The Realtime API is a game changer and the reference implementations are quite good to get started. However, I wish there was some cookbook that shows the events and UX cases that OpenAI handled in the Advanced Voice Mode – this will help us create similar apps. For example, I just got a POC done …

[image] stevenic: What’s the issue with silence? I’ve verified that you’re not charged by OpenAI for silence. Twilio you are of course. Standard practice with voice calls is to typically timeout after a period of inactivity since its easy enough to measure how long silence has been going on. Al…

[image] alden: How to implement interruptions correctly? (sometimes the Realtime API keeps talking for a minute) One thing to note is that the cost of output is based on generated tokens and not minutes. The importance of that is that generation of the audio happens a lot faster then the play…

[image] alden: How to handle silence? What’s the issue with silence? I’ve verified that you’re not charged by OpenAI for silence. Twilio you are of course. Standard practice with voice calls is to typically timeout after a period of inactivity since its easy enough to measure how long silence…

I worked on IVR systems back in the 90’s before I joined Microsoft in 2003. The Microsoft Bot Framework started from my hackathon project so it feels like I’ve been working on chat bots for almost 30 years :slight_smile: There’s a lot of tricks, like pre-recorded responses, that are still very muc…

One thing to note is that the cost of output is based on generated tokens and not minutes. The importance of that is that generation of the audio happens a lot faster then the playback. You can terminate the audio playback but it’s not going to save you any money because the audios already been gen…

[image] stevenic: What’s the issue with silence? I’ve verified that you’re not charged by OpenAI for silence. Twilio you are of course. Standard practice with voice calls is to typically timeout after a period of inactivity since its easy enough to measure how long silence has been going on. A…

[image] stevenic: I worked on IVR systems back in the 90’s before I joined Microsoft in 2003. The Microsoft Bot Framework started from my hackathon project so it feels like I’ve been working on chat bots for almost 30 years :slight_smile: Nice – Yeah – it feels like we need to dust out some o…

Realtime API - What events should be handled? (e.g. for call centers)

API

alden October 16, 2024, 4:43pm 12

UPDATE: Just posted the source code for the POC : OpenAI Realtime API w/ Twilio + RAG == AI Call Center

2 Likes

Topic		Replies	Views
OpenAI Realtime API w/ Twilio + RAG == AI Call Center Community project , rag , realtime	8	5869	December 22, 2025
How to manage user silence in Twilio calls? [openai realtime api] API api-realtime	7	782	December 11, 2025
Realtime api phone use case - speaking text Feedback assistants-api , realtime	16	2192	November 5, 2024
Background Noise Interfering with Realtime API Using Phone API realtime	14	5857	July 31, 2025
SIP Trunking + Realtime API Call Flow — Initial Greeting Delay & Language Mismatch API realtime , api-realtime , gpt-realtime	4	267	November 18, 2025

Realtime API - What events should be handled? (e.g. for call centers)

Related topics