• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

NVIDIA RTX Voice: Real-World Testing & Performance

Inle

Staff member
Joined
Apr 6, 2017
Messages
213 (0.14/day)
System Name Efrafa
Processor Intel Core i7-5960X @ 4,3 GHz
Motherboard Asus X99 STRIX Gaming
Cooling NZXT Kraken X52
Memory G.Skill Ripjaws 4 32 GB
Video Card(s) Asus ROG STRIX GeForce GTX 1080 OC Edition
Storage ADATA SX8000 NVMe 512 GB + 5x Kingston HyperX Savage 512 GB
Display(s) Acer Predator XB271HU
Case Corsair Crystal 460X
Audio Device(s) Audiolab M-DAC
Power Supply Seasonic X-850
Mouse Logitech G900 Chaos Spectrum
Keyboard Cherry MX Board 6.0
Software Battlefield 1
NVIDIA's RTX Voice technology promises to remove background noise from your audio input and output. We tested it on a wide range of audio hardware, at many price points, to find out what it's capable of, and how it affects frame rates during gaming.

Show full review
 
Joined
Nov 11, 2016
Messages
1,410 (0.86/day)
System Name The de-ploughminator
Processor I7 9900K @ 5.1Ghz
Motherboard Gigabyte Z370 Gaming 5
Cooling Custom Watercooling
Memory 4x8GB G.Skill Trident Neo 3600mhz 15-15-15-30
Video Card(s) RTX 3090 + Bitspower WB
Storage Plextor 512GB nvme SSD
Display(s) LG OLED CX48"
Case Lian Li 011D Dynamic
Audio Device(s) Creative AE-5
Power Supply Corsair RM1000
Mouse Razor Viper Ultimate
Keyboard Corsair K75
Software Win10
I don't think RTX Voice is gonna be any detrimental to FPS if you cap the FPS to your monitor refresh rate, which everyone should have done anyways.
 

Cheeseball

Not a Potato
Supporter
Joined
Jan 2, 2009
Messages
1,494 (0.33/day)
Location
Pittsburgh, PA
System Name Custom AMD Rig
Processor AMD Ryzen™ 7 3800X
Motherboard ASUS TUF GAMING X570-PLUS (WI-FI)
Cooling EVGA CLC 280mm AIO Liquid Cooler
Memory G.SKILL TridentZ 32GB (8GBx4) F4-3200C16-8GTZR
Video Card(s) EVGA GeForce RTX 3080 FTW3 ULTRA GAMING 10GB
Storage 250GB Samsung 970 EVO NVMe, 2TB Inland Premium NVMe, 1TB Crucial MX500 SATA, 4TB WD Blue SATA
Display(s) Acer Nitro XV340CK Pbmiipphzx 34" UWQHD 1440p, LG 27GN850-B UltraGear 27" 1440p 144 Hz
Case NZXT H510i Matte White
Audio Device(s) Kanto Audio YU2 and SUB8 Desktop Speakers and Subwoofer, Blue Yeti
Power Supply Corsair RMx Series RM750x 750W
Mouse Kingston HyperX Pulsefire Haste
Keyboard Kingston HyperX Alloy Origins Core
Software Windows 10 Pro 64-bit 20H2
I don't think RTX Voice is gonna be any detrimental to FPS if you cap the FPS to your monitor refresh rate, which everyone should have done anyways.

It's best to cap FPS within the game if there is an existing setting. V-Sync's major disadvantages has been mostly mitigated with advancements in adaptive sync, but it still does cause minimal (but still noticable) input lag, especially when FPS drops occur OR if the FPS goes over the monitor refresh rate.

My practice is to disable adaptive sync when playing any competitive shooters then enable it for a better overall experience in other games.
 
Joined
Jun 28, 2016
Messages
3,595 (2.02/day)
@Inle
We could use a test on a card without Tensor Cores - i.e. if it's just as effective and how the GPU load looks.
Can you do this? Same procedure, if possible.

Some GPU load has to happen even on RTX cards. Tensor Cores don't run the whole code - just the (large) matrix operations involved.

