31–40 of 71 posts
is there an open source variant available? I am building https://github.com/bolna-ai/bolna which is an open source voice orchestration. would love to have something like this integrated as part of our open source stack.
I'll reach out async!
AI voice agents are weird to me because voice is already a very inefficient and ambiguous medium, the only reason I would make a voice call is to talk to a human who is equipped to tackle the ambiguous edge cases that the engineers didn't already anticipate. If you're going to develop AI voice agents to tackle pre-determined cases, why wouldn't you just develop a self-serve non-voice UI that's way more efficient? Why…
- I am dictating this message through macOS's voice to text right now
- I am a huge user of Google Assistant
- I prefer to call people versus texting them
- I tend to call restaurants instead of using something like Toast to order takeout (although this is partially because online services will add a surcharge onto the price sometimes, and sometimes I need to ask questions about dietary restrictions, etc.)
Generally, wherever possible, I will use a voice interface versus a text based one to get my point across. It's just faster and more convenient for me. I'm pretty neutral on the consumption side: I read and listen to audiobooks in roughly equal amounts.
All that to say that, just like there are people out there who prefer text UIs, there are also people who prefer voice interfaces.
AI voice agents are weird to me because voice is already a very inefficient and ambiguous medium, the only reason I would make a voice call is to talk to a human who is equipped to tackle the ambiguous edge cases that the engineers didn't already anticipate. If you're going to develop AI voice agents to tackle pre-determined cases, why wouldn't you just develop a self-serve non-voice UI that's way more efficient? Why…
I'm the same way, and I don't have any data on this, but it's possible that we're in the minority. This probably isn't the case, but hopefully anyone implementing such a system has thought through whether it will actually provide any value. For example, if you had an existing IVR system and you tracked menu options and found that a significant portion of calls were able to be answered by non-smart pre-recorded messag…
There is not even one reliable and proven "voice agent" yet (correct me if I'm wrong but the best available, elevenlabs, isn't that great yet to be a voice agent) but there is already companies selling the test of voice agents? Selling shovels on a gold rush seems to have become the only one mantra here.
As a test, I asked GPT to call my phone company and get my account balance. It worked and even declined some program they tried to sign me up for. Blew my mind.
is there an open source variant available? I am building https://github.com/bolna-ai/bolna which is an open source voice orchestration. would love to have something like this integrated as part of our open source stack.
Bolna looks awesome! We've considered going open-source, but we're not sure how to effectively manage a community. I'll reach out async!
There is not even one reliable and proven "voice agent" yet (correct me if I'm wrong but the best available, elevenlabs, isn't that great yet to be a voice agent) but there is already companies selling the test of voice agents? Selling shovels on a gold rush seems to have become the only one mantra here.
Making current voice agents reliable is incredibly time-consuming and complex. This challenge has kept many teams from pushing their agents into production. Those who do launch often release a very limited, basic version to minimize risk. We frequently talk to teams in both camps.
As a result, there aren't many 'killer' voice products on the market right now. But as models improve, we'll see more voice-centric companies emerge.
Teams are already calling their agents by hand and keeping track of experiment runs in a spreadsheet. We're just automating the workflow and making it easier to run experiments!
This is great to see. Evals on voice are hard - we only have evals on text based prompting, but it doesn't fully capture everything. Excited to give this a try.
I work in the telecom space. I don't think this paradigm will get adopted in the near future. Customers are already building voice bots on top of Google Dialogflow e.g. Cognigy. Cognigy does have LLM capabilities, but it is not widely adopted. I think voice bots will still have to be manually configured for some time.