max, so if an app is going to ship a dedicated model, I strongly recommend investigating Parakeet.
On the more cutting edge front, Granite Speech 4.1 has proven to be a reliable workhorse for me, but it is larger than Parakeet. Cohere Transcribe is interesting, but how strong it is seems to vary more from task to task.
Parakeet Unified 0.6B came out a few months ago, combining both online streaming and offline transcription into one model, and that is one that I need to test more, but it seems promising.
As others have mentioned macOS 27/iOS 27 is supposed to have a new model, particularly on devices with 12GB of RAM or more. I have not actually seen the option to enable that new model yet, though, despite being on the beta on a device that meets the requirements. Maybe a benchmark would reveal that it is already active?
satvikpendem 3 hours ago [-]
Why do you not use Whisper large models when on macOS? They're still fast even when streaming and yield a much lower WER.
Also, just out of curiosity, seems like everyone and their mother is making Whisper wrappers, how is your app different?
Chu4eeno 3 hours ago [-]
Why use relatively ancient models like whisper and not e. g. parakeet?
Still nothing beats OpenAI's VTT. Anthropic's sucks and Apple's isn't even usable.
Edit: Getting downvoted by Apple fanboys for telling the truth is a badge of honor.
3 hours ago [-]
simonw 4 hours ago [-]
Which OpenAI model/API do you mean?
behnamoh 3 hours ago [-]
Whisper and GPT-4o (for diarization).
nicce 3 hours ago [-]
In which world 98% accuracy is not usable?
behnamoh 3 hours ago [-]
In a world where you say "tmux" and Apple's VTT writes "T Max".
gobdovan 2 hours ago [-]
You can't reasonably expect generic ASR to infer tmux from "tee-mucks". "tee-em-you-ex" works reliably if you're ok with capitalisation for your use case.
Wacari 3 hours ago [-]
agreed. plus all the languages supported!
Rendered at 20:10:30 GMT+0000 (Coordinated Universal Time) with Vercel.
However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone seems to be vibe coding these days.
Is parakeet state of the art? It always transcribes speech fragments for me, like if I stutter and say "m-m-m-map" parakeet will dutifully transcribe "m m m map". Which I guess could be a good thing or a bad thing depending on what you want. Whisper does not do that however.
I do like cohere transcribe a lot.
With whisper v3 turbo, I can almost always live with the few mistakes because the overall stream-of-thought word-salad I provide is still clear at a high level. The bits and pieces of context seem to help, that I might leave out if typing and focused more on traditional conciseness / clean writing. With parakeet, I needed to do frequent editing even for shorter bits of speech.
I realize some applications prioritize the latency.
I started using a few open source apps for transcription and eventually subscribed to a paid one...
On paper, it's not hard to compete, but for this use case, a few rough edges make it really frustrating to use. Like a keyboard that sometimes doubles the letter "e"
Automatic dictionary, seamless language switch, no issues with accents, etc... Putting the effort in the last mile makes a world of difference.
If anyone has better options, I'm willing to have a look. The best open source solution I found was Handy, and I currently use Wispr Flow
- parakeet usually runs on Bfloat16. NPU doesn't support that
- CPU is not as fast as the NPU for these ops on A-series, and even on modern CPUs, there's a latency delay
- Parakeet latency is fine but "fine" may not be good enough for Apple's UX team.
- CPU increases power consumption over dedicated float blocks
So I would say that Parakeet was a non-option for Apple to ship, although it should be in the benchmarks anyways!
https://github.com/FluidInference/FluidAudio
https://github.com/finnvoor/yap
Superwhisper does a lot more than just provide a whisper/parakeet UI so I’m not sure Apple will destroy them so easily
Even for those sorts of apps, MacParakeet which I've been using is FOSS so no payment needed. In reality these days with AI the ability to spin up a free and/or OSS competitor falls to zero.
A new VAD I found though is FireRedVAD which has better benchmark results than TEN and Silero by far
Also doesn't seem to be tailored to Apple hardware (i.e. no MLX or ANE variant/implementation)
Listen and transcribe felt like the easiest thing to do.
