Viewing profile — AustinZzx

Glad you like it!

Hey think about the bright side of voice AI -- there are new opportunities like AI companions, AI assistant, not only the antiquated contact methodologies.

The doc is here: https://docs.retellai.com/guide/phone-setup

Deepgram TTS is pretty fast, but they have not publicly launched yet.

We will keep that in mind. In the meantime, if you have a working version, we are happy to feature your integration repo in our doc.

Voice cloning is definitely on our roadmap.

If you are referring to the LLM used in the demo, it's a simple GPT. If you are referring to audio data, there are some (not a lot) public datasets, although be careful of the lice…

We are dedicated to preventing that from happening. Spam calling and identity theft are key areas we will build guardrails around. Feel free to let us know if you think of any othe…

Good point, note token. benchmarking is a great tool to show differentiation. BTW, apart from what we think is important ourselves (latency, mean opinion score, etc), would you min…

Nice catch on the working -- customer is indeed more accurate than user. For outage handling: we strive to keep up 99.9 plus up time, and in the case of a dropped call, the agent w…

Thank you for the support!

Yes, we are a developer tool, and we certainly get interest from clients working on customer satisfaction agents, call center agent training, etc.

I totally get that clicking in Web UI is super convenient in many scenarios, and I think GUI and voice can co-exist and create synergy. Suppose AI voice agent can solve your proble…

We are actively working on that. Thanks for the support.

Could you elaborate a bit on "my speech engine tied to a specific model provider"? Sorry, I might be lacking some context on what you are referring to here.

You certainly could, given you play video games for long enough to gather the needed data lol.

The demo uses a simple gpt 3.5 turbo.

This can be handled with function calling and other features in LLM. We support the input signal of closing the call, and you can have your rule-based (timer) system or LLM-based e…

Yes, I agree there are problems with LLM (hallucinations, persona, etc), and that's exciting because that means room for improvement and opportunities. I know many people who are w…

We handle the audio bytes in / out, and also connect to your user's server for response. We handle the interaction and decide when to listen and when to talk, and send live updates…

Thanks for the support, we still have a lot of work ahead of us to make it better!

Thanks for the support. Means a lot to us.

Good point. Currently, our product does not contain LLM, as we are purely voice API -- instead the developer is bringing in their own LLM solutions and gets to decide what to say. …

We strive to make conversation humanlike, so maybe less contact center ops development, but more focus on performance and customizability of voice interactions. As a startup, our e…

For TTS, we are currently integrating with different providers like Elevenlabs, Openai TTS, etc. We do have plans down the road to train our own TTS model.