Sam Altman

DeepGram - Search engine for speech

by•

Add a comment

Replies

Best
Rudy Yazdi
Sounds like a good idea :)
Noah Shutty
@rdyazdi Thanks Rudy! What would you use it for?
Imran Ghory
Speech analysis is something I've been looking at recently for a fintech company but from testing the standard API transcription services (those from IBM, AT&T, etc.) the quality hasn't been great. Is exposing raw transcript something you're looking at, even if it's a probabilistic transcript ? - search is one use case but we've also got other use cases for which we'd want raw data (predicting conversion, risk, fraud, etc.)
Scott Stephenson
@imranghory We definitely can expose the transcript (there's a DeepGram API call for that), but the error rate in the transcript is highly dependent on the input audio quality (better quality audio has better transcripts, phone calls in noisy cars don't). However, our analysis techniques don't rely solely on the transcript being perfect, which is a feature that really sets us apart—especially for medium to poor quality audio. On prediction: We've built AI prediction layers to do what you are mentioning (predicting outcomes) but we don't rely on the text in the transcript being perfect, we build it on top of our fuzzy key phrase search. Contact us if you need that sort of thing!
Imran Ghory
@stephensonsco our current dataset is recorded phone calls in mp3 so the greatest, most models that are trained on phone data (i.e. dealing with narrowband) fail on our data due to the lossy compression on mp3. We're looking at switching to uncompressed call recording though. What's the pricing structure for search and the API ?
Noah Shutty
@imranghory @stephensonsco We'd be happy to talk about our pricing and set up a demo for your call audio! Shoot us a quick message at deepgram.com/contact and we'll be in touch.
Jaswinder Brar
Consider these new Use Cases: 1) Associated multiple language sound bytes!.. For people to use in foreign countries as a handheld translator! 2) Voice mail generator. Thanks, Jaswinder Brar.
Noah Shutty
@jay_bee12345 We're also very interested in multiple languages (right now it's only English) As for 2), you should check out mashily.com (our mashup generator) if you want to use the search to make a great voicemail sound clip. Reply with the URL if you make a mashup!
Noah Shutty
Any lifeloggers up in here?
Scott Stephenson
@noajshu You are revealing our secret plot to index the world. :-P
Janardhan
Nice. Searches speech but wont accept speech as input :)
Scott Stephenson
@nj_raju I know right?! This is something we want to add soon. Getting it working on different platforms while not frustrating users is a challenge, though.
Ben Myers
Not sure what's up but no matter what I search, it only plays back Hoover Dam related video. I'm on Chrome 49 Mac OSX
Scott Stephenson
@iamhabitat Hey Ben! Thanks for the feedback. Are you searching on our homepage? That demo is only for searching within that single creative commons video about the Hoover Dam—we don't yet provide search that is akin to Google for Audio/Video (but we certainly work on it). You can search through other files files (YouTube videos, your own recorded memos, things like that) by creating an account and uploading them to the DeepGram console. Let us know if you have more feedback (also, we have a slack channel—https://www.hamsterpad.com/chat/...!)
Chris Strom
I love the concept - eager to use it! I tried to index a YouTube video and got a Failed status. Any ideas why this could happen?
Scott Stephenson
@marketplicity We'll check this out right away. What's the YouTube URL? You can also drop us a line at https://www.deepgram.com/contact with any problems. Thanks for letting us know!
Ouriel Ohayon
that would be killer to use this to built a true search engine for podcasts.
Scott Stephenson
@ourielohayon I totally agree! Which platforms would you want to search on?
Abe Storey
I love this. Freakin' brilliant and seamless.. Can you do product analysis @stephensonsco ?
Scott Stephenson
@abe_storey We might be able to. What kind of product analysis are you looking for?
Abe Storey
@stephensonsco What's your email? I'll dm you more.
Noah Shutty
@abe_storey @stephensonsco Reach out to contact -at- deepgram -dot- com
Noah Shutty
@abe_storey @stephensonsco Or just leave us a note at deepgram.com/contact :)
Abe Storey
@noajshu thanks! I'll be in touch soon.
Kenny
Someone needs to go redesign the site. The search doesn't seem to work. Just keeps playing the same video. I think it skips to parts of the video where the search keyword can be found? No idea. I searched "apple" and nothing happened.
Scott Stephenson
@topcities Sorry that it's annoying. There is only a single video to search through as a demo and 'apple' isn't mentioned in the video. You can upload videos from YouTube or your personal audio/video stash by creating an account and dropping it into the console. Let us know how that goes for you!
Kenny
@stephensonsco The technology is cool. With better messaging on the site I think you'd increase your signup and engagement rates a lot.
Noah Shutty
@topcities @stephensonsco Thanks! Do you have any tips for improving our messaging?
Kenny
@noajshu @stephensonsco Sure. 1. Don't make users sign up before trying it. Let users play with it a bit then ask them to register. 2. The video demo has many usability issues. The search box insinuates a user can search for a video, not text within the video. The pink buttons feel like they let users paginate to the next video search result. Might be better if you just made a video explaining the value proposition right above the fold. 3. I didn't realize there was more stuff below the video, because I got stuck at the video section and left shortly after because I didn't really get it right away. 4. The slogan didn't hook me because I didn't get it right away. I was just scanning so probably that's the reason. Perhaps make it even simpler for the average joe to get it. Something like "Search through speech within videos" might be easier to understand. You can always explain in more detail later after the user is hooked.