# Session.say() hangs indefinitely (~20s+) when using Gemini RealtimeModel(gemini 3.1) as llm together with google.beta.GeminiTTS as tts; session.input.set\_audio\_enabled() / aec\_warmup\_duration do not reliably block user interruption in this configuration

**URL:** <https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448>\
**Category:** Getting Started\
**Tags:** python, realtime, gemini, google\
**Created:** [June 17, 2026, 9:58am UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448 "2026-06-17T09:58:40Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jayesh\_Shinde](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/jayesh_shinde/32/1508_2.png) [@Jayesh\_Shinde](https://community.livekit.io/u/Jayesh_Shinde)\
**Post date:** [June 17, 2026, 9:58am UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448/1 "2026-06-17T09:58:40Z")

</div>

### Summary

When using `llm=google.beta.realtime.RealtimeModel` (`gemini-3.1-flash-live-preview`) together with a **separate** `tts=google.beta.GeminiTTS(`gemini-3.1-flash-tts-preview`)` instance on the same `AgentSession`, a sequence of two `session.say()` calls used to deliver a scripted greeting reliably hangs on the second call for ~20 seconds with no logs, no exception, and no `say()` completion — even though `allow_interruptions=False` is set and `session.input.set_audio_enabled(False)` was called beforehand. The same code path works correctly when `tts` is swapped for a non-Google provider (e.g. `sarvam.TTS`), with both calls completing in well under 2 seconds combined.

Separately, even when the hang is not occurring, we’ve observed that `session.input.set_audio_enabled(False)` and the session’s `aec_warmup_duration` interruption window do not compose as expected. The AEC-warmup-based interruption suppression appears to be a fixed timer independent of how long the `say()` calls actually take, so it can expire mid-greeting and let STT-detected noise/echo interrupt the agent before our manually-disabled input window ends.

### Environment

- `livekit-agents` version: ~=1.5
- Realtime model: `gemini-3.1-flash-live-preview`
- TTS (problem case): `google.beta.GeminiTTS`, model `gemini-3.1-flash-tts-preview`, voice `Sulafat`
- TTS (working case): `sarvam.TTS`, model `bulbul:v3`
- `AgentSession(aec_warmup_duration=6, ...)`

### Code

python

```python
session = AgentSession[Call_State](
    userdata=call_state,
    llm=realtime_model,  
    tts=tts_model,
    user_away_timeout=user_away_timeout,
    aec_warmup_duration=6,
)

```

python

```python
session.input.set_audio_enabled(False)
logger.warning("disabling the user input for saying the Hello and first intro!!")

await session.say(
    "Hello",
    audio=audio_frames_from_file(
        file_path=f"src/assets/audio_files_for_hello/{audio_file}",
    ),
)
logger.warning("said hello!!")

await asyncio.sleep(1.5)

await session.say("Hey there, I am an AI calling bot. Can we have a quick chat?")
logger.warning("said second sentence from the script") # <-- never reached for ~20s

session.input.set_audio_enabled(True)
logger.warning("enabled the user input")

```

---

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [June 17, 2026, 12:54pm UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448/2 "2026-06-17T12:54:48Z")

</div>

Interesting, I believe this could just be the start up time of the `gemini-3.1-flash-tts-preview` model rather than anything you or the plugin is doing wrong.

Unfortunately, I need to request a new key before I can look into this further / properly, which will take a few days. I do see some external reports about slow startup time, but nothing internally.

---

<div class="post-metadata">

**Author:** ![Muhammad\_Usman\_Bashir](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/muhammad_usman_bashir/32/1149_2.png) [@Muhammad\_Usman\_Bashir](https://community.livekit.io/u/Muhammad_Usman_Bashir)\
**Post date:** [June 17, 2026, 7:16pm UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448/3 "2026-06-17T19:16:25Z")

</div>

@Jayesh_Shinde, That startup-time read fits, and your own code pins it down: the hang is on the second `say()` because the first one plays a file. `say()` with an `audio=` argument streams those frames directly and never invokes the TTS [[livekit/agents voice/agent\_activity.py](https://github.com/livekit/agents/blob/main/livekit-agents/livekit/agents/voice/agent_activity.py) ], so your “Hello” never touches `GeminiTTS`. The second call has no `audio=`, so it goes through the `tts`, making it `GeminiTTS`’s first real synthesis of the session, exactly where a preview-model cold start lands. `Sarvam`’s first synth just warms faster.

You can confirm this today without waiting on the key: warm `GeminiTTS` once at session start, before the first `say()`. `synthesize()` just produces frames you drain, so nothing is published to the caller:

```auto
async for _ in tts_model.synthesize("warmup"):
    pass

```

If that call absorbs the `~20s` and the live greeting is then fast, it’s `GeminiTTS` first-request latency and pre-warming hides it. If even the warmup hangs with no completion, it’s not cold start and a minimal repro on `livekit/agents` is worth filing; I didn’t find an existing one.

The `aec_warmup_duration / set_audio_enabled` behavior is a separate code path; I’d pin the say hang first, then isolate that on its own.

---

<div class="post-metadata">

**Author:** ![Jayesh\_Shinde](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/jayesh_shinde/32/1508_2.png) [@Jayesh\_Shinde](https://community.livekit.io/u/Jayesh_Shinde)\
**Post date:** [June 18, 2026, 10:03am UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448/4 "2026-06-18T10:03:41Z")

</div>

No difference!!  
Expected a lag in the initial part.

```python
async for _ in tts_model.synthesize("warmup"):
    pass

```

Then after the first ‘Hello’, the behaviour was the same as earlier.

---

<div class="post-metadata">

**Author:** ![system](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/system/32/26_2.png) [@system](https://community.livekit.io/u/system)\
**Post date:** [July 3, 2026, 10:04am UTC](https://community.livekit.io/t/session-say-hangs-indefinitely-20s-when-using-gemini-realtimemodel-gemini-3-1-as-llm-together-with-google-beta-geminitts-as-tts-session-input-set-audio-enabled-aec-warmup-duration-do-not-reliably-block-user-interruption-in-this-configuration/1448/5 "2026-07-03T10:04:11Z")

</div>

This topic was automatically closed 15 days after the last reply. New replies are no longer allowed.