i am collecting agent usage summary for openai rea...
# ask-ail
late-helmet-58096
09/12/2025, 4:41 AMi am collecting agent usage summary for openai realtime models is return correct data but gemini realtime not given to me output audio data this gemini data : {"llm_prompt_tokens": 4600, "llm_prompt_cached_tokens": 0, "llm_input_audio_tokens": 15, "llm_completion_tokens": 154, "llm_output_audio_tokens": 0, "tts_characters_count": 0, "tts_audio_duration": 0.0, "stt_audio_duration": 0.0} and this openai data : {"llm_prompt_tokens": 2060, "llm_prompt_cached_tokens": 1408, "llm_input_audio_tokens": 1455, "llm_completion_tokens": 1753, "llm_output_audio_tokens": 1346, "tts_characters_count": 0, "tts_audio_duration": 0.0, "stt_audio_duration": 0.0} why
t
tall-airline-16756
09/12/2025, 4:41 AMThanks for reaching out, biberim45. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
tall-airline-16756
09/12/2025, 4:41 AMI'd love to help you out! Could you please share a bit more about your setup and how you're using it? Specifically:
• Are you working with the same input data and configuration for both the Gemini and OpenAI models?
• What kind of audio output are you expecting from the Gemini model?
• Are there any particular settings or parameters you've applied to the Gemini model that might be influencing its output?
l
late-helmet-58096
09/12/2025, 4:44 AMactual i cant get "llm_output_audio_tokens": 0, this data actually gemini is speaking but llm output audio tokens not increased, must be increased i use gemini realtime model how can i get llm output audio tokens
t
tall-airline-16756
09/12/2025, 4:44 AMI don't have the answer you're looking for.
You could also try asking your question:
• in one of the other Slack channels
or
• to https://deepwiki.com/livekit/livekit_composite which is trained on all LiveKit source code
If you find the answer, please post it here to help others!
3 Views