@Ferrum Master
How is your "hardware could do this long time ago" theory working so far? :D
 
Joined
Jul 10, 2015
Messages
565 (0.26/day)
Location
Sokovia
System Name Alienation from family
Processor i7 7700k
Motherboard Hero VIII
Cooling Macho revB
Memory 16gb Hyperx
Video Card(s) Asus 1080ti Strix OC
Storage 960evo 500gb
Display(s) AOC 4k
Case Define R2 XL
Power Supply Be f*ing Quiet 600W M Gold
Mouse NoName
Keyboard NoNameless HP
Software You have nothing on me
Benchmark Scores Personal record 100m sprint: 60m
Great test, Inle. I am not impressed with keyboard result, its still there in the background. Not magic :'(
 
Joined
Nov 11, 2016
Messages
1,410 (0.86/day)
System Name The de-ploughminator
Processor I7 9900K @ 5.1Ghz
Motherboard Gigabyte Z370 Gaming 5
Cooling Custom Watercooling
Memory 4x8GB G.Skill Trident Neo 3600mhz 15-15-15-30
Video Card(s) RTX 3090 + Bitspower WB
Storage Plextor 512GB nvme SSD
Display(s) LG OLED CX48"
Case Lian Li 011D Dynamic
Audio Device(s) Creative AE-5
Power Supply Corsair RM1000
Mouse Razor Viper Ultimate
Keyboard Corsair K75
Software Win10
It's best to cap FPS within the game if there is an existing setting. V-Sync's major disadvantages has been mostly mitigated with advancements in adaptive sync, but it still does cause minimal (but still noticable) input lag, especially when FPS drops occur OR if the FPS goes over the monitor refresh rate.

My practice is to disable adaptive sync when playing any competitive shooters then enable it for a better overall experience in other games.

I use Nvidia maximum fps in the driver to cap the fps to monitor refresh - 2fps. The fps is extremely stable compare to ingame fps limiter, which is in my opinion more crucial to aiming accuracy rather than slightly lower input lag. I have been playing almost exclusively BR games like PUBG and COD Warzone and had done lot of testing to increase my KDR :D (around 2.0 KDR so far).

My point here regarding RTX Voice is that the reduction in performance is related to Tensor Cores sucking available power from the shader cores (~30watt), which capping FPS will instantly solve as your card would not reach its power limit. Undervolting here should work too.
 
Joined
Apr 21, 2008
Messages
5,248 (1.10/day)
Location
IRAQ-Baghdad
System Name MASTER
Processor Core i7 3930k run at 4.4ghz
Motherboard Asus Rampage IV extreme
Cooling Corsair H100i
Memory 4x4G kingston hyperx beast 2400mhz
Video Card(s) 2X EVGA GTX680
Storage 2X Crusial M4 256g raid0, 1TbWD g, 2x500 WD B
Display(s) Samsung 27' 1080P LED 3D monitior 2ms
Case CoolerMaster Chosmos II
Audio Device(s) Creative sound blaster X-FI Titanum champion,Creative speakers 7.1 T7900
Power Supply Corsair 1200i, Logitch G500 Mouse, headset Corsair vengeance 1500
Software Win7 64bit Ultimate
Benchmark Scores 3d mark 2011: testing
so if I use external devices like modi 2 and lyr 2 and blue yeti,, do i get more improvements?
 
Joined
Dec 15, 2009
Messages
226 (0.05/day)
Location
Austria
System Name bazinga 3
Processor i7 6700k @ 4.7GHz
Motherboard Asus Hero IV Alpha
Cooling Some Water AIO
Memory 16GB 3400
Video Card(s) MSi GTX 980Ti G6
Storage 512GB 970 EVO+ , 4TB HDD
Display(s) BenQ XL2420T |BenQ XL2411T
Case Nanoxia Deep Silence 6
Audio Device(s) Hardware Modified Creative SB X-Fi Titanium
Power Supply EVGA 1000G2 with Fan mod
Mouse G502
Keyboard K95
Software Win10 x64
tried this with my 980Ti, the app is useing 13% GPU when aktiv and around 500MB ram :kookoo:
 
