Skip to content

Realtime: Twilio example #1216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 29, 2025
Merged

Realtime: Twilio example #1216

merged 1 commit into from
Jul 29, 2025

Conversation

rm-openai
Copy link
Collaborator

@rm-openai rm-openai commented Jul 22, 2025

@rm-openai rm-openai mentioned this pull request Jul 22, 2025
@rm-openai rm-openai marked this pull request as draft July 22, 2025 17:12
@seratch seratch added feature:realtime documentation Improvements or additions to documentation labels Jul 23, 2025
@rm-openai rm-openai changed the base branch from main to rm/pr1243 July 25, 2025 01:35
@rm-openai rm-openai marked this pull request as ready for review July 25, 2025 01:36
@rm-openai rm-openai requested a review from seratch July 25, 2025 01:36
@rm-openai rm-openai changed the title twilio Realtime: Twilio example Jul 25, 2025
@seratch
Copy link
Member

seratch commented Jul 25, 2025

need to resolve mypy warnings and python 3.9 runtime errors but overall i don't have anything to mention so far

@sibblegp
Copy link

@rm-openai Deeply appreciate your taking the time to figure this out.

@sibblegp
Copy link

@rm-openai When you have a moment, will you explain what is so different about this it needed all this extra work to get the "audio_interrupted" event?

I'm also setting up my own in-app voice which will need interruption. Does this mean I'll need to send and handle "mark" events similar to this or will it work more like your demos?

Thanks!

@sibblegp
Copy link

Would love to get this merged and a new version pushed so I can put it out on production. Thanks!

rm-openai added a commit that referenced this pull request Jul 29, 2025
So far, we've been assuming that audio is played:
- immediately (i.e. with 0 delay/latency)
- at realtime

This causes issues with our interrupt tracking. The model wants to know
how much audio the user has actually heard. For example in a phone call
agent, this wouldn't work (bc theres a delay of a few hundred ms between
model sending audio and the user hearing it). This PR allows you to pass
a playback tracker.






---
[//]: # (BEGIN SAPLING FOOTER)
* #1252
* #1216
* #1243
* __->__ #1242
rm-openai added a commit that referenced this pull request Jul 29, 2025
We need not cancel a response if the server will cancel it.








---
[//]: # (BEGIN SAPLING FOOTER)
* #1252
* #1216
* __->__ #1243
Base automatically changed from rm/pr1243 to main July 29, 2025 18:17
@rm-openai rm-openai merged commit bdc91df into main Jul 29, 2025
10 checks passed
@rm-openai rm-openai deleted the rm/pr1216 branch July 29, 2025 18:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation feature:realtime
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants