# Live API latency spikes

**URL:** <https://discuss.ai.google.dev/t/live-api-latency-spikes/106814>\
**Category:** Gemini API\
**Tags:** api, bug, models, gemini-2-5, live-streaming\
**Created:** [October 3, 2025, 7:14am UTC](https://discuss.ai.google.dev/t/live-api-latency-spikes/106814 "2025-10-03T07:14:00Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![OverFitter](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/overfitter/32/66675_2.png) [@OverFitter](https://discuss.ai.google.dev/u/OverFitter)\
**Post date:** [October 3, 2025, 7:14am UTC](https://discuss.ai.google.dev/t/live-api-latency-spikes/106814/1 "2025-10-03T07:14:01Z")

</div>

Using Live API with `gemini-live-2.5-flash-preview` on a `audio/pcm;rate=8000` audio chunks stream and streaming responses, the latency sometimes spikes and the wait time goes to 7-15 seconds to first token (measuring from audio stream end). Narrowing down the problem, the most latency is coming from transcription (`server_content.input_transcription`) which took up to 30 seconds during testing (measuring from audio stream beginning)

Here is config we are using:  
`config = types.LiveConnectConfig( `  
` realtime_input_config=types.RealtimeInputConfig(`  
` automatic_activity_detection=types.AutomaticActivityDetection(`  
` start_of_speech_sensitivity=types.StartSensitivity.START_SENSITIVITY_HIGH,`  
` end_of_speech_sensitivity=types.EndSensitivity.END_SENSITIVITY_LOW,`  
` silence_duration_ms=int(silence_duration * 1000),`  
` ),`  
` turn_coverage=types.TurnCoverage.TURN_COVERAGE_UNSPECIFIED,`  
` ),`  
` response_modalities=[“TEXT”],`  
` system_instruction=types.Content(`  
` parts=[types.Part.from_text(text=f"{preprompt}\n{system_instruction}")],`  
` role=“user”,`  
` ),`  
` media_resolution=“MEDIA_RESOLUTION_MEDIUM”,`  
` input_audio_transcription=dict(),`  
` speech_config=types.SpeechConfig(`  
` language_code=language_iso_code,`  
` voice_config=types.VoiceConfig(prebuilt_voice_config=types.PrebuiltVoiceConfig(voice_name=“Puck”)),`  
` ),`  
` context_window_compression=types.ContextWindowCompressionConfig(`  
` trigger_tokens=25600,`  
` sliding_window=types.SlidingWindow(target_tokens=12800),`  
` ),`  
`)`

---

<div class="post-metadata">

**Author:** ![Mahesh\_Sutar](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mahesh_sutar/32/31644_2.png) [@Mahesh\_Sutar](https://discuss.ai.google.dev/u/Mahesh_Sutar)\
**Post date:** [November 25, 2025, 8:46am UTC](https://discuss.ai.google.dev/t/live-api-latency-spikes/106814/3 "2025-11-25T08:46:39Z")

</div>

Hello  
welcome to the forum!!

the random 15–30s latency spikes because of Using `END_SENSITIVITY_LOW` on 8kHz audio is problematic. The model interprets background line static as “whispering,” causing it to keep the turn open until the hard server timeout (~30s).

**The Solution:**

**Set Sensitivity to HIGH:** `end_of_speech_sensitivity=HIGH`. This forces the model to ignore the static.

**Increase Silence Duration:** Set `silence_duration_ms=1000`. Since sensitivity is high, this 1-second buffer ensures natural pauses aren’t cut off.

**Remove `media_resolution`:** This parameter is for video/images only and should be removed from audio-only configs to keep things clean.

Thanks