Joined
Jun 24, 2011
Messages
93 (0.03/day)
Location
Germany
System Name MonsterPC
Processor AMD Threadripper 3960X
Motherboard Gigabyte TRX40 AORUS Extreme
Cooling IceGem 280
Memory 128GB DDR4 @3200
Video Card(s) AMD RX6900XT
Storage 120TB HDD + 3x 2TB SSD RAID
Display(s) C49RG90
Case BIG Tower
Audio Device(s) Creative X-FI + SteelSeries Arctis Pro USB
Power Supply Corsair AX1200i
Mouse SteelSeries Rival710
Keyboard SteelSeries Apex Pro
Software W10 x64
@Inle
We could use a test on a card without Tensor Cores - i.e. if it's just as effective and how the GPU load looks.
Can you do this? Same procedure, if possible.

Some GPU load has to happen even on RTX cards. Tensor Cores don't run the whole code - just the (large) matrix operations involved.

@Ferrum Master
How is your "hardware could do this long time ago" theory working so far? :D

Even on a very weak Maxwell card the gpu usage is negligible (2-5%), same on a 1030. So Tensor cores are not required, but this is typically NV --- to lock a feature down.
I bet in the next version the installer will be encrypted so there is no possibility to mod it (unlocking it for non-RTX cards)...
 
Joined
Jun 28, 2016
Messages
3,595 (2.02/day)
Even on a very weak Maxwell card the gpu usage is negligible (2-5%), same on a 1030. So Tensor cores are not required, but this is typically NV --- to lock a feature down.
You'd have to check this in relation to how effective it is.
People with non-RTX cards often report artifacts and poor noise cancelling in general. It can be cause either by performance issues or by missing CUDA instructions. Missing CUDA instructions means less load. It makes sense.
E.g.:
- RTX2080 can run the full model, leading to 5% load and very good results,
- GTX1030 can run a simplified model, leading to 3% load (despite being few times slower) and worse results.

You'd need to do controlled testing to evaluate this properly, i.e.: record the background and run the same process on multiple cards.
At the very least, the same person would need to listen to outputs from multiple cards, because the quality assessment is purely empirical. You hear the difference or you don't.
I bet in the next version the installer will be encrypted so there is no possibility to mod it (unlocking it for non-RTX cards)...
It's their software. They can do what they want.
You're welcome to write an alternative that works on any GPU or CPU. Seriously. :)
 
Last edited:
Joined
Nov 3, 2011
Messages
459 (0.13/day)
System Name Fractal Define R5 | Fractal Define R6
Processor AMD Ryzen 9 3900X | Intel Core i7-9900K @ 5 Ghz all cores
Motherboard ASUS ROG Strix X570 Gaming | MSI Z390 Gaming Pro Carbon AC
Cooling CORSAIR Hydro H115i, RGB | CORSAIR Hydro H150i RGB
Memory G.Skill Trident 32GB 3200 Mhz RGB| HyperX 32GB 3600 Mhz RGB
Video Card(s) Gigabyte RTX 2080 Windforce 8G OC| MSI RTX 2080 Ti Gaming X TRIO
Display(s) 3X Samsung 23 in LED | LG 32UL950-W 32in 4K HDR FreeSync
Case Fractal R5 tempered glass | Fractal R6 tempered glass
Audio Device(s) Creative Sound Blaster Z | Creative Sound Blaster AE-7
Power Supply Seasonic 750 watts| Seasonic 1000 watts
Mouse Bloody P95s
Keyboard Logitech G810s
Software MS Windows 10 Pro version 2004
Benchmark Scores Intel Core i7-7820X 4.5 Ghz and ASUS ROG Strix X299-E Gaming parts in storage.

