Using Google Live Caption for Gotomeeting conference calls

I have a lot of conference calls on both Microsoft Teams and Gotomeeting. I have a Macbook Pro. Most of my conference calls are with folks in India and the Philippines who have strong accents.

For the Teams meetings I call in on my iPhone using Teams (which pipes sound to my Resound Enzos) and then also bring up the Teams meeting on my Mac so I have a larger screen to see the charts. Then, I turn on captions in the Teams meeting. It’s a bit cumbersome but it works and MS live captioning is pretty darn good. I think I can probably avoid the iPhone call-in if I can pipe the desktop audio to the Resound all-mic clip but haven’t tried that yet. (Macbook bluetooth won’t connect directly to Resound hearing aids. Thanks, Apple.)

For the Gotomeeting conference calls I haven’t found any way to get LIVE captions like MS Teams. There are third party services my company would have to pay for and they seem cumbersome. Has anyone solved this problem? Remember, my need is for live captions, not for a transcript after the call.

One idea I had was to junk my iPhone, buy a Pixel, and run Google Caption on the Pixel 4 while dialed in on Gotomeeting (I haven’t seen anything about Google Caption being able to run on a laptop browser). Then I would mirror the phone to my desktop so I could more easily read the captions. I’d have the charts open on the Mac through a desktop Gotomeeting session. Would this work? I know it sounds crazy kludgy but I really like the live captioning I get in Teams and want to replicate it on Gotomeeting.

Any other ideas?

Thanks all for any and all ideas.

Regards, CH

1 Like

@Don has lots of experience with your type questions.
He might be able to give you some ideas.

Thanks! I appreciate the quick response and referral.

I have used Live Transcribe on my Galaxy S10+ to caption Google Duo calls with my parents. You want Live Transcribe by the way, not Live Caption. Live Caption is a Pixel exclusive feature that captions sound on the device. Live Transcribe captures microphone sound and generates captions from it.

My wife was watching NCIS so I booted up LT. It does this in juuuust shy of real time.

1 Like

I find with Live Transcribe (Samsung S7) that the volume needs to be pretty significant. I’ve used it a few times and it was helpful, but for something really important I’d be tempted to us a service that involved a human doing the captioning. I’m not knocking Live Transcribe, I think it’s amazing, but for a phone situation or a room with ambient noise or other issues, a person with excellent hearing is still going to pull out the subtleties better.

1 Like

It sounds like you have the phone calls covered, getting the meeting sounds in both ears, so that’s good.

You mentioned the Resound all-Mic clip. Is that the Phone Clip+ or the multimic? I don’t think there is a way to get your outgoing voice to the meeting with the multimic. I think it is incoming only. So that would leave the Phone Clip+, assuming it works with your model hearing aid.

If you currently use the iPhone for calls/meetings and that is working well, and switch to the Mac only for the screen, you could continue calling in from the iPhone, and not use sound on the Mac.

That is similar to every Webex meeting we do. All our meetings are Webex and I use the laptop for the screen, and a phone call for audio.

1 Like

Absolutely they will. It will always be a compromise for those who need it. Something that bugs me is that our phones have multiple mics but LT clearly doesn’t make use of them because phone orientation matters a lot to how well it works.

This might be more effort than you want, but I’ll offer it as a possibility on your computer.

At my church, we use a captioning system called Web Captioner ( It is designed to do speech to text talking into the microphone.

We had a similar need come up, where we wanted other audio coming into the computer to be fed to the Web Captioner as if it were being spoken into the speaker.

To do this (and a few other needed functions), we used a software sound mixing program called VoiceMeeter Potato (weird name, but I don’t care as long as it works). This can be found at VB-Audio VoiceMeeter Potato

This takes multiple sound inputs to the computer, and sends them out to multiple outputs (include the Chrome browser which is used for the previously mentioned Web Captioner).

Though a bit of a challenge to set up, this should do what you’re looking for.

Thanks for your replies, all.

I think I made my initial question way too complicated.

All I really want is to have “live captioning” display what is being said by all participants when I’m in a business conference call (using Gotomeeting software) on my Mac. Currently, I can submit a conference call for non-live captioning after the meeting is over, but I want live captioning. If you think about how Youtube can generate live captioning, that’s what I want but for a business conference call.

I do understand that Live Transcribe has its own great uses but I’m not physically in the conference room in order to capture the speech.

Do you all think that if I bought a Pixel phone, the live captioning service on the Pixel would work against the Android version of the Gotomeeting app? I realize that’s not the same as having the live captioning work on my Mac which has the bigger screen, but at least it would provide (I think) live captioning.

If you have speakers, Live Transcribe will work. I don’t know if Pixel Live Caption supports any random Android app. They probably have a support page someplace within the Pixel websites.

Right, I guess that’s the key point – will Pixel Live Caption transcribe audio on all apps where speech is detected (not just phone conversations). I thought about using speakers but would prefer a “silent” solution. But I’ll give it a try.

MS Teams has a business conference call function that has built-in live captioning on both devices and desktops. It’s not perfect but much better than expected. So, I think the speech recognition engines are available to be used on the desktop, but people just haven’t integrated them yet – except for big money money software like YouTube.

No. I read their website. It says it only captions video and audio media and specifically does not support video or audio calls. Basically you’ll get captions in Instagram and Facebook… Honestly i wonder what the point is.

Yeah, that’s just what I need. Listening to people narrate what they had for dinner on social media :slight_smile:

Interestingly, Microsoft seems to get it – probably because they’re more enterprise focused than Google. I know MS Teams has live captioning for conference calls and I think Skype does as well.

It would actually be a solid move by Google to make their live captioning technology available via API to video chat vendors. It would be one more way to make Google indispensable in folks’ daily lives.

Thanks for your help.

Hi, I think Google Hangouts (that is the alternative to Teams/skype provided by Google) allows automatic captions (Use captions in a video meeting - Computer - Meet Help).

On the other hand, being able to caption any video call or audio call from the computer, regardless the native option of captioning provided, would be great. I’ve tried splitting the audio output of my computer, and connecting it to my smartphone, and with Ava app I was able to caption, but without very high accuracy. I was wondering if somebody has tried Live Transcribe but using a cable connected to the computer, instead of using the smartphone microphone (to improve accuracy). I don’t have an Android phone to check, but if works, I would try to get one for this purpose.

Thank you!