Tool call audio output silence

acknowledged

2 independent reportsacross 1 sourceon 5 stackslast reported 2026-02-06

What this is

After the agent completes one or more tool calls within a turn, its spoken response never gets synthesized, leaving the caller in silence.

Status acknowledged: the thread it was reported in was acknowledged upstream.

Evidence

Jaya-sys2026-02-06deepgramlivekitsileroGitHub issuesgithub.com/…/4729
...livekit.agents: expected to receive only one AgentTask from the tool executions"""" After this error: No audio response is returned No fallback or partial response is produced The call/session becomes silent...

First seen 2026-02-06 · our copy fetched 2026-08-10T13:48:55Z · SHA-256 of that copy begins ff375d9702ac4e03… · profile

sibblegp2025-07-17openai-agentsopenai-realtimeGitHub issuesgithub.com/…/1168
...were those times again?" then it responds. See this trace: [Imgur](https://imgur.com/a/BCjukuj) Note there is no audio out after the tool calls. ### Debug information - Agents SDK version: v0.2.1 -...

First seen 2025-07-17 · our copy fetched 2026-07-26T14:05:22Z · SHA-256 of that copy begins 6b3215c5a3151e14… · profile

Quotes run to 30 words around the reported failure and link to the post.Add your call to this entryTake a quote down within 24 hours.

What is measurable

SignalThis record stands on its own linked sources. To put a number on your own call, hotato autopsy ./call.wav reads a recording you already have and ranks the timing incidents in it.
EstablishesEvery report below links to the original post and names the handle that wrote it; the quote is at most 30 words around the reported failure.
What else it establishes, and what your own trace settles
  • The status changes only when a re-check stores the evidence link, the quote and the date behind the change.
  • Every timestamp comes from the fetched artifact it describes, recorded with the sha256 of the response body it was read from.

What your trace settles

  • Reproducing the mode on your own stack is the next step: the reports below carry the configuration each reporter was running.
TierAtlas record: every field on this page traces to a fetched public artifact. hotato is MIT and runs locally, getting started.

Status history

DateStateWhat moved it
2026-08-10fixedacknowledgedissue closed (completed) evidence dated 2026-08-02
2026-08-02openfixedissue closed (completed) evidence dated 2026-08-02

Discussion

Reader discussion of this mode: what fixed it and what did not. The reports above are attributed and linked; a comment is a comment.

Open this discussion on GitHub

The record

Ids, digests, every link this entry stands on, and how to take a quote down
Atlas idVFA-2025-0002
Mode idpat_15da2b2e712d5062cd9ba735
Content digestsha256:15da2b2e712d5062cd9ba7350569c72c4d5dd96b8d2d38449aaa6dcadcd38bcc
First reported2025-07-17
Last reported2026-02-06
First seen by the atlas2025-07-17T15:09:47Z
Last re-checked2026-02-06T05:57:22Z
Reported ondeepgramlivekitopenai-agentsopenai-realtimesilero
SourcesGitHub issues
Scope2 independent public reports across 1 source. This entry states where the mode has been reported; where else it can occur is what the next report settles.
ResolvedA stored artifact shows this mode closed upstream: 2026-08-02. The quote and the date behind each move are in the status history above.
References
  1. reporthttps://github.com/livekit/agents/issues/4729 · Jaya-sys · GitHub issues · 2026-02-06
  2. reporthttps://github.com/openai/openai-agents-python/issues/1168 · sibblegp · GitHub issues · 2025-07-17
Machine surfacesfeed.jsonfeed.atomfeed.schema.jsonatlas.llms.txt
RemovalIf you wrote something quoted on this page and want it gone, one email to atlas-remove@hotato.dev does it. The removal path takes the quote, the handle and the link off this page, out of the feeds and out of the llms.txt within 24 hours, and tombstones the id so the entry cannot quietly return at a new address.