.... :p
 
Joined
Apr 29, 2011
Messages
109 (0.03/day)
In B4 some hacker team find a way to exploit this and capture all your communications :p
 
Joined
Sep 17, 2014
Messages
14,832 (6.11/day)
Location
The Washing Machine
Processor i7 8700k 4.6Ghz @ 1.24V
Motherboard AsRock Fatal1ty K6 Z370
Cooling beQuiet! Dark Rock Pro 3
Memory 16GB Corsair Vengeance LPX 3200/C16
Video Card(s) MSI GTX 1080 Gaming X @ 2100/5500
Storage Samsung 850 EVO 1TB + Samsung 830 256GB + Crucial BX100 250GB + Toshiba 1TB HDD
Display(s) Gigabyte G34QWC (3440x1440)
Case Fractal Design Define C TG
Audio Device(s) Situational :)
Power Supply EVGA G2 750W
Mouse Logitech G502 Protheus Spectrum
Keyboard Lenovo Thinkpad Trackpoint II (Best K/B ever... <3)
Software W10 x64
tried this with my 980Ti, the app is useing 13% GPU when aktiv and around 500MB ram :kookoo:

13%? I saw very low load on my 1080. The gap in perf isn't that large... but perhaps things change once you apply another load to the same GPU - those benches show us something like that I think.

I ran a little test yesterday and saw low loads at 2-3%. But going on the info in the review I tested again. See below.

You'd have to check this in relation to how effective it is.
People with non-RTX cards often report artifacts and poor noise cancelling in general. It can be cause either by performance issues or by missing CUDA instructions. Missing CUDA instructions means less load.

Source? Often? I don't get any of this... You seem to assume a lot on this subject, for reasons unknown.

Here is my 1080. The behaviour is about the exact same as it is on a 2070S in the review. The noise suppression is excellent. GPU load maxed at 7% with this setup. Yesterday I had no app between the input and had lower loads. I suppose this is it actually working now. I see the load vary more depending on noise.

Note how clean that waveform looks too. I had music in background, it was 100% inaudible when listening to recording my voice.

Judging the 3-4% load difference between my 1080 and a (faster) 2070S I'm not quite convinced this does anything over Tensor cores to be honest. And even if it does, the net performance gain is not there compared to a Pascal card at least.

1587626324641.png
 
Joined
Oct 22, 2014
Messages
11,890 (4.96/day)
Location
Sunshine Coast
System Name Black Box
Processor Intel i5-9600KF
Motherboard NZXT N7 Z370 Black
Cooling Cooler Master 240 RGB AIO / Stock
Memory Thermaltake Toughram 16GB 4400MHz DDR4 or Gigabyte 16GB 3600MHz DDR4 or Adata 8GB 2133Mhz DDR4
Video Card(s) Asus Dual 1060 6GB
Storage Kingston A2000 512Gb NVME
Display(s) AOC 24" Freesync 1m.s. 75Hz
Case Corsair 450D High Air Flow.
Audio Device(s) No need.
Power Supply FSP Aurum 650W
Mouse Yes
Keyboard Of course
Software W10 Pro 64 bit
Joined
Jun 24, 2011
Messages
93 (0.03/day)
Location
Germany
System Name MonsterPC
Processor AMD Threadripper 3960X
Motherboard Gigabyte TRX40 AORUS Extreme
Cooling IceGem 280
Memory 128GB DDR4 @3200
Video Card(s) AMD RX6900XT
Storage 120TB HDD + 3x 2TB SSD RAID
Display(s) C49RG90
Case BIG Tower
Audio Device(s) Creative X-FI + SteelSeries Arctis Pro USB
Power Supply Corsair AX1200i
Mouse SteelSeries Rival710
Keyboard SteelSeries Apex Pro
Software W10 x64
You'd have to check this in relation to how effective it is.
People with non-RTX cards often report artifacts and poor noise cancelling in general. It can be cause either by performance issues or by missing CUDA instructions. Missing CUDA instructions means less load. It makes sense.
E.g.:
- RTX2080 can run the full model, leading to 5% load and very good results,
- GTX1030 can run a simplified model, leading to 3% load (despite being few times slower) and worse results.

You'd need to do controlled testing to evaluate this properly, i.e.: record the background and run the same process on multiple cards.
At the very least, the same person would need to listen to outputs from multiple cards, because the quality assessment is purely empirical. You hear the difference or you don't.

It's their software. They can do what they want.
You're welcome to write an alternative that works on any GPU or CPU. Seriously. :)


TL;DR : no difference between RTX and GTX. Just pure marketing bluff.
 
