Видео

To ashmed to use Muhammed lol good podcast tho

Good one Mo!

Thanks for the feature! We had a great time with it :)

I really enjoyed my time on the podcast, thanks for having us Demetrios and Deepgram!

Go mo go!!

All the best pallavi

I went through the video and its a Great product. ""Hats off" to you Pallavi. Wishing you all the Success. With Regards, Thirumoorthy P, DoodleMango

Great !

Wow, as always, if you know how to do it then things often are so simple! I tried your code example in my react app and it works! Thanks a lot!

Haha nice joke😐

Hi, do you have such coding written in Arduino to implement on ESP32 microcontroller? Been googling for Deepgram speech-to-text live transcription, but couldn't find anything useful.

Thanks for having me! Had a great time on the pod!

Just tried the demo as well, and it is indeed impressing. It does work! The changes in camera angle in this video are a bit unfortunate I would say, but what you see is the exact response time: it's fast! Sometimes faster than any random person.

I guess there still an issue showing on the AI respond transcript,

Incredible. We are implementing this into our retailer solution. Approve us on the waiting list please ☺🙏

integrating this ASAP into our AI phone receptionists...👏

Cool, but why does the transcription get displayed for only 2-3 of the AI's responses as opposed to all of them?

You DO know we can see all the cuts in the video, right? this doesn't look real-time , one-go , real-world situation at all..

Just tried out the demo. I am seriously impressed.

Very impressive phone prices! Also, the AI good.

It does not work :(

can you interrupt it?

I am excited to try out this API! I am currently building a tool that uses Deepgram for live transcription and then OpenAI for responses and real-time and interjecting responses, but it’ll be nice to see what kind of control and performance I can get from doing it all through Deepgram.

Great job 👏

Hi, it doesn't work for me it says outdated or something after I try to run the second command. Is there an update version of the google collab somewhere? Thanks

very nice. this still working?

watch this at 0.01 Speed

"Don't do any outbound sales at all" is a wonderful era to be in as a sales guy.

Loved it!

Isso é simplesmente uma obra-prima! 🏆

Price ? is it included in voice pricing or it has seperate Audio Intelligence pricing ?

How will the asymmetry between languages in training data affect AI and its business uses in the 5-10 year time scale?

Best AI show I've seen to date. The STT as a information discarder is a great observation.

Amazing, nicely presented and hosted.

So good. Do you hire worldwide?

Hey can this Transcrib Chinese Audio?

haiku be like: haiku write haiku write haiku write more haiku and then they all die

Dear Deepgram team, I'm Felix, a developer working with Next.js. Our team is building an application that requires real-time voice transcription. While I've managed to integrate your Nova-2 API locally, I'm having problems deploying it on Vercel. The API key works locally but not in production. I should also point out that I'm using a free account at the moment. Could you help me solve this problem? Thanks for your help! Best regards, Felix N'TOUGAN

Rgdbehs

I want my chstgpt to flirt

No

Solid interview guys!

Great job on the interview Ross!

superb, thanks

Bruuutal Mog 💀

So if I want to translate say a Japanese video into English and it is 2 Hours long it costs me ZERO dollars.. How much is Deepgram again?

instead of using url can we use and direct audio file in my system ?