I am experiencing significant latency with the Gemini 2.0 flash multimodal life API when streaming voice. Text-based queries receive near-instantaneous responses, but audio input results in delays of several minutes. Is this expected behavior? I understand this issue will be resolved after the 31st with the release of the new production version. The system functioned flawlessly for fifteen days prior to this problem.he past week, it hasn’t worked. The same thing is happening even with Google Studio.
Sorry for the off-topic, but I came across your post and was wondering: how do you know Google will release a new production version of Gemini 2.0 Flash?
Many Gemini services are slated for release on the 31st (Gemini Developer API Pricing | Gemini API | Google AI for Developers), hence my statement. It’s a conjecture.
1 Like