VAPI•6mo ago

Gladia transcriber very slow

I tried the Solaria model from Gladia because it was supposed to be more accurate and have a smaller latency than deepgram.
I did some testing and ended up having an average of 2.42s when using Solaria compared to 1.24s for deepgram nova-2-general (exact same parameters for the rest)

I don't understand the gap??

forward-apricotOP•7/17/25, 2:12 PM

the call id: 2efb66ef-5fc2-4bec-9cb3-c33df46517e7

forward-apricotOP•7/18/25, 12:38 PM

this is what their team said

forward-apricotOP•7/18/25, 12:39 PM

their response to what i said

forward-apricotOP•7/18/25, 12:39 PM

@Kings_big

KyleAPP•7/18/25, 1:02 PM

Looking into it

extreme-purple•7/18/25, 1:15 PM

could you also share:
When exactly this happened (the timestamp)
What response you expected to get
What response you actually got instead
This would really help us figure out what went wrong! @pierreh

forward-apricotOP•7/18/25, 1:58 PM

FYI, this is what they said:

Hi, thanks for reaching out and for testing Gladia!

You're absolutely right to expect lower latency and improved French accuracy with Solaria, that’s what we designed it for. That said, I don’t know the exact implementation details of how Gladia is integrated within Vapi, and from what I could find in their documentation, it’s unclear how they pass parameters like endpointing or custom vocabulary.

This could be part of the latency discrepancy you're observing.

Here are a few suggestions and examples you can try to improve your setup:

Recommended Gladia Parameters

Please make sure you're explicitly setting these parameters in your config (either directly or by asking Vapi support if these are passed through properly):

Endpointing
Lowering this value can drastically reduce perceived latency:

{
"endpointing": 0.05
}

Docs on endpointing

Custom Vocabulary
If your use case includes domain-specific terms, brand names, or unusual phrases, you can use custom vocabulary to improve accuracy:

"realtime_processing": {
"custom_vocabulary": false,
"custom_vocabulary_config": {
"vocabulary": [
"Westeros",
{
"value": "Stark"
}
],
"default_intensity": 0.5
}

Docs on custom vocab

Speech Threshold Tuning (for noisy or degraded calls)
If your calls are 8kHz or have background noise, try:

{
"pre_processing": {
"audio_enhancer": false,
"speech_threshold": 0.6
}
}

Docs on speech threshold

Eextreme-purple could you also share: When exactly this happened (the timestamp) What response y...

forward-apricotOP•7/18/25, 2:00 PM

If you take any assistant, connect the gladia transcriber (solaria) and see the latency, you'll see that it's very high (about 2 sec) where normally it should be lower than for deepgram

forward-apricotOP•7/18/25, 2:00 PM

its for every call i did using solaria

KyleAPP•7/19/25, 6:05 PM

Hey pierreh,

I sincerely apologize for the delay in our responses this week. We experimented with some process adjustments that didn’t work as intended, and unfortunately, this caused some disruptions. That’s entirely my responsibility.

Just a quick note—our team is unavailable on weekends. However, if something urgent or critical comes up, feel free to reach out to me directly, and I’ll assist you.

The support issues will be resolved in the coming weeks, and starting Monday, you can expect more consistent and improved support. Thank you so much for your patience and for continuing to stick with us!

forward-apricotOP•7/20/25, 9:38 AM

Thank you @Shubham Bajaj , have a great WE!

KyleAPP•7/22/25, 4:59 AM

We reached out to our team to have them take a look at our current Gladiia implementation and see what they can do to improve the experience for our users. Thank you for your patience while our team reviews it

forward-apricotOP•7/22/25, 6:26 PM

thanks!

technical-ivory•7/23/25, 2:23 PM

Great ! Adding on this the requested feature of custom vocabulary : https://vapi.canny.io/feature-requests/p/add-custom-vocabulary-feature-to-gladia-transcriber, also essential to proper gladia integration

KyleAPP•7/25/25, 4:42 AM

Our team is currently working on making improvements to our implementation for Gladia. While there is no exact ETA on its release, you will either hear from us when it's deployed or it'll show up in the changelogs for upcoming updates to the platform.

Ccomprehensive-tomato Our team is currently working on making improvements to our implementation for G...

forward-apricotOP•8/10/25, 3:38 PM

any news on that ?

technical-ivory•8/12/25, 2:07 PM

@pierreh I've recently asked during an OH (vapi-stage) and @Shubham Bajaj told me it was planned for last week / this week I believe

I hope to get some news soon !

KyleAPP•8/12/25, 8:42 PM

No update yet, but it is in the works. Thank you for your patience

technical-ivory•8/13/25, 8:59 AM

It seems they are even going one step further in the nearby future, for even lower latency !

technical-ivory•8/13/25, 4:37 PM

Found this in the changelog. Could it be live already ?

KyleAPP•8/14/25, 5:43 AM

It should be live if it was found in our August 3rd changelog. Feel free to check it out

technical-ivory•8/14/25, 11:28 AM

I've done a few tests but all transcriptions are translated in English by Gladia by default (couldn't change that).
Opened a new ticket for this : supportGladia transcriber translates output automatically

forward-apricotOP•8/21/25, 6:54 AM

let me know @Jeebs from eva.be when you here from them! We are getting there

technical-ivory•8/21/25, 7:19 AM

@pierreh it does work

forward-apricotOP•8/21/25, 11:40 AM

what is your first feedbacks on Gladia vs Deepgram @Jeebs from eva.be ? Do you see a difference?

Gladia transcriber very slow

Similar Threads

Similar Threads

Similar Threads