Joined
Feb 11, 2009
Messages
3,289 (0.74/day)
System Name Cyberline
Processor Intel Core i7 2600k
Motherboard Asus P8P67 LE Rev 3.0
Cooling Tuniq Tower 120
Memory Corsair (4x2) 8gb 1600mhz
Video Card(s) AMD RX480
Storage Samsung 750 Evo 250gb SSD + WD 1tb x 2 + WD 2tb
Display(s) Philips 32inch LPF5605H (television)
Case antec 600
Audio Device(s) Focusrite 2i4 (USB)
Power Supply Seasonic 620watt 80+ Platinum
Mouse Elecom EX-G
Keyboard Rapoo V700
Software Windows 10 Pro 64bit
"With RTX Voice (currently in beta), Tensor Cores are finally in charge of something tangible and potentially useful to just about anyone. "

Ermmm no...have we not established a few posts ago that it works on the cuda cores....hence older Nvidia cards can do this at exactly the same level as multiple people have showed already?
 

Septemvri

New Member
Joined
Feb 4, 2020
Messages
1 (0.00/day)
Can't believe a review on TPU talks about performance hit from turning a feature from off to on but gives numbers for the performance gain for turning that feature from on to off. Not cool.
 
Joined
Feb 19, 2009
Messages
1,102 (0.25/day)
Location
I live in Norway
System Name 3 sys spec seperated by "|"
Processor R9 3900x| R7 1700 @3.75 | 4800H
Motherboard Asrock X570M | AB350M Pro 4 | Asus Tuf A15
Cooling Air | Air | duh laptop
Memory 64gb G.skill SniperX @3600 CL16 | 64GB | 32GB
Video Card(s) XFX RX 6800 Speedster |V64\Quadro P4000 | RTX2060M
Storage MP510 2TB, 660P 2TB, 2x860 evo 1tb | 960 500gb Intel 660P 1tb PM871 4x256gb ++| 1TB 660+ 1tb A1000
Display(s) AOC 28" 4K something + 1440p AOC 144hz something.
Case Phanteks EvolvX M-Atx
Power Supply Corsair RM850
Mouse g502 Lightspeed
Keyboard G915
Software win10,unraid,Manjaro
Benchmark Scores 30000FS, 16300 TS. Lappy, 7000 TS.
it just works...
3rd times the charm.

Also, RTX naming and lock in.. gotta sell em rtx cards somehow :)

And yes, it does work amazingly :)
 
Joined
Jun 28, 2016
Messages
3,595 (2.02/day)
TL;DR : no difference between RTX and GTX. Just pure marketing bluff.
That depends how you look at it.
It's just a side project beta right now. We don't know how the final release will work (nor if it's going to happen).

By principle: this software will work on any GPU with a compatible CUDA API.
In other words: no software requires tensor cores to run (at least not in current CUDA implementation).

This stems from the fact that tensor cores aren't activated by some separate methods, but in the math engine setup, which defaults to non-tensor use.
So if you don't set it all (e.g. because you wrote the code before tensor cores existed) - it's non-tensor all the way.
If you asked for them in the code, but there are no tensor cores in the GPU, they're disabled or locked by another process - it'll also use the base CUDA implementation.
The rest of the code is identical.

Tensor cores are just faster in some operations. They don't add functionality.
Whether this is a noticeable gain in RTX Voice is another story.

But that's only true for Tensor cores. Running on RT cores demands completely different game code.

So yeah, Nvidia decided to make RTX card a artificial requirement. Well, it's not something you give Peace Nobel for, but it's their software.
I can write a program that will only work when you're connected to the internet from some chosen countries. I'm entitled to do so.
 

W1zzard

Administrator
Staff member
Joined
May 14, 2004
Messages
22,080 (3.56/day)
Processor Core i7-8700K
Memory 32 GB
Video Card(s) RTX 3080
Display(s) 30" 2560x1600 + 19" 1280x1024
Software Windows 10 64-bit
"With RTX Voice (currently in beta), Tensor Cores are finally in charge of something tangible and potentially useful to just about anyone. "

Ermmm no...have we not established a few posts ago that it works on the cuda cores....hence older Nvidia cards can do this at exactly the same level as multiple people have showed already?
I'll just leave that here for you
 
