[dandaka]

Can I connect it to my skills/tools? Example case, I have a knowledge base and event log in my company. I need a brainstorm companion, which will have full access to this knowledge, can converse about it and can invoke skills/tools available in the repo.

[athyuttamre]

In ChatGPT, Voice doesn't yet support connectors, but we're hoping to add support soon! Once GPT-Live launches in the API, you can also build custom integrations yourself.

[asats]

+1 to the op. This is one of the first things I thought about after using it for a few minutes. I have a large collection of local knowledge bases that I use through codex, having this real time thing be able to plug into it would be the killer feature, otherwise the utility is severely limited. I don't want to talk to it about the weather, I want to brainstorm about the things I am working on, which it currently knows nothing about.

[BoorishBears]

Do integrations supporting streaming input?

One big gap I've run into for UX is most realtime voice harnesses wait for a full response from tools, and at most support the model filling the dead air until then

It'd be a game-changer to be able to have the model start replying with partial information streamed from the tool call, then seamlessly continue with additional information.

[alooPotato]

honestly its not that big of a deal, being able to call tools is the high order bit

[BoorishBears]

It rubs me the wrong way that someone would respond to something I need with 0 context just to tell me it's not a big deal.

Some people have standards in what they build.

[alooPotato]

ok sorry - can you explain more why it'd be a game changer to stream the tool call. Whats an example tool call that this would help with. Most of the time the tools I want called are at the end of the conversation (i.e. "summarize what we talked about and email it to me"). Or if its in the middle of the conversation, we can just carry on the conversation while the tool call is happenning in parallel..

[BoorishBears]

"It'd be a game-changer to be able to have the model start replying with partial information streamed from the tool call, then seamlessly continue with additional information."

You can't continue a conversation if it hinges on information that takes inherently takes 30+ seconds to generate. Previously even models that "handle it" can only play for time.

You can try and simulate this by messing with model context mid-conversation but that breaks down reliability massively as the model loses track of what it's talking about.