If you're participating in the Deepgram Hackathon on DEV, we’re so excited to have you joining us! Need some help with your submission or participation? You’re in the right spot.
If you have any questions about how this contest works (ex: due dates, how to post your submission, picking a category/challenge, etc.) the DEV team is here to help you.
How to Use This Thread
If you’ve browsed Deepgram’s documentation but need some help understanding or implementing a feature, @bekahhw from the Deepgram team will be here to jump in and assist you. This thread is a great resource for you whether you’re taking part in the “Build” or “Innovative Ideas” challenge.
Comment below if you need asynchronous assistance with the Deepgram Hackathon on DEV ❤️
Note: Don’t forget that we’re granting a special profile badge to anyone (outside of the DEV and Deepgram teams) who answers a question and to anyone who ASKS a technical question about Deepgram here in the help thread. Additionally, the DEV team will be randomly selecting one person per badge category to receive $50 USD to the Forem Shop! This goes for anyone in the DEV Community – whether you plan to submit an entry or not. For more information, take a look at the official contest rules here. DEV and Deepgram will wait to answer thread questions until we’ve given the community a chance to hop in.
Open Office Hours with Deepgram Devs
Deepgram will also be hosting open “office hours” on their Twitch Stream every Friday at 6:30 PM UTC throughout the contest (March 11, 18, & 25. April 1 & 8). During these streams, Deepgram will be addressing some of the questions asked in this thread and in the live Twitch chat. If they choose a question you posted to the help thread to talk about on the live stream, you'll be entered to win some Deepgram Swag!
If you'd like to share an update on the progress you're making on your project or if you'd like to connect with other participants, please do so in the Community Discussion Thread!
Oldest comments (118)
How do you guys at Deepgram deal with the data provided by users? Is there any document describing it?
What do you mean by 'deal'? Just making sure we can answer your question correctly :)
I'd be curious to know where to look for any data retention policies concerning those of accidental streaming transcriptions when someone forgot to turn off their mic.
I want to understand if you guys store this kind of information that is given by your users (input audio). If it's stored, how you manage to keep it safe from public access. And if, for some reason, this data leak, what you guys will do, for example, alert people contacting through e-mail.
There is information about the data collection in the Terms of Service Agreement, the Privacy Notice, and Data Privacy Policy.
From what I can tell, uploaded data is collected and stored, measures are in place to protect the data, and customers will receive an email or message about any security notices.
Note: I am not a member of the Deepgram team, so any clarifications should be directed towards them.
Got it, thanks for the answer.
Please read through the Terms of Services and the Privacy Policy on questions related to data retention. In short, Deepgram stores and processes a small percentage of the data for the purposes of improving services and/debugging debugging client requests. If you have further inquiries, including one-off requests for data deletion, please reach out to the Deepgram customer success team at support@deepgram.com.
In the case of a breach, end users will be notified within 72 hours of breach confirmation.
Can we have multiple submission for this hackathon?
The post says yes and even encourages multiple submissions, so yes i guess
Yes! We'd love to see you get as many chances as possible to win!
I want to participate, but, the post says that it's
Open only to 18+.So, does that mean I'm not eligible ? :(
I don't think it means that you aren't eligible for badges for helping. So if you contribute in the Help and Community threads, I think that means you can still earn badges.
i have a couple ideas, if i just write a post with he ideas, would I be eligible? (I could even execute them)
The post seems to imply that all parts of the Hackathon are 18+ to participate. It is likely there for legal reasons, and I would think that if you should be able to participate if your parents approve.
Hello! Unfortunately, DEV hackathons are currently only open to community members 18 years of age and older. We would absolutely love to open this up to younger community members, but we are legally unable to at this time. We revisit the topic frequently as a team and intend to open up our challenges to younger folks if and when it's possible for us to do so. I'm so sorry to bear this news. We really value having all of you as part of DEV.
It's normal for contests to be 18+ due to prizes and legal ruling.
You can ask the dev people if it's OK if you submit but are not considered as a potential winner.
Yeah, I've already submitted my project. It's completely fine if I don't win, or win and not get prizes. atleast I got to learn stuff, that's all that matters
That's a great attitude @dhravya! I'm REALLY looking forward to checking out your submission.
Hi there! Thanks a lot!
Here's the post dev.to/dhravya/deepsubtitles-gener...
Well that was fast, great job 👌👌
thanks a lot!
Having a little bit of a hard time figuring out the final part of the
listenendpoint.1) In a local environment, how would I go about sending the empty binary message to the server?
2) Upon ending, where is the final transcript JSON now?
Thank you.
Great question. It depends on how you're hitting the API. If you are using the Node SDK you'd use the
finishfunction, as in:If you're communicating with the WebSocket directly with JavaScript you can send a new Uint8Array, as in:
When the Deepgram API receives that it will finish transcribing the audio, send a final transcript, and then close the WebSocket connection.
Appreciate the response.
What about good old Python please?
