Speech to text usage - worth it?

CosmicOutpost wrote on 10/6/2024, 3:08 PM

Hi Folks,

I'm really interested in upgrading to Vegas 22 for the Speech to Text function so I can do Descript style editing where you edit a text transcription of the video like a text document and this makes edit on the timeline. Descript is ok with 60 mins free a month but ideally I'd want to keep the post production in one place so this feature of Vegas22 seems useful and happy to get top up credit when I need.

I'd like to know if others are using this feature in their productions and if an edit made this way will cut up and down the layers on a ripple edit. I've seen that the edit made via text editing needs to be closed up manually which will be a pain if I have to take out a load of "errs2 and "Umms" so is there a way round it like the Resolve feature of 'close up gaps'.

Would be interested in people's experiences.

Thanks!

Comments

RogerS wrote on 10/6/2024, 10:51 PM

Yes, VEGAS lets you use autoripple with the text-based editing feature and VEGAS also has a close gaps feature (edit / close gaps).

Last changed by RogerS on 10/6/2024, 10:52 PM, changed a total of 1 times.

Custom PC (2022) Intel i5-13600K with UHD 770 iGPU with latest driver, MSI z690 Tomahawk motherboard, 64GB Corsair DDR5 5200 ram, NVIDIA 2080 Super (8GB) with latest studio driver, 2TB Hynix P41 SSD and 2TB Samsung 980 Pro cache drive, Windows 11 Pro 64 bit https://pcpartpicker.com/b/rZ9NnQ

ASUS Zenbook Pro 14 Intel i9-13900H with Intel graphics iGPU with latest ASUS driver, NVIDIA 4060 (8GB) with latest studio driver, 48GB system ram, Windows 11 Home, 1TB Samsung SSD.

VEGAS Pro 21.208
VEGAS Pro 22.239

Try the
VEGAS 4K "sample project" benchmark (works with VP 16+): https://forms.gle/ypyrrbUghEiaf2aC7
VEGAS Pro 20 "Ad" benchmark (works with VP 20+): https://forms.gle/eErJTR87K2bbJc4Q7

mark-y wrote on 10/10/2024, 2:40 PM

Batch Whisper AI puts all the text on your timeline in sync as separate, small text events, which can be edited, moved, and deleted. It's free from one of our members, get it here --

https://tools4vegas.com/batch-whisperai-speech-to-text/

planetdelirium wrote on 10/10/2024, 3:06 PM

Is there a way to get more than 2 lines of text for each 'event' in Speech to Text?

Reyfox wrote on 10/10/2024, 3:32 PM

Did you try the software or read the description in the link?

Last changed by Reyfox on 10/10/2024, 3:35 PM, changed a total of 1 times.

Newbie😁

Vegas Pro 22 (VP18-21 also installed)

Win 11 Pro always updated

AMD Ryzen 9 5950X 16 cores / 32 threads

32GB DDR4 3200

Sapphire RX6700XT 12GB Driver: 25.3.2

Gigabyte X570 Elite Motherboard

Panasonic G9, G7, FZ300

ngjb wrote on 10/11/2024, 12:33 PM

I think text to speech is worth it.

Desktop system:


OMEN 30L GT13-1094
Operating system: Windows 10 Home
Processor: AMD Ryzen™ 7 5800X Processor
Memory: HyperX® 32GB DDR4-3200 XMP RGB SDRAM memory(97) (4x8 GB)
Internal Storage: 1 TB PCIe® NVMe™ M.2 SSD (Application storage, Windows OS)

1 TB NVMe M.2 SSD (working drive)
500GB SDD (working drive)
4 TB HDD (Media Storage)
Graphics: EVGA NVIDIA® GeForce RTX™ 3060 XC graphics card with 12 GB GDDR6 dedicated memory
Display:
Samsung U28E590, Displayport,
UHD Monitor 3820x 2160


Laptop:


Acer Nitro 5 Gamer Laptop
Windows 10 (64 Bit)
System Memory 32 GB
500 GB SSD

500 GB SSD (working drive)
1TB HDD

FHD Display
CPU Intel I-5 9300H
Graphics NVIDA GTX 1050

CosmicOutpost wrote on 10/17/2024, 4:20 PM

So got the trial version of Vegas22 but there is no credit included in the trial to try the speech to text function! After finding out the multicam audio sync doesn't sync audio well I might just stick with version 19. 🙁

Reyfox wrote on 10/17/2024, 4:24 PM

Well, if Vegas has to pay for that option, I would not think it would be included in a trial version.

Newbie😁

Vegas Pro 22 (VP18-21 also installed)

Win 11 Pro always updated

AMD Ryzen 9 5950X 16 cores / 32 threads

32GB DDR4 3200

Sapphire RX6700XT 12GB Driver: 25.3.2

Gigabyte X570 Elite Motherboard

Panasonic G9, G7, FZ300

Candive wrote on 10/18/2024, 6:48 PM

@CosmicOutpost

So got the trial version of Vegas22 but there is no credit included in the trial to try the speech to text function! After finding out the multicam audio sync doesn't sync audio well I might just stick with version 19. 🙁

Just curious, are you saying that multicam audio synch doesn't synch well in your trial version of 22 vs Version 19 or is this a general statement regarding the software?

CosmicOutpost wrote on 10/19/2024, 2:46 AM

@Candive I tested the audio sync on V22 with 6 tracks of audio from a zoom call with five guests so the master stereo track should have been able to guide Vegas to line up the other individual track but didn't even come close! If you search Audio Sync in this forum you'll see other have problems too. No a big deal as DaVinci Resolve can't sync audio either. I really miss Pluraeyes and the Original HitfilmPro!

RogerS wrote on 10/19/2024, 2:54 AM

I still use Pluraleyes 4 in VEGAS and it works well.

Candive wrote on 10/19/2024, 3:19 AM

@CosmicOutpost

Thanks for confirming that your audio synch test involved V22. I personally haven't had to synch 6 tracks with my editing. You mentioned you currently use V19. Since you indicated that you miss Pluraeyes and HitfilmPro can I assume V19 suffers from the same synching issue?

CosmicOutpost wrote on 10/19/2024, 4:04 AM

@Candive V19 doesn't have Audio Sync abilities that I've found.

Candive wrote on 10/20/2024, 3:28 AM

@CosmicOutpost

In V19 if you go to Tools/Multicam/Synchronize Audio to Align Events; this is the function. I previously didn't have the need to synch audio but I decided to test this feature. Unfortunately, I was not able to get it to work. And as you suggested there may still be issues. But the good news is, the developers are working on a solution according to @Wolfgang S.

https://www.vegascreativesoftware.info/us/forum/need-help-in-multi-camera-sync-by-audio--146789/​​​​​​

 

Wolfgang S. wrote on 10/20/2024, 4:27 AM

It is not my statement:

https://www.vegascreativesoftware.info/us/forum/vegas-pro-22-build-122-general-discussion--147185/#ca925287

Desktop: PC AMD 3960X, 24x3,8 Mhz * RTX 3080 Ti (12 GB)* Blackmagic Extreme 4K 12G * QNAP Max8 10 Gb Lan * Resolve Studio 18 * Edius X* Blackmagic Pocket 6K/6K Pro, EVA1, FS7

Laptop: ProArt Studiobook 16 OLED * internal HDR preview * i9 12900H with i-GPU Iris XE * 32 GB Ram) * Geforce RTX 3070 TI 8GB * internal HDR preview on the laptop monitor * Blackmagic Ultrastudio 4K mini

HDR monitor: ProArt Monitor PA32 UCG-K 1600 nits, Atomos Sumo

Others: Edius NX (Canopus NX)-card in an old XP-System. Edius 4.6 and other systems

bitman wrote on 10/20/2024, 4:47 AM

I must confess I have not yet felt the need or used Vegas speech to text (although I have written a script to use Whisper AI in the past for speech to text - you can find this if you search this forum). So I cannot really comment on this.

