Thank you so much. This was useful and has helped me. After 2 weeks of figuring this out. Google should update their AI documentation. They are not sending RAW PCM. Gemini is sending Base64-Encoded Audio.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Suddenly the Gemini Live API stopped understanding input audio | 6 | 543 | November 12, 2025 | |
| Inconsistent Response Behavior in gemini-2.5-flash-native-audio-preview-09-2025 Voicebot | 5 | 516 | January 7, 2026 | |
| Will it be possible to receive text and audio data in the multimodal API? | 13 | 965 | July 22, 2025 | |
| Gemini Live API: token generation suddenly stops | 13 | 863 | October 8, 2025 | |
| How to get text output from gemini-2.5-flash-preview-native-audio-dialog | 4 | 927 | November 3, 2025 |