P.S. Great Twitch btw, really enjoyed it.
Thanks!
For the Python SDK:
Against the WebSocket without the SDK would be something like:
Thanks for coming to the stream today!
IIRC from previous hackathons, you're allowed to have multiple submissions. Is that still true? And if so, does that apply to a mix of code and "Innovative Ideas" submissions?
Absolutely! We're stoked to see all the cool submissions. And we actually talked about finding ways to optimize your submissions for multiple categories on our Twitch kickoff stream today|!
I have one interesting question here,
i just started exploring deepgram, i wonder how deepgram is different than other STT Python libraries out there ? as there are so many opensource python libraries are available for example github.com/mozilla/DeepSpeech !
Hi @leo1612d! Thank you for your question. I'm not as familiar with DeepSpeech, the mozilla library you posted so I can only speak to Deepgram.
At Deepgram our mission is we believe every voice should be heard and understood.
A major advantage Deepgram has over other STT libraries is that we're the only provider that uses End-to-End Deep Learning. This means that you'll get improved accuracy with training, an easier to use and integrated API and is priced to use at scale.
@michaeljolley
I'm trying to send real-time audio to deebgram and get the transcription but I get this error while doing so.
I'm using pyaudio to send the binary data.
input_audio = stream_in.read(3200)
await ws.send(input_audio)
DEBUG:websockets.client:< CLOSE 1008 (policy violation) DATA-0000 [11 bytes]
Hi @sandy_codes_py, I'm not a Python pro, but I can hook you up with @tonyasims. She's an amazing pythonista and one of Deepgram's Developer Advocates.
One thing that might help, is there a GitHub repo where we can review the full block of code?
Please check here
I've used api reference code from the deepgram docs
Sweet. Thanks for that. Tonya is out of the office today, but she'll likely respond Monday.
Mental note: I should really start playing with Python more so I can help more. 🙂
That would do!
I did find a workaround it by using her post "Live Transcription With Python and Flask" but that's not really needed here.
I just want to run it locally to do something cool.
Yay, even I've to learn about async and how it works.
Great! I think she wrote several posts like that: "using Flask," "using Django," "using FastAPI," and more.
And yeah! for learning! 🎉🎉
Hi @sandy_codes_py ! Happy Monday! I'm sorry to hear you were having some trouble. Were you able to figure out the issue? Please let me know if you still need some help and we can work through it together.
Nope, I followed your Flask repo and did that same. But I really want to run that in just Python and not on Flask. I do have limited knowledge on asyncio. Will be learning that soon. I've shared the error and the complete code I'm using the same thread.
Ok, so if I understand correctly you follwed the Flask example in the tutorial but still having some issues? Is the issue still with PyAudio?
Also, is this the error message you received? (I want to make sure this is the correct error):
input_audio = stream_in.read(3200)
await ws.send(input_audio)
DEBUG:websockets.client:< CLOSE 1008 (policy violation) DATA-0000 [11 bytes]
Sorry to misled you!
Actually I wanted to directly send the audio feed using PyAudio to the Deepgram websocket (that's when the above error is occurring).
But I found your Flask tutorial and used that instead which worked in the first go.
The complete code I used can be found here.
Oh nice! Good to hear you found a solution with the tutorial 😄.
About asyncio, yea, I totally understand it can be very confusing. It took me awhile to wrap my head around it. How do you plan on learning asyncio? Tutorials? Blog posts? Videos? Something else?
Gonna read through this for a while and try some hands-on stuff.
docs.python.org/3/library/asyncio....
I'll try to make a tutorial here once I get a good grasp.
Wonderful! Make sure to let me know when it's published so I can read it :)
You got it!
How easy or straightforward is it to integrate with a text based chatbot? Any examples?
Good question. I suppose it depends on what you're trying to do. Because Deepgram is a speech-to-text API, are you looking for users to ask a question to the bot rather than type? If so, that's pretty straightforward. You can get the transcript of the person speaking and send that text to the chatbot.
I don't know of any specific examples of sending it to a chatbot, but we have several examples of taking real-time audio and transcribing it. That link will show several pieces of documentation and many blog posts that are using it.
Yes mostly on the usecase - talk to bot instead of type; any integrations with intent classifiers (RASA/Diaglogflow)?
I don't think we've built a demo for those yet. Very interesting. I'd love to see that in action.
I created Deepgram account. But How do i
Select one of the following four categories
I don't see any of this options on the Deepgram website
The instructions said "Select one of following categories," but it isn't clear that you're really selecting it in your mind. You're deciding what category you want to build a project for. When you create a submission you'll use this template to create your submission post. That template has a section where you'll enter what category you're submitting your project for.
Thanks, It's helpful
Hi all,
Can we use deepgram in react.js ?
You can use Deepgram with React. Our primary tech stack uses Vue, so many of our blog post examples do as well. You can take a look at those and see that React would work as well.
Thanks, got it.😍🔥