Joined
Sep 17, 2014
Messages
14,832 (6.11/day)
Location
The Washing Machine
Processor i7 8700k 4.6Ghz @ 1.24V
Motherboard AsRock Fatal1ty K6 Z370
Cooling beQuiet! Dark Rock Pro 3
Memory 16GB Corsair Vengeance LPX 3200/C16
Video Card(s) MSI GTX 1080 Gaming X @ 2100/5500
Storage Samsung 850 EVO 1TB + Samsung 830 256GB + Crucial BX100 250GB + Toshiba 1TB HDD
Display(s) Gigabyte G34QWC (3440x1440)
Case Fractal Design Define C TG
Audio Device(s) Situational :)
Power Supply EVGA G2 750W
Mouse Logitech G502 Protheus Spectrum
Keyboard Lenovo Thinkpad Trackpoint II (Best K/B ever... <3)
Software W10 x64

TL;DR : no difference between RTX and GTX. Just pure marketing bluff.

Well, if you are analyzing an FPS graph I'm sure the tensor processing takes a tiny bit of load away from CUDA... but then again, the review shows us that even running over tensor (as it apparently does) there is a performance hit. So even if it is something... its negligible and it certainly isn't similar to any sort of 'AI' processing that Turing handles better than any arch before it.

At least it just works eh... the marketing works too. Nvidia has a headline, we have a free app, and its actually useful too. Win.

Given all these Tensor core arguments, I wonder how much performance hit it will be using Tensor cores vs turning them off.

See post and test above.. If someone can bench a 1080ti you have a pretty direct comparison to the 2070S with tensor.
 

Fourstaff

Moderator
Staff member
Joined
Nov 29, 2009
Messages
9,719 (2.32/day)
Location
Home
System Name Orange! // ItchyHands
Processor 3570K // 10400F
Motherboard ASRock z77 Extreme4 // TUF Gaming B460M-Plus
Cooling Stock // Stock
Memory 2x4Gb 1600Mhz CL9 Corsair XMS3 // 2x8Gb 3200 Mhz XPG D41
Video Card(s) Sapphire Nitro+ RX 570 // Asus TUF RTX 2070
Storage Samsung 840 250Gb // SX8200 480GB
Display(s) LG 22EA53VQ // Philips 275M QHD
Case NZXT Phantom 410 Black/Orange // Tecware Forge M
Power Supply Corsair CXM500w // CM MWE 600w
Given all these Tensor core arguments, I wonder how much performance hit it will be using Tensor cores vs turning them off.
 
Joined
Feb 11, 2009
Messages
3,289 (0.74/day)
System Name Cyberline
Processor Intel Core i7 2600k
Motherboard Asus P8P67 LE Rev 3.0
Cooling Tuniq Tower 120
Memory Corsair (4x2) 8gb 1600mhz
Video Card(s) AMD RX480
Storage Samsung 750 Evo 250gb SSD + WD 1tb x 2 + WD 2tb
Display(s) Philips 32inch LPF5605H (television)
Case antec 600
Audio Device(s) Focusrite 2i4 (USB)
Power Supply Seasonic 620watt 80+ Platinum
Mouse Elecom EX-G
Keyboard Rapoo V700
Software Windows 10 Pro 64bit
I'll just leave that here for you

Ok so what is this entire article then about?

EDIT: so it does "use" tensor cores...except it does not need to at all.
Bringing me back to my original statement in that article, im waiting for some modders to get this to work on an AMD GPU or just the CPU.
 
Joined
Jun 28, 2016
Messages
3,595 (2.02/day)
EDIT: so it does "use" tensor cores...except it does not need to at all.
Well that's just failed logic. Of course it doesn't need tensor cores.
It doesn't even need a GPU. Frankly, everything can be calculated on a CPU - it'll just take longer.
In fact, everything can be calculated on a piece of paper - it'll just take longer.
Bringing me back to my original statement in that article, im waiting for some modders to get this to work on an AMD GPU or just the CPU.
It's CUDA code underneath. You can't "mod" it. You'll have to rewrite it.
Of course it is possible to write a program giving identical results just on CPUs.
But Nvidia makes GPUs and they made a program that runs on their product, as an additional feature. Are you able to accept this or not?
 
Top