Repository navigation
gemini-3.8-live emits no VoiceActivity (documented replacement for deprecated speechState) #2981
Description
Activity
Hi @r09528039,
Thanks for the clear explanation! You are right that gemini-3.8-live models do not send VoiceActivity signals at this time.
We are escalating this issue internally to investigate further. If you need voice activity detection right now, please use gemini-3.1-flash-live-preview as a workaround.
We’ll keep you updated on progress. Thanks!
Reacted by r09528039Hi @Venkaiahbabuneelam ,
It looks like gemini-3.8-live now sends voiceActivity (ACTIVITY_START / ACTIVITY_END), which seems like it could fix my issue. Has this been resolved on your end?
Thanks!
Data point for the question above. On 29 and 30 September, with google-genai 2.25.0 (Python) against
gemini-3.8-liveon the Gemini API (AI Studio) and VAD at its default (norealtime_input_config),voiceActivityframes arrived in all 20 sessions with streamed 16 kHz PCM speech.ACTIVITY_STARTcame 139 to 154 ms after the first audio chunk of an utterance while the model was silent, and up to 261 ms while it was speaking;ACTIVITY_ENDcame about 1.2 to 1.3 s after the last speech chunk.On the wire the message is
{"voiceActivity":{"type":"ACTIVITY_START","audioOffset":"0.160s"}}, and the SDK exposed it asvoice_activity_type. One detail: a second utterance starting 0.3 s after the previous one got noACTIVITY_STARTof its own; the server merged both into one.Raw JSONL timelines and the clips: https://github.com/frontier-on-cloud/gemini-live-stop-test (
results/audio_*.jsonl, eventsraw_vadandvoice_activity).Reacted by r09528039
The Live API reference marks
speechStateas deprecated: "Use VoiceActivity instead". gemini-3.1-flash-live-preview emitsvoiceActivity(top-level,ACTIVITY_START/ACTIVITY_ENDwithaudioOffset) on both v1alpha and v1beta. gemini-3.8-live and gemini-3.8-live-extended-thinking emit nothing during user speech.VoiceActivityis referenced by the deprecation note but not defined on the reference page nor listed in the BidiGenerateContentServerMessage union.Is the absence of any server-side voice-activity signal on 3.8 intended?