The simple reason is that my filming source material is usually travel, landscape, plants, birds, so in general nature centric. And apart from parrots, not many animals or can speak...

APPS: VIDEO: VP 365 suite (VP 22 build 194) VP 21 build 315, VP 365 20, VP 19 post (latest build -651), (uninstalled VP 12,13,14,15,16 Suite,17, VP18 post), Vegasaur, a lot of NEWBLUE plugins, Mercalli 6.0, Respeedr, Vasco Da Gamma 17 HDpro XXL, Boris Continuum 2025, Davinci Resolve Studio 18, SOUND: RX 10 advanced Audio Editor, Sound Forge Pro 18, Spectral Layers Pro 10, Audacity, FOTO: Zoner studio X, DXO photolab (8), Luminar, Topaz...

  • OS: Windows 11 Pro 64, version 24H2 (since October 2024)
  • CPU: i9-13900K (upgraded my former CPU i9-12900K),
  • Air Cooler: Noctua NH-D15 G2 HBC (September 2024 upgrade from Noctua NH-D15s)
  • RAM: DDR5 Corsair 64GB (5600-40 Vengeance)
  • Graphics card: ASUS GeForce RTX 3090 TUF OC GAMING (24GB) 
  • Monitor: LG 38 inch ultra-wide (21x9) - Resolution: 3840x1600
  • C-drive: Corsair MP600 PRO XT NVMe SSD 4TB (PCIe Gen. 4)
  • Video drives: Samsung NVMe SSD 2TB (980 pro and 970 EVO plus) each 2TB
  • Mass Data storage & Backup: WD gold 6TB + WD Yellow 4TB
  • MOBO: Gigabyte Z690 AORUS MASTER
  • PSU: Corsair HX1500i, Case: Fractal Design Define 7 (PCGH edition)
  • Misc.: Logitech G915, Evoluent Vertical Mouse, shuttlePROv2

 

 

Dexcon wrote on 10/20/2024, 4:56 AM

And apart from parrots, not many animals can speak...

😀😁😂

Cameras: Sony FDR-AX100E; GoPro Hero 11 Black Creator Edition

Installed: Vegas Pro 15, 16, 17, 18, 19, 20, 21 & 22, HitFilm Pro 2021.3, DaVinci Resolve Studio 19.0.3, BCC 2025, Mocha Pro 2025.0, NBFX TotalFX 7, Neat NR, DVD Architect 6.0, MAGIX Travel Maps, Sound Forge Pro 16, SpectraLayers Pro 11, iZotope RX11 Advanced and many other iZ plugins, Vegasaur 4.0

Windows 11

Dell Alienware Aurora 11:

10th Gen Intel i9 10900KF - 10 cores (20 threads) - 3.7 to 5.3 GHz

NVIDIA GeForce RTX 2080 SUPER 8GB GDDR6 - liquid cooled

64GB RAM - Dual Channel HyperX FURY DDR4 XMP at 3200MHz

C drive: 2TB Samsung 990 PCIe 4.0 NVMe M.2 PCIe SSD

D: drive: 4TB Samsung 870 SATA SSD (used for media for editing current projects)

E: drive: 2TB Samsung 870 SATA SSD

F: drive: 6TB WD 7200 rpm Black HDD 3.5"

Dell Ultrasharp 32" 4K Color Calibrated Monitor

 

LAPTOP:

Dell Inspiron 5310 EVO 13.3"

i5-11320H CPU

C Drive: 1TB Corsair Gen4 NVMe M.2 2230 SSD (upgraded from the original 500 GB SSD)

Monitor is 2560 x 1600 @ 60 Hz