Distavo.com
The source is open for anyone to use, and the builds are in github.
I found quite interesting that claude didn't help too much on how to publish to SetApp until Fable.
(Genuine question - I'm a happy Whisper user but am always looking for improvements).
What's insane to me is that you have all of these low-quality me-too apps, and literally no one could bother to read the damn Human Interface Guidelines or follow iOS design conventions.
Doing so is literally LESS WORK than trying to make your own custom awful iOS UI.
If you use SwiftUI (the native recommendation by Apple), it severely penalizes you, if you want to paint outside the lines (which is a big reason that I don't use SwiftUI for shipping apps). It's insanely easy to write a native app that is 100% in line with HIG.
And if someone were broadly comparing all on-device models (instead of just looking at how this new on-device ones compares to what a specific product uses), Nemotron 3.5's WER are actually a bit higher than what they report for SpeechAnalyzer, for both tests.
Its so good that I'm not sure that it's possible to get any better. Speech to text seems like basically a solved problem, if not now then definitely in 5 years. I don't know if any of these speech to text businesses will work in the long run, but for consumers they are great. My guess is the 2030 version of Apple's SpeechAnalyzer will be so good that nobody will need to use 3rd party software.
Splitting the audio in multiple segments and firing it up without hitting the maximum limit of concurrent decoding streams makes it blazing fast. Fair enough you loose the cut, but it’s good enough for just podcast. In one minute it chews through one hour of audio. This on an iPhone 17 Pro.
Edit: all that said, the app is irrelevant. What I want to say is that live transcripts on iOS using Apples frameworks works very well. Only thing I miss is diarization support.
Looks like Voxtral and Nvidia's Nemotron are best.
[0] https://artificialanalysis.ai/speech-to-text/non-streaming
> The new API cuts word error rate by 3.5 to 4x on the same audio: from 9.02% to 2.12% on clean speech
Shouldn't they have said "cuts error rate by 78%" or something?
- it implies that error could be increased n-times, but a 15x _increase_ in 9% error would be an error rate of 135%, which is nonsensical.
- a reduction from 90% error to 20% error is clearly a bigger improvement in rightness to a reduction from 9% to 2%. One is “almost all wrong to almost all right”, the other is “more right”, but they are both a 4.5x reduction in error which means that the 4.5 quantity doesn’t have a constant meaning.
The answer is something like log odds ratios, but that introduces the additional need for a reader to know what that is, and that would be unusual.
If I start typing and the existing text is in Spanish, then a sensible default is to select the Spanish keyboard I have installed and let me adjust otherwise.
App developers should also be allowed to supply mini-dictionaries within a context to allow autocorrect to work correctly in that context, so for example in this thread [SpeechAnalyzer, API, Whisper, Parakeet, Nemotron] should be supplied so that these terms are autocorrected.
https://huggingface.co/spaces/hf-audio/open_asr_leaderboard
Supports SRT/TXT/VTT or JSON-with-optional-word-level-timestamps output and progress meter.
Also it can transcribe live system audio.
https://apfel.franzai.com/
> What this means if you just want good transcription
> If you are on a current iPhone or Mac, the best on-device transcription engine for English is already in the operating system, and the private option is no longer the compromise option
How can you be sure this isn't leaking data or metadata to Apple? Can Apple really be trusted?
> If you are on a current iPhone or Mac
Presumably if you don't trust apple you wouldn't purchase their products and even if you were for example forced to use it via work or something you wouldn't use this feature ... so it doesn't really change the calculus as presented by this article - IF you ALREADY HAVE a MODERN Mac (and trust apple) this is your best option
The appeal is that users only have to download it once across all apps that use it. Instead of convincing a user to give a couple gigs for just your one app
This is useless test and benchmark when you have these day Whisper-V3-Large and Whisper V3-Turbo that you can faster than realtime on 5 years old macbook on apple sillicon (ANE). They didn't even compared to parakeet v2 or parakeet v3. And only english language...
Cloud models are usually protected by trade secret laws, leaking them would get you in trouble. However if the model is made available publicly, as long as you don't break the law to get them, anything after that would be fair game unless Apple can prove that humans have significant authorship over the weights, which hasn't been tested and is a significant burden to prove/disprove.
