# AI\_coustics blocking pipeline (?)

**URL:** <https://community.livekit.io/t/ai-coustics-blocking-pipeline/876>\
**Category:** Getting Started\
**Created:** [April 15, 2026, 7:58pm UTC](https://community.livekit.io/t/ai-coustics-blocking-pipeline/876 "2026-04-15T19:58:16Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Alexander\_Mehregan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/alexander_mehregan/32/157_2.png) [@Alexander\_Mehregan](https://community.livekit.io/u/Alexander_Mehregan)\
**Post date:** [April 15, 2026, 7:58pm UTC](https://community.livekit.io/t/ai-coustics-blocking-pipeline/876/1 "2026-04-15T19:58:16Z")

</div>

Hi all,

I’m seeing an intermittent but severe failure in a Python LiveKit Agents deployment and wanted to check whether anyone else has run into this.

Setup:

- LiveKit Agents Python SDK 1.5.2
- Python worker
- ai-coustics noise cancellation enabled with the Quail model

What happens:

- A session is running normally
- The last normal log is typically something like the user beginning to speak
- After that, there is a long gap with no STT events, no transcription events, and no downstream activity
- Eventually the worker is killed by the supervisor with logs like:
  - `process is unresponsive, killing process`
  - exit code `-10`

What makes this concerning is that the failure appears to happen before STT is activated, so it looks like the audio/input pipeline is getting blocked upstream rather than a normal STT/LLM/TTS exception. There is no useful traceback when it happens.

Current hypothesis:  
I suspect the issue may be related to ai-coustics Quail in the input pipeline, possibly blocking or stalling audio processing under some conditions. I’m removing ai-coustics for now to see whether the issue disappears.

Questions:

1. Has anyone seen ai-coustics / Quail cause worker hangs or audio pipeline stalls in Python agents?
2. Are there recommended timeout / watchdog / fallback patterns for the audio input path?
3. If this is not likely ai-coustics, are there other parts of the pre-STT pipeline I should inspect first?

Any guidance would be really appreciated. This is intermittent but production-impacting because it causes the whole worker handling the session to die.

---

<div class="post-metadata">

**Author:** ![Pawel\_Lach](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/pawel_lach/32/1127_2.png) [@Pawel\_Lach](https://community.livekit.io/u/Pawel_Lach)\
**Post date:** [April 21, 2026, 8:27am UTC](https://community.livekit.io/t/ai-coustics-blocking-pipeline/876/2 "2026-04-21T08:27:40Z")

</div>

Hi Alexander,

Thanks for the details - we’re actively investigating and have a local repro setup running. A few things would help us narrow it down:

1. How long does a session usually run before it hangs? Any pattern around long pauses or inactivity?
2. Where is the pipeline running? Cloud VM / container / local — and rough CPU + RAM specs?
3. How many concurrent sessions per worker when it happens?
4. Any additional logs from just before the “process unresponsive” kill would be very useful.

Will keep you posted. Thanks for your patience!

---

<div class="post-metadata">

**Author:** ![Alexander\_Mehregan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/alexander_mehregan/32/157_2.png) [@Alexander\_Mehregan](https://community.livekit.io/u/Alexander_Mehregan)\
**Post date:** [April 21, 2026, 9:06am UTC](https://community.livekit.io/t/ai-coustics-blocking-pipeline/876/3 "2026-04-21T09:06:04Z")

</div>

Hi Pawel,

Thanks for looking into this. Quick update first: since removing ai\_coustics from the  
input pipeline on Apr 17, we have not seen a single occurrence of the  
“process is unresponsive, killing process” signature. For reference, prior to that  
we had several hundred occurrences of that exact issue going back to Feb 26, with the most recent  
one on Apr 15 14:05 UTC. So the correlation is strong on our side, though not a  
definitive causal proof.

Answers to your questions based on what we observed prior to removal:

1. Session length / pattern before the hang

2. Where the pipeline runs

3. Concurrency per worker

4. Logs just before the kill

Happy to share any other information we can to assist in the local repro.

Thanks again.