Skip to content

Development of Voice AI Gateway for Google, Microsoft, and Amazon Engines

RejectedGrant Request

Proposal Details

Author0xb350…8e04
PublishedDec 22, 2022 12:23
Voting beginsDec 22, 2022 12:23
Voting endsJan 05, 2023 12:23
Snapshot#c996284

Grant size

60,000 USD

Tier

Tier 4

Beneficiary

0xb350…8e04

Description

**Example Use Cases** Conversational AI can be used to power voice assistants or chatbots in Decentraland in such cases as: * Automate FAQs and users' onboarding process with a voice-powered assistant (to help visitors at events, games, shops, etc.) * Create AI-driven in-game characters * Automate sales interactions (take payments, check refund statuses, balances and more) * Power smart real estate agents (deliver information on parcel location, property details etc. ) * Create a Siri-like voice assistant that helps users navigate around Decentraland * Many other things, just like in the real world \   **Working prototype** [Try it here](https://dcl.voctiv.com/ "") (loads 3-5 minutes). Instructions to use the prototype: 1. Allow your browser to use your microphone when requested 2. Approach the NPC (the dog) - if you are close enough a pop-up with “Hello” will appear. This will launch the voice bot 3. Wait for the voice greeting from the NPC 4. You may ask the NPC the following questions: * Who are you? * What is your name? * How are you? * How many players are online? * Which districts are presented in Decentraland? * Where I can buy some art or NFTs? * Any great events (happening)? * Where I can go? What is interesting right now? 5. When finished you can say “goodbye” to the NPC ![](https://i.ibb.co/wRy2vYN/dcl-mvp.png "Screenshot of prototype") **Decription** We are going to develop a package that will: * Grab voice from the DCL scene * Pass the voice to Middleware * Connect Middleware to a number of existing platforms with speech-to-text engines and natural language understanding engine capabilities, where the voice would be processed and return a result and commands back to Decentraland * According to the command received from the platform by Decentraland, the voice bot will continue communication with the user and proceed with all necessary transactions if needed

Voting Power

01M2MRequired to pass12/2212/2612/2901/0101/05
YesNo

9 Comments

InaJul 24, 2023

have a lot of opensource ways to do it (speech to text and viceversa, and chatbots). Im sure in the next months this software will be improved (specially opensource chatbots). The option to capture the player voice from decentraland its interestingm the other things i have maked it for the gamejam lucid dreams in a week of work.

daoJan 05, 2023

Development of Voice AI Gateway for Google, Microsoft, and Amazon Engines This proposal is now in status: REJECTED. Voting Results: * Yes 1% 71 VP (65 votes) * No 99% 6,704,899 VP (157 votes)

CheddarQuesoJan 03, 2023

I like the idea of voice features but I don't think we are there yet. I agree with Nikki.

NikkiFuegoDec 30, 2022

I voted no because I personally do not think this is something that DCL needs at the moment. I think there are accessibility needs that should be addressed before voice commands. I also have a huge concern with centralized software mixing with voice recognition/recordings. There are already a lot of unethical issues going on with anything related to voice comms on the internet and inviting those into web3 I feel would be taking steps back. If this was done without the need for Google, Amazon, etc then I think it would be cool, but again I don't think the timing is super warranted. This seems like it would be a feature included with any VR integrations/development.

IliaSpirinDec 26, 2022

Hey everyone, as a member of the team that made this project, I'm biased but still, we have a lot of ideas for implementing Voice AI for Decentraland. For example, the GPT3 can also be implemented using our connector - so there are a lot of cool things that can be done here. Please play with our working prototype (links and instructions are in the grant description) to have an idea about the project. **If you voted "No" please share your thoughts on that - what is wrong with our project here? What we can change or add to bring value to the community?** Thanks!

pabloDec 24, 2022

I dont think there are not much other games implementing voice commands, I think it's cool and innovative idea to start exploring. But, will Foundation accept a pull request? afaik Foundation is still owner of the code. Any alternative? with browser extension maybe?

IliaSpirinDec 22, 2022

Hi, member of the developers' team here. let me add a bit to our documentation. Only open-source code will be added to the kernel, it allows Decentraland scene to establish a connection to the WebRTC server via an open protocol. WebRTC server is also open source, and due to that, anyone can create anything on top of that code. Connectors to Google, Amazon, and all other platforms are optional, but we want to empower content creators and give them easy access to integration with the most popular speech engines Let me know If there are any other questions.

TudamoonDec 22, 2022

That's a "disrespectful" question and is leading. If you are genuinely concerned, maybe you would ask "nicely" and in a non-bias way. Don't worry I am told that all the time also.

HPrivakosDec 22, 2022

Do we really want to introduce proprietary and centralized technologies in the kernel and ECS?