The Jedi Hand Wave-y nature of the way people talk about AI these days is going to make reigning in the AI superpowers nearly impossible. Because there are people out here who believe models of this quality are easily replicated or reverse engineered. Neither is really doable on any reasonable timeline by people who are not AI experts. Real AI experts. Not TF/PyTorch monkeys or Agent Slop Slingers.
And those people are already highly incentivized to not make anything performing better than SOTA models open source.
Im looking for the same experience I have when talking to chatGPT. As for past two years or more talking to GPT within it's app and on my iPhone Pro Max 15 it runs smooth as butter :-). This is the experience I was and still am hoping with Apple, but Im thinking all the extra layers of privacy and security might be slowing them down?
Overall, Apple who is suing Open AI should just buy them and let me have the best conversational AI out there baked into my old ass iPhone. Because as so far the new Siri on my old phone (tho again GPT works great talking to it and for years) doesnt come close. It's the same old "Could you try that again," Siri. BOO!!!
Thanks for the tip and if Im not mistaken it's similar to asking Siri to ask chatGPT to ask XYZ?
Effectively, it sort of does that, but really it just listens to the wakeword and opens/switches to the requested app & modality.
FWIW, I get a very different functional result using the Shortcut method vs. asking Siri to delegate natively. To compare, I asked Siri (non-beta here) now to "ask ChatGPT <x>" and I got a top-card with some fairly low quality SEO-ranked weblinks.
New Siri is impressive in that it answers satisfactorily now 80% of the time vs 10% with old Siri.
But it’s slow as shit. GPT, Claude, and Gemini can answer me in 5-10 seconds. Google AI Mode can answer in 2 seconds.
New Siri usually takes 25 seconds to respond to me. This morning it timed out (with strong network connection) when asked a simple multiplication question.
Apple would never do that, if anything they did not offer their Siri with the most advanced AI on iPhone 16 Pro Max, which is one year-old only.
Apple published no accuracy numbers for SpeechAnalyzer (or for SFSpeechRecognizer, ever, as far as I can tell), so the migration question has been guesswork. Short version: the new API cuts WER 3.5-4x vs the old one (2.12% vs 9.02% on test-clean), and it also beat Whisper Small on both splits at about 3x the speed. The old API came in last on clean speech, behind even Whisper Tiny.
On "why should I trust a vendor benchmark": the Whisper column reproduces OpenAI's published LibriSpeech WERs within +0.11 to +0.42 on all six measurements (same corpus, same normalizer, same scorer for every engine), and the raw per-utterance transcripts are downloadable from the article if anyone wants to rescore with their own normalizer.
Limitations worth stating up front: English only, read speech rather than meeting audio, one machine. Precise per-engine timing isn't in the article yet because the accuracy runs shared the machine with a dev workload; WER is load-independent, timing isn't.
Two things that might interest people migrating: SFSpeechRecognizer sends audio to Apple's servers unless you set requiresOnDeviceRecognition, and with SpeechAnalyzer, finishing your input stream is not enough to end a session. If you never call finalizeAndFinishThroughEndOfInput(), the results sequence never terminates and your await hangs forever. I found that one because it was shipping in my own app.
Happy to answer questions about the harness or the normalizer.
On the more cutting edge front, Granite Speech 4.1 has proven to be a reliable workhorse for me, but it is larger than Parakeet. Cohere Transcribe is interesting, but how strong it is seems to vary more from task to task.
Parakeet Unified 0.6B came out a few months ago, combining both online streaming and offline transcription into one model, and that is one that I need to test more, but it seems promising.
As others have mentioned macOS 27/iOS 27 is supposed to have a new model, particularly on devices with 12GB of RAM or more. I have not actually seen the option to enable that new model yet, though, despite being on the beta on a device that meets the requirements. Maybe a benchmark would reveal that it is already active?
Also, just out of curiosity, seems like everyone and their mother is making Whisper wrappers, how is your app different?
MOSS-Transcribe-Diarize
Edit: Getting downvoted by Apple fanboys for telling the truth is a badge of honor.