Distorted & Sped Up Audio

[ronny-horst-taod]

This issue is for a: (mark with an x)

- [x] Bug report -> Please search issues before submitting
- [ ] Feature request
- [ ] Documentation issue or request
- [ ] Regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

I’m encountering intermittent issues where the audio from the real-time speech API starts by slowing down, then speeds up, resulting in distorted output. I suspect this may be related to how audio is handled during network congestion, particularly when many response.audio.deltas are sent in rapid succession. I’ve attempted various methods to reproduce the error, such as network throttling and lowering Azure OpenAI limits, but have not been able to reproduce it consistently. Is this a known issue?

Any log messages given by the failure

Unfortunately, there are no log messages or errors associated with this behavior.

Expected/desired behavior

Audio should play normally without distortion.

OS and Version

Windows 11