TubeSum ← Transcribe a video

How to Talk Like Zentreya Using Voice-to-Text-to-Speech

0h 06m video Published Jan 26, 2022 Transcribed Jul 31, 2026 V VtuberSenpai
Intermediate 5 min read For: Vtubers and streamers who want to use text-to-speech voice effects without paid software, with basic Windows and streaming app knowledge.
AI Trust Score 76/100
⚠️ Average / Some Fluff

"Delivers exactly on its promise: a free, working voice-to-text-to-speech setup, though the brief intro/outro add minor padding."

AI Summary

This tutorial demonstrates how to speak with a generated text-to-speech voice on stream, modeled after VTuber Zentreya, using only free tools. The creator walks through WebCaptioner for speech-to-text-to-speech, Virtual Audio Cable for audio routing, and configuration in 3tene, VCFace, and OBS.

[00:02]
Why this method exists

Zentreya inspired many VTubers to use a generated voice rather than their own. The creator searched for a free solution and found one through a Twitter post.

[00:17]
Free speech-to-text-to-speech tool

WebCaptioner.com is presented as the free website that transcribes speech and reads it back in a synthetic voice. A link is provided in the description.

[00:45]
WebCaptioner setup steps

Access 'Start Captioning', open settings, enable 'Speak everything back' as an experiment, and allow microphone access.

[01:54]
Accuracy and voice limitations

The software isn't always 100% accurate and currently only supports a female voice, but practice improves recognition.

[02:08]
Virtual Audio Cable installation

Download and install Virtual Audio Cable, then restart the PC so the virtual audio driver is registered.

[03:31]
Windows audio loopback

In Sound Control Panel, enable 'Listen to this device' on the CABLE Input and route Chrome's output to the virtual cable.

[04:25]
3tene lip-sync configuration

Inside 3tene, set the lip-sync voice input to CABLE Output, save, restart, and enable tracking for the avatar.

[05:20]
VCFace configuration

Enable Audio Lip Sync and Hybrid Lip Sync, and change the microphone input to CABLE Output.

[05:47]
OBS audio routing

In OBS, change the microphone/audio source to Cable Output so only the generated voice is captured, not the real mic.

[06:15]
App-specific lip-sync tuning

Different VTube applications track audio lip sync differently, so users should test which app works best.

With WebCaptioner and Virtual Audio Cable, any VTuber can start using a text-to-speech voice for free. The key is routing audio correctly and testing lip-sync settings in your preferred VTube application.

Mentioned in this Video

Tutorial Checklist

1 00:45 Open WebCaptioner.com in Google Chrome and click 'Start Captioning'.
2 00:58 Click the settings icon, enable 'Speak everything back', click Add, check all three boxes, and click 'Add Experiment'.
3 01:26 Start captioning, allow microphone access, and speak clearly so the software transcribes accurately.
4 02:22 Download and install Virtual Audio Cable for your operating system.
5 02:49 Restart your PC and open Sound Control Panel to confirm the CABLE Input device appears.
6 03:04 Open Chrome with WebCaptioner, then open 'App volume and device preferences'.
7 03:31 In the Recording tab, open CABLE Input > Properties > Listen, check 'Listen to this device', Apply, OK.
8 03:43 In App volume and device preferences, change Google Chrome's output device to CABLE Input.
9 04:25 In 3tene: go to Settings, set Lip Sync Voice Input to CABLE Output, save, and restart the app.
10 04:52 In 3tene, enable toggle tracking and reset the avatar position, then test by speaking.
11 05:20 In VCFace: enable Audio Lip Sync and Hybrid Lip Sync, set Microphone to CABLE Output, and re-enable tracking.
12 05:47 In OBS: open Settings > Audio and set Microphone/Auxiliary Audio to Cable Output so the real mic isn't recorded.

Study Flashcards (11)

What is WebCaptioner?

easy Click to reveal answer

A free Chrome-only web service that transcribes your speech and speaks it back with a generated voice.

00:17

What must be enabled in WebCaptioner settings to make it speak back?

easy Click to reveal answer

The 'Speak everything back' experiment.

00:58

Which virtual audio driver is used to route WebCaptioner's output?

easy Click to reveal answer

Virtual Audio Cable.

02:08

What should you do after installing Virtual Audio Cable?

easy Click to reveal answer

Restart your computer.

02:49

In the Recording tab, what option routes the audio back to the speakers?

medium Click to reveal answer

Checking 'Listen to this device' on the CABLE Input properties.

03:31

Which device should Chrome output to in App volume settings?

medium Click to reveal answer

Virtual Audio Cable (CABLE Input).

03:43

In 3tene, where do you set the lip-sync voice input?

medium Click to reveal answer

Settings > Lip Sync Voice Input > CABLE Output.

04:38

What two settings must be enabled in VCFace for lip sync?

easy Click to reveal answer

Audio Lip Sync and Hybrid Lip Sync.

05:20

In OBS, what should the microphone be set to?

medium Click to reveal answer

Cable Output, to avoid recording the real mic.

05:47

What voice does WebCaptioner support at the time of the video?

easy Click to reveal answer

Only a female voice.

02:08

Why might lip sync be imperfect?

medium Click to reveal answer

The software isn't always 100% accurate and different VTube apps track lip sync differently.

01:54

💡 Key Takeaways

💡

Free voice-changer alternative

A free web tool can replicate Zentreya's text-to-speech style without expensive software.

00:17
🔧

Virtual Audio Cable is the key

Installing Virtual Audio Cable lets you route the synthesized voice into VTube apps.

02:08
🔧

Loopback trick

Enabling 'Listen to this device' creates the audio loopback needed for the generated voice to be picked up.

03:31
💡

Lip-sync settings vary by app

Different VTube apps have different audio lip-sync accuracy, so users should experiment.

05:20
⚖️

Practice improves accuracy

Consistent practice helps the speech recognizer understand your voice better over time.

01:54

[00:02] has shown and inspired so many new v tubers and older v tubers alike that they don't have to use their own voice to make b-tubing content and for the past few weeks i have scoured high and low across the internet trying to find a

[00:17] free way to do this and i happen to come across a twitter post showing a piece of software that might be the answer hello everyone i'm your v tuber senpai and today i'm going to show you on how to use speech to text to speech just like

[00:33] zentreya the method we will be using today will be through a website and the website will be linked in the description bar down below the website we'll be using today is webcaptioner.com

[00:45] webcaptioner.com this is a google chrome only website so make sure you are using google chrome now what we're going to do is head to start captioning right here we're going to have a black

[00:58] screen what we're going to do is go down to the bottom right hand side we are going to go to the settings at the settings we're going to click on then we're going to click on speak everything back and we're going to click

[01:12] on add then we're going to check all three of these boxes and click on add experiment we are going to then click on the x and then we are going to click on start captioning it will pop up somewhere in

[01:26] the middle right here that says it wants to have access to your microphone just click allow and then once you do that you're going to click this you want to make sure you are speaking very loud and clear so when the software transcribes

[01:39] what you're saying it does actually record it properly and speaks it back to you correctly you want to make sure you are speaking transcribes what you're saying it does actually record it properly and speaks

[01:54] it back to you correct the software itself is not always 100 accurate but with a lot of practice and time you'll learn on how it will pick you up and understand you right now the time of this video being made this

[02:08] website only supports a female voice but they do say that they will support other voices down the road the next thing we need to do is download the program called virtual audio cable so here at google what we're going to do is just

[02:22] type in virtual audio we're going to scroll down as we see we've seen the site before we're going to click that button right there and we're going to download it

[02:35] for our respective operating system in this case once you're done doing that you're going to extract the file and install it once you're done installing the software please make sure you restart your

[02:49] now what we're going to do is the bottom left search bar we are going to type in this window will now up here we're going to scroll down a little bit we're going to click on sound control panel we're going to scroll and we're going to

[03:04] see that audio input by virtual audio cable is installed that's perfect now what we want to do is open our google what we want to do is open our google chrome make sure web captioner is open

[03:16] we are also going to just close that a little bit and we are going to go click on app volume in device preferences before we play too much in the app volume and devices preferences menu we will click

[03:31] on the recording tab under sound we're going to scroll down a little bit we are going to right click we're going to hit properties we're going to click on listen and we're going to click on listen to this device

[03:43] we're going to click apply and we are going to click ok and now what we want to do is scroll down just a little bit until we see google chrome under default what we want to do is change the cable input to virtual

[03:57] audio cable then what we can now do is test and make sure virtual output actually detects the web captioner so let's do a test right now web captioner should be

[04:12] right now web captioner should be captured by audio cable right now web captioner should be captured by audio cable perfect now what we're going to do is open up two v tubing applications for an example first

[04:25] tubing applications for an example first example will be 310a with 310a open what we need to do is go to the make avatar adjustments then we're going to click on settings under settings we're going to change lip

[04:38] sync voice input to cable output we're going to click on save settings and we are going to restart the application with the application restarted what we're going to do is we're going to click on toggle tracking we're going to

[04:52] start everything up and we are just going to make sure we reset our avatar's position just like so captioning hello

[05:06] hello and as you see my mouth moves as i speak [Music] and as you see my mouth moves as i speak perfect now let's go into vc face for some setup let's click on the settings

[05:20] general settings let's make sure audio lip sync is turned let's make sure audio lip sync is turned on and hybrid lip sync is turned on as little bit and we are going to make sure the microphone is changed to

[05:34] cable output audio virtual cable we're going to close that and then we're going to enable this again hello how are you hello how are you

[05:47] perfect and in obs we're going to have to change a particular setting as well in obs what we're gonna do is have to hit settings we are gonna go to audio and then microphone we're gonna change it from

[06:02] microphone we're gonna change it from default or disabled to cable out by doing this we are ensuring that obs is not recording anything like your real microphone and just the virtual audio cable now there are v-tubing

[06:15] applications that track audio lip sync better than others so you will have to play around and fiddle with it to see which one will work better for you but just like that you're all done and ready to go if you found today's tutorial

[06:30] useful make sure you like comment and subscribe it really does help out the video and the channel i also stream here on youtube every monday wednesday and friday so come on by say hi let's talk about anime gaming v tubing whatever and

[06:46] i'll catch in the next one bye

More from VtuberSenpai

View all

⚡ Saved you 0h 06m reading this? Transcribe any YouTube video